%0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 2 %P e23458 %T Using Automated Machine Learning to Predict the Mortality of Patients With COVID-19: Prediction Model Development Study %A Ikemura,Kenji %A Bellin,Eran %A Yagi,Yukako %A Billett,Henny %A Saada,Mahmoud %A Simone,Katelyn %A Stahl,Lindsay %A Szymanski,James %A Goldstein,D Y %A Reyes Gil,Morayma %+ Department of Pathology, Albert Einstein College of Medicine, Montefiore Medical Center, 111 E 210th St, The Bronx, NY, 10467, United States, 1 9493703777, kikemura@montefiore.org %K automated machine learning %K COVID-19 %K biomarker %K ranking %K decision support tool %K machine learning %K decision support %K Shapley additive explanation %K partial dependence plot %K dimensionality reduction %D 2021 %7 26.2.2021 %9 Original Paper %J J Med Internet Res %G English %X Background: During a pandemic, it is important for clinicians to stratify patients and decide who receives limited medical resources. Machine learning models have been proposed to accurately predict COVID-19 disease severity. Previous studies have typically tested only one machine learning algorithm and limited performance evaluation to area under the curve analysis. To obtain the best results possible, it may be important to test different machine learning algorithms to find the best prediction model. Objective: In this study, we aimed to use automated machine learning (autoML) to train various machine learning algorithms. We selected the model that best predicted patients’ chances of surviving a SARS-CoV-2 infection. In addition, we identified which variables (ie, vital signs, biomarkers, comorbidities, etc) were the most influential in generating an accurate model. Methods: Data were retrospectively collected from all patients who tested positive for COVID-19 at our institution between March 1 and July 3, 2020. We collected 48 variables from each patient within 36 hours before or after the index time (ie, real-time polymerase chain reaction positivity). Patients were followed for 30 days or until death. Patients’ data were used to build 20 machine learning models with various algorithms via autoML. The performance of machine learning models was measured by analyzing the area under the precision-recall curve (AUPCR). Subsequently, we established model interpretability via Shapley additive explanation and partial dependence plots to identify and rank variables that drove model predictions. Afterward, we conducted dimensionality reduction to extract the 10 most influential variables. AutoML models were retrained by only using these 10 variables, and the output models were evaluated against the model that used 48 variables. Results: Data from 4313 patients were used to develop the models. The best model that was generated by using autoML and 48 variables was the stacked ensemble model (AUPRC=0.807). The two best independent models were the gradient boost machine and extreme gradient boost models, which had an AUPRC of 0.803 and 0.793, respectively. The deep learning model (AUPRC=0.73) was substantially inferior to the other models. The 10 most influential variables for generating high-performing models were systolic and diastolic blood pressure, age, pulse oximetry level, blood urea nitrogen level, lactate dehydrogenase level, D-dimer level, troponin level, respiratory rate, and Charlson comorbidity score. After the autoML models were retrained with these 10 variables, the stacked ensemble model still had the best performance (AUPRC=0.791). Conclusions: We used autoML to develop high-performing models that predicted the survival of patients with COVID-19. In addition, we identified important variables that correlated with mortality. This is proof of concept that autoML is an efficient, effective, and informative method for generating machine learning–based clinical decision support tools. %M 33539308 %R 10.2196/23458 %U https://www.jmir.org/2021/2/e23458 %U https://doi.org/10.2196/23458 %U http://www.ncbi.nlm.nih.gov/pubmed/33539308 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 2 %P e23427 %T An Automated Patient Self-Monitoring System to Reduce Health Care System Burden During the COVID-19 Pandemic in Malaysia: Development and Implementation Study %A Lim,Hooi Min %A Teo,Chin Hai %A Ng,Chirk Jenn %A Chiew,Thiam Kian %A Ng,Wei Leik %A Abdullah,Adina %A Abdul Hadi,Haireen %A Liew,Chee Sun %A Chan,Chee Seng %+ eHealth Unit, Faculty of Medicine, University of Malaya, Kuala Lumpur, 50603, Malaysia, 60 142204126, ngcj@um.edu.my %K COVID-19 %K coronavirus disease %K home monitoring %K symptom monitoring %K system %K teleconsultation %K development %K eHealth %K digital health %K mHealth %K health services research %K telesurveillance %K infectious disease %K app %D 2021 %7 26.2.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: During the COVID-19 pandemic, there was an urgent need to develop an automated COVID-19 symptom monitoring system to reduce the burden on the health care system and to provide better self-monitoring at home. Objective: This paper aimed to describe the development process of the COVID-19 Symptom Monitoring System (CoSMoS), which consists of a self-monitoring, algorithm-based Telegram bot and a teleconsultation system. We describe all the essential steps from the clinical perspective and our technical approach in designing, developing, and integrating the system into clinical practice during the COVID-19 pandemic as well as lessons learned from this development process. Methods: CoSMoS was developed in three phases: (1) requirement formation to identify clinical problems and to draft the clinical algorithm, (2) development testing iteration using the agile software development method, and (3) integration into clinical practice to design an effective clinical workflow using repeated simulations and role-playing. Results: We completed the development of CoSMoS in 19 days. In Phase 1 (ie, requirement formation), we identified three main functions: a daily automated reminder system for patients to self-check their symptoms, a safe patient risk assessment to guide patients in clinical decision making, and an active telemonitoring system with real-time phone consultations. The system architecture of CoSMoS involved five components: Telegram instant messaging, a clinician dashboard, system administration (ie, back end), a database, and development and operations infrastructure. The integration of CoSMoS into clinical practice involved the consideration of COVID-19 infectivity and patient safety. Conclusions: This study demonstrated that developing a COVID-19 symptom monitoring system within a short time during a pandemic is feasible using the agile development method. Time factors and communication between the technical and clinical teams were the main challenges in the development process. The development process and lessons learned from this study can guide the future development of digital monitoring systems during the next pandemic, especially in developing countries. %M 33600345 %R 10.2196/23427 %U https://medinform.jmir.org/2021/2/e23427 %U https://doi.org/10.2196/23427 %U http://www.ncbi.nlm.nih.gov/pubmed/33600345 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 2 %P e23335 %T Utilization of Telehealth Services in Libya in Response to the COVID-19 Pandemic: Cross-sectional Analysis %A Elhadi,Muhammed %A Msherghi,Ahmed %A Elhadi,Ahmed %A Ashini,Aimen %A Alsoufi,Ahmed %A Bin Alshiteewi,Fatimah %A Elmabrouk,Amna %A Alsuyihili,Ali %A Elgherwi,Alsafa %A Elkhafeefi,Fatimah %A Abdulrazik,Sarah %A Tarek,Ahmed %+ Faculty of Medicine, University of Tripoli, Furnaj, University Road, Tripoli, 13275, Libyan Arab Jamahiriya, 218 945196407, muhammed.elhadi.uot@gmail.com %K COVID-19 %K cross-sectional study %K resource-limited countries %K SARS-CoV-2 %K telehealth %K telemedicine %K transitional countries %K usability %D 2021 %7 26.2.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: Health care systems in transitional countries have witnessed unprecedented challenges related to adequate and continuous health care provision during the COVID-19 pandemic. In many countries, including Libya, institutions and organizations have begun to implement telehealth technology for the first time. This serves to establish an alternative modality for direct physician-patient interviews to reduce the risk of COVID-19 transmission. Objective: This study aimed to assess the usability of telehealth services in Libya and to provide an overview of the current COVID-19 scenario. Methods: In this cross-sectional study, an anonymous web-based survey was administered to Libyan residents between April and May 2020. Participants were contacted through text messaging, emails, and social media. The survey items yielded information on the sociodemographic characteristics, availability and accessibility of health care services, effects of the COVID-19 pandemic on health care services, mental health status, and the feasibility and application of the telehealth system. Results: We obtained 2512 valid responses, of which 1721 (68.5%) were from females. The participants were aged 28.2 (SD 7.6) years, of whom 2333 (92.9%) were aged <40 years, and 1463 (58.2%) were single. Regarding the health care services and their accessibility, 786 (31.1%) participants reported having a poor health status in general, and 492 (19.6%) reported having a confirmed diagnosis of at least one chronic disease. Furthermore, 498 (19.9%) participants reported varying degrees of difficulty in accessing health care centers, and 1558 (62.0%) could not access their medical records. Additionally, 1546 (61.6%) participants experienced problems in covering medical costs, and 1429 (56.9%) avoided seeking medical care owing to financial concerns. Regarding the feasibility of the telehealth system, approximately half of the participants reported that telehealth services were useful during the COVID-19 pandemic, and 1545 (61.5%) reported that the system was an effective means of communication and of obtaining health care services. Furthermore, 1435 (57.1%) participants felt comfortable using the telehealth system, and 1129 (44.9%) felt that they were able to express themselves effectively. Moreover, 1389 (55.3%) participants found the system easy to understand, and 1354 (53.9%) reported having excellent communication with physicians through the telehealth system. However, only 1018 (40.5%) participants reported that communication was better with the telehealth system than with traditional methods. Conclusions: Our study revealed high levels of usability and willingness to use the telemedicine system as an alternative modality to in-person consultations among the Libyan residents in this study. This system is advantageous because it helps overcome health care costs, increases access to prompt medical care and follow-up evaluation, and reduces the risk of COVID-19 transmission. However, internet connectivity and electricity issues could be a substantial barrier for many resource-limited communities, and further studies should address such obstacles. %M 33606654 %R 10.2196/23335 %U https://medinform.jmir.org/2021/2/e23335 %U https://doi.org/10.2196/23335 %U http://www.ncbi.nlm.nih.gov/pubmed/33606654 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 2 %P e26773 %T Rapid Response to Drive COVID-19 Research in a Learning Health Care System: Rationale and Design of the Houston Methodist COVID-19 Surveillance and Outcomes Registry (CURATOR) %A Vahidy,Farhaan %A Jones,Stephen L %A Tano,Mauricio E %A Nicolas,Juan Carlos %A Khan,Osman A %A Meeks,Jennifer R %A Pan,Alan P %A Menser,Terri %A Sasangohar,Farzan %A Naufal,George %A Sostman,Dirk %A Nasir,Khurram %A Kash,Bita A %+ Houston Methodist, 7550 Greenbriar Drive, Houston, TX, 77030, United States, 1 3463561479, fvahidy@houstonmethodist.org %K COVID-19 %K SARS-CoV-2 %K data science %K data curation %K electronic health records %K learning health system %K databases, factual %D 2021 %7 23.2.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: The COVID-19 pandemic has exacerbated the challenges of meaningful health care digitization. The need for rapid yet validated decision-making requires robust data infrastructure. Organizations with a focus on learning health care (LHC) systems tend to adapt better to rapidly evolving data needs. Few studies have demonstrated a successful implementation of data digitization principles in an LHC context across health care systems during the COVID-19 pandemic. Objective: We share our experience and provide a framework for assembling and organizing multidisciplinary resources, structuring and regulating research needs, and developing a single source of truth (SSoT) for COVID-19 research by applying fundamental principles of health care digitization, in the context of LHC systems across a complex health care organization. Methods: Houston Methodist (HM) comprises eight tertiary care hospitals and an expansive primary care network across Greater Houston, Texas. During the early phase of the pandemic, institutional leadership envisioned the need to streamline COVID-19 research and established the retrospective research task force (RRTF). We describe an account of the structure, functioning, and productivity of the RRTF. We further elucidate the technical and structural details of a comprehensive data repository—the HM COVID-19 Surveillance and Outcomes Registry (CURATOR). We particularly highlight how CURATOR conforms to standard health care digitization principles in the LHC context. Results: The HM COVID-19 RRTF comprises expertise in epidemiology, health systems, clinical domains, data sciences, information technology, and research regulation. The RRTF initially convened in March 2020 to prioritize and streamline COVID-19 observational research; to date, it has reviewed over 60 protocols and made recommendations to the institutional review board (IRB). The RRTF also established the charter for CURATOR, which in itself was IRB-approved in April 2020. CURATOR is a relational structured query language database that is directly populated with data from electronic health records, via largely automated extract, transform, and load procedures. The CURATOR design enables longitudinal tracking of COVID-19 cases and controls before and after COVID-19 testing. CURATOR has been set up following the SSoT principle and is harmonized across other COVID-19 data sources. CURATOR eliminates data silos by leveraging unique and disparate big data sources for COVID-19 research and provides a platform to capitalize on institutional investment in cloud computing. It currently hosts deeply phenotyped sociodemographic, clinical, and outcomes data of approximately 200,000 individuals tested for COVID-19. It supports more than 30 IRB-approved protocols across several clinical domains and has generated numerous publications from its core and associated data sources. Conclusions: A data-driven decision-making strategy is paramount to the success of health care organizations. Investment in cross-disciplinary expertise, health care technology, and leadership commitment are key ingredients to foster an LHC system. Such systems can mitigate the effects of ongoing and future health care catastrophes by providing timely and validated decision support. %M 33544692 %R 10.2196/26773 %U https://medinform.jmir.org/2021/2/e26773 %U https://doi.org/10.2196/26773 %U http://www.ncbi.nlm.nih.gov/pubmed/33544692 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 2 %P e23026 %T Learning From Past Respiratory Infections to Predict COVID-19 Outcomes: Retrospective Study %A Sang,Shengtian %A Sun,Ran %A Coquet,Jean %A Carmichael,Harris %A Seto,Tina %A Hernandez-Boussard,Tina %+ Department of Medicine, Biomedical Informatics, Stanford University, 1265 Welch Rd, 245, Stanford, CA, 94305-5479, United States, 1 650 725 5507, boussard@stanford.edu %K COVID-19 %K invasive mechanical ventilation %K all-cause mortality %K machine learning %K artificial intelligence %K respiratory %K infection %K outcome %K data %K feasibility %K framework %D 2021 %7 22.2.2021 %9 Original Paper %J J Med Internet Res %G English %X Background: For the clinical care of patients with well-established diseases, randomized trials, literature, and research are supplemented with clinical judgment to understand disease prognosis and inform treatment choices. In the void created by a lack of clinical experience with COVID-19, artificial intelligence (AI) may be an important tool to bolster clinical judgment and decision making. However, a lack of clinical data restricts the design and development of such AI tools, particularly in preparation for an impending crisis or pandemic. Objective: This study aimed to develop and test the feasibility of a “patients-like-me” framework to predict the deterioration of patients with COVID-19 using a retrospective cohort of patients with similar respiratory diseases. Methods: Our framework used COVID-19–like cohorts to design and train AI models that were then validated on the COVID-19 population. The COVID-19–like cohorts included patients diagnosed with bacterial pneumonia, viral pneumonia, unspecified pneumonia, influenza, and acute respiratory distress syndrome (ARDS) at an academic medical center from 2008 to 2019. In total, 15 training cohorts were created using different combinations of the COVID-19–like cohorts with the ARDS cohort for exploratory purposes. In this study, two machine learning models were developed: one to predict invasive mechanical ventilation (IMV) within 48 hours for each hospitalized day, and one to predict all-cause mortality at the time of admission. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, positive predictive value, and negative predictive value. We established model interpretability by calculating SHapley Additive exPlanations (SHAP) scores to identify important features. Results: Compared to the COVID-19–like cohorts (n=16,509), the patients hospitalized with COVID-19 (n=159) were significantly younger, with a higher proportion of patients of Hispanic ethnicity, a lower proportion of patients with smoking history, and fewer patients with comorbidities (P<.001). Patients with COVID-19 had a lower IMV rate (15.1 versus 23.2, P=.02) and shorter time to IMV (2.9 versus 4.1 days, P<.001) compared to the COVID-19–like patients. In the COVID-19–like training data, the top models achieved excellent performance (AUROC>0.90). Validating in the COVID-19 cohort, the top-performing model for predicting IMV was the XGBoost model (AUROC=0.826) trained on the viral pneumonia cohort. Similarly, the XGBoost model trained on all 4 COVID-19–like cohorts without ARDS achieved the best performance (AUROC=0.928) in predicting mortality. Important predictors included demographic information (age), vital signs (oxygen saturation), and laboratory values (white blood cell count, cardiac troponin, albumin, etc). Our models had class imbalance, which resulted in high negative predictive values and low positive predictive values. Conclusions: We provided a feasible framework for modeling patient deterioration using existing data and AI technology to address data limitations during the onset of a novel, rapidly changing pandemic. %M 33534724 %R 10.2196/23026 %U https://www.jmir.org/2021/2/e23026 %U https://doi.org/10.2196/23026 %U http://www.ncbi.nlm.nih.gov/pubmed/33534724 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 2 %P e21679 %T Lexicon Development for COVID-19-related Concepts Using Open-source Word Embedding Sources: An Intrinsic and Extrinsic Evaluation %A Parikh,Soham %A Davoudi,Anahita %A Yu,Shun %A Giraldo,Carolina %A Schriver,Emily %A Mowery,Danielle %+ Department of Biostatistics, Epidemiology, & Informatics, Institute for Biomedical Informatics, University of Pennsylvania, A206 Richards Hall,, 3700 Hamilton Walk, Philadelphia, PA, 19104-6021, United States, 1 215 746 6677, dlmowery@pennmedicine.upenn.edu %K natural language processing %K word embedding %K COVID-19 %K intrinsic %K open-source %K computation %K model %K prediction %K semantic %K syntactic %K pattern %D 2021 %7 22.2.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: Scientists are developing new computational methods and prediction models to better clinically understand COVID-19 prevalence, treatment efficacy, and patient outcomes. These efforts could be improved by leveraging documented COVID-19–related symptoms, findings, and disorders from clinical text sources in an electronic health record. Word embeddings can identify terms related to these clinical concepts from both the biomedical and nonbiomedical domains, and are being shared with the open-source community at large. However, it’s unclear how useful openly available word embeddings are for developing lexicons for COVID-19–related concepts. Objective: Given an initial lexicon of COVID-19–related terms, this study aims to characterize the returned terms by similarity across various open-source word embeddings and determine common semantic and syntactic patterns between the COVID-19 queried terms and returned terms specific to the word embedding source. Methods: We compared seven openly available word embedding sources. Using a series of COVID-19–related terms for associated symptoms, findings, and disorders, we conducted an interannotator agreement study to determine how accurately the most similar returned terms could be classified according to semantic types by three annotators. We conducted a qualitative study of COVID-19 queried terms and their returned terms to detect informative patterns for constructing lexicons. We demonstrated the utility of applying such learned synonyms to discharge summaries by reporting the proportion of patients identified by concept among three patient cohorts: pneumonia (n=6410), acute respiratory distress syndrome (n=8647), and COVID-19 (n=2397). Results: We observed high pairwise interannotator agreement (Cohen kappa) for symptoms (0.86-0.99), findings (0.93-0.99), and disorders (0.93-0.99). Word embedding sources generated based on characters tend to return more synonyms (mean count of 7.2 synonyms) compared to token-based embedding sources (mean counts range from 2.0 to 3.4). Word embedding sources queried using a qualifier term (eg, dry cough or muscle pain) more often returned qualifiers of the similar semantic type (eg, “dry” returns consistency qualifiers like “wet” and “runny”) compared to a single term (eg, cough or pain) queries. A higher proportion of patients had documented fever (0.61-0.84), cough (0.41-0.55), shortness of breath (0.40-0.59), and hypoxia (0.51-0.56) retrieved than other clinical features. Terms for dry cough returned a higher proportion of patients with COVID-19 (0.07) than the pneumonia (0.05) and acute respiratory distress syndrome (0.03) populations. Conclusions: Word embeddings are valuable technology for learning related terms, including synonyms. When leveraging openly available word embedding sources, choices made for the construction of the word embeddings can significantly influence the words learned. %M 33544689 %R 10.2196/21679 %U https://medinform.jmir.org/2021/2/e21679 %U https://doi.org/10.2196/21679 %U http://www.ncbi.nlm.nih.gov/pubmed/33544689 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 2 %P e23390 %T Establishing Classifiers With Clinical Laboratory Indicators to Distinguish COVID-19 From Community-Acquired Pneumonia: Retrospective Cohort Study %A Dai,Wanfa %A Ke,Pei-Feng %A Li,Zhen-Zhen %A Zhuang,Qi-Zhen %A Huang,Wei %A Wang,Yi %A Xiong,Yujuan %A Huang,Xian-Zhang %+ Department of Laboratory Medicine, The Second Affiliated Hospital, Guangzhou University of Chinese Medicine, 111 Dade Rd, Guangzhou, 510210, China, 86 020 81887233 ext 35362, huangxz020@gzucm.edu.cn %K COVID-19 %K clinical laboratory indicators %K community-acquired pneumonia %K classifier %K classification algorithm %D 2021 %7 22.2.2021 %9 Original Paper %J J Med Internet Res %G English %X Background: The initial symptoms of patients with COVID-19 are very much like those of patients with community-acquired pneumonia (CAP); it is difficult to distinguish COVID-19 from CAP with clinical symptoms and imaging examination. Objective: The objective of our study was to construct an effective model for the early identification of COVID-19 that would also distinguish it from CAP. Methods: The clinical laboratory indicators (CLIs) of 61 COVID-19 patients and 60 CAP patients were analyzed retrospectively. Random combinations of various CLIs (ie, CLI combinations) were utilized to establish COVID-19 versus CAP classifiers with machine learning algorithms, including random forest classifier (RFC), logistic regression classifier, and gradient boosting classifier (GBC). The performance of the classifiers was assessed by calculating the area under the receiver operating characteristic curve (AUROC) and recall rate in COVID-19 prediction using the test data set. Results: The classifiers that were constructed with three algorithms from 43 CLI combinations showed high performance (recall rate >0.9 and AUROC >0.85) in COVID-19 prediction for the test data set. Among the high-performance classifiers, several CLIs showed a high usage rate; these included procalcitonin (PCT), mean corpuscular hemoglobin concentration (MCHC), uric acid, albumin, albumin to globulin ratio (AGR), neutrophil count, red blood cell (RBC) count, monocyte count, basophil count, and white blood cell (WBC) count. They also had high feature importance except for basophil count. The feature combination (FC) of PCT, AGR, uric acid, WBC count, neutrophil count, basophil count, RBC count, and MCHC was the representative one among the nine FCs used to construct the classifiers with an AUROC equal to 1.0 when using the RFC or GBC algorithms. Replacing any CLI in these FCs would lead to a significant reduction in the performance of the classifiers that were built with them. Conclusions: The classifiers constructed with only a few specific CLIs could efficiently distinguish COVID-19 from CAP, which could help clinicians perform early isolation and centralized management of COVID-19 patients. %M 33534722 %R 10.2196/23390 %U https://www.jmir.org/2021/2/e23390 %U https://doi.org/10.2196/23390 %U http://www.ncbi.nlm.nih.gov/pubmed/33534722 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 2 %P e24572 %T Development and Validation of a Machine Learning Approach for Automated Severity Assessment of COVID-19 Based on Clinical and Imaging Data: Retrospective Study %A Quiroz,Juan Carlos %A Feng,You-Zhen %A Cheng,Zhong-Yuan %A Rezazadegan,Dana %A Chen,Ping-Kang %A Lin,Qi-Ting %A Qian,Long %A Liu,Xiao-Fang %A Berkovsky,Shlomo %A Coiera,Enrico %A Song,Lei %A Qiu,Xiaoming %A Liu,Sidong %A Cai,Xiang-Ran %+ Centre for Health Informatics, Australian Institute of Health Innovation, Faculty of Medicine, Health and Human Sciences, Macquarie University, 75 Talvera Road, Macquarie Park, 2113, Australia, 61 29852729, sidong.liu@mq.edu.au %K algorithm %K clinical data %K clinical features %K COVID-19 %K CT scans %K development %K imaging %K imbalanced data %K machine learning %K oversampling %K severity assessment %K validation %D 2021 %7 11.2.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: COVID-19 has overwhelmed health systems worldwide. It is important to identify severe cases as early as possible, such that resources can be mobilized and treatment can be escalated. Objective: This study aims to develop a machine learning approach for automated severity assessment of COVID-19 based on clinical and imaging data. Methods: Clinical data—including demographics, signs, symptoms, comorbidities, and blood test results—and chest computed tomography scans of 346 patients from 2 hospitals in the Hubei Province, China, were used to develop machine learning models for automated severity assessment in diagnosed COVID-19 cases. We compared the predictive power of the clinical and imaging data from multiple machine learning models and further explored the use of four oversampling methods to address the imbalanced classification issue. Features with the highest predictive power were identified using the Shapley Additive Explanations framework. Results: Imaging features had the strongest impact on the model output, while a combination of clinical and imaging features yielded the best performance overall. The identified predictive features were consistent with those reported previously. Although oversampling yielded mixed results, it achieved the best model performance in our study. Logistic regression models differentiating between mild and severe cases achieved the best performance for clinical features (area under the curve [AUC] 0.848; sensitivity 0.455; specificity 0.906), imaging features (AUC 0.926; sensitivity 0.818; specificity 0.901), and a combination of clinical and imaging features (AUC 0.950; sensitivity 0.764; specificity 0.919). The synthetic minority oversampling method further improved the performance of the model using combined features (AUC 0.960; sensitivity 0.845; specificity 0.929). Conclusions: Clinical and imaging features can be used for automated severity assessment of COVID-19 and can potentially help triage patients with COVID-19 and prioritize care delivery to those at a higher risk of severe disease. %M 33534723 %R 10.2196/24572 %U http://medinform.jmir.org/2021/2/e24572/ %U https://doi.org/10.2196/24572 %U http://www.ncbi.nlm.nih.gov/pubmed/33534723 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 2 %P e24246 %T A Machine Learning Prediction Model of Respiratory Failure Within 48 Hours of Patient Admission for COVID-19: Model Development and Validation %A Bolourani,Siavash %A Brenner,Max %A Wang,Ping %A McGinn,Thomas %A Hirsch,Jamie S %A Barnaby,Douglas %A Zanos,Theodoros P %A , %+ Feinstein Institutes for Medical Research, Northwell Health, 350 Community Dr, Room 1257, Manhasset, NY, 11030, United States, 1 5165620484, tzanos@northwell.edu %K artificial intelligence %K prognostic %K model %K pandemic %K severe acute respiratory syndrome coronavirus 2 %K modeling %K development %K validation %K COVID-19 %K machine learning %D 2021 %7 10.2.2021 %9 Original Paper %J J Med Internet Res %G English %X Background: Predicting early respiratory failure due to COVID-19 can help triage patients to higher levels of care, allocate scarce resources, and reduce morbidity and mortality by appropriately monitoring and treating the patients at greatest risk for deterioration. Given the complexity of COVID-19, machine learning approaches may support clinical decision making for patients with this disease. Objective: Our objective is to derive a machine learning model that predicts respiratory failure within 48 hours of admission based on data from the emergency department. Methods: Data were collected from patients with COVID-19 who were admitted to Northwell Health acute care hospitals and were discharged, died, or spent a minimum of 48 hours in the hospital between March 1 and May 11, 2020. Of 11,525 patients, 933 (8.1%) were placed on invasive mechanical ventilation within 48 hours of admission. Variables used by the models included clinical and laboratory data commonly collected in the emergency department. We trained and validated three predictive models (two based on XGBoost and one that used logistic regression) using cross-hospital validation. We compared model performance among all three models as well as an established early warning score (Modified Early Warning Score) using receiver operating characteristic curves, precision-recall curves, and other metrics. Results: The XGBoost model had the highest mean accuracy (0.919; area under the curve=0.77), outperforming the other two models as well as the Modified Early Warning Score. Important predictor variables included the type of oxygen delivery used in the emergency department, patient age, Emergency Severity Index level, respiratory rate, serum lactate, and demographic characteristics. Conclusions: The XGBoost model had high predictive accuracy, outperforming other early warning scores. The clinical plausibility and predictive ability of XGBoost suggest that the model could be used to predict 48-hour respiratory failure in admitted patients with COVID-19. %M 33476281 %R 10.2196/24246 %U http://www.jmir.org/2021/2/e24246/ %U https://doi.org/10.2196/24246 %U http://www.ncbi.nlm.nih.gov/pubmed/33476281 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 2 %P e25457 %T Classification of the Disposition of Patients Hospitalized with COVID-19: Reading Discharge Summaries Using Natural Language Processing %A Fernandes,Marta %A Sun,Haoqi %A Jain,Aayushee %A Alabsi,Haitham S %A Brenner,Laura N %A Ye,Elissa %A Ge,Wendong %A Collens,Sarah I %A Leone,Michael J %A Das,Sudeshna %A Robbins,Gregory K %A Mukerji,Shibani S %A Westover,M Brandon %+ Department of Neurology, Massachusetts General Hospital, 50 Staniford St, Boston, MA, 02114, United States, 1 6508621154, mbentofernandes@mgh.harvard.edu %K ICU %K coronavirus %K electronic health record %K unstructured text %K natural language processing %K BoW %K LASSO %K feature selection %K machine learning %K intensive care unit %K COVID-19 %K EHR %D 2021 %7 10.2.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: Medical notes are a rich source of patient data; however, the nature of unstructured text has largely precluded the use of these data for large retrospective analyses. Transforming clinical text into structured data can enable large-scale research studies with electronic health records (EHR) data. Natural language processing (NLP) can be used for text information retrieval, reducing the need for labor-intensive chart review. Here we present an application of NLP to large-scale analysis of medical records at 2 large hospitals for patients hospitalized with COVID-19. Objective: Our study goal was to develop an NLP pipeline to classify the discharge disposition (home, inpatient rehabilitation, skilled nursing inpatient facility [SNIF], and death) of patients hospitalized with COVID-19 based on hospital discharge summary notes. Methods: Text mining and feature engineering were applied to unstructured text from hospital discharge summaries. The study included patients with COVID-19 discharged from 2 hospitals in the Boston, Massachusetts area (Massachusetts General Hospital and Brigham and Women’s Hospital) between March 10, 2020, and June 30, 2020. The data were divided into a training set (70%) and hold-out test set (30%). Discharge summaries were represented as bags-of-words consisting of single words (unigrams), bigrams, and trigrams. The number of features was reduced during training by excluding n-grams that occurred in fewer than 10% of discharge summaries, and further reduced using least absolute shrinkage and selection operator (LASSO) regularization while training a multiclass logistic regression model. Model performance was evaluated using the hold-out test set. Results: The study cohort included 1737 adult patients (median age 61 [SD 18] years; 55% men; 45% White and 16% Black; 14% nonsurvivors and 61% discharged home). The model selected 179 from a vocabulary of 1056 engineered features, consisting of combinations of unigrams, bigrams, and trigrams. The top features contributing most to the classification by the model (for each outcome) were the following: “appointments specialty,” “home health,” and “home care” (home); “intubate” and “ARDS” (inpatient rehabilitation); “service” (SNIF); “brief assessment” and “covid” (death). The model achieved a micro-average area under the receiver operating characteristic curve value of 0.98 (95% CI 0.97-0.98) and average precision of 0.81 (95% CI 0.75-0.84) in the testing set for prediction of discharge disposition. Conclusions: A supervised learning–based NLP approach is able to classify the discharge disposition of patients hospitalized with COVID-19. This approach has the potential to accelerate and increase the scale of research on patients’ discharge disposition that is possible with EHR data. %M 33449908 %R 10.2196/25457 %U https://medinform.jmir.org/2021/2/e25457 %U https://doi.org/10.2196/25457 %U http://www.ncbi.nlm.nih.gov/pubmed/33449908 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 2 %P e25245 %T Blockchain-Based Digital Contact Tracing Apps for COVID-19 Pandemic Management: Issues, Challenges, Solutions, and Future Directions %A Idrees,Sheikh Mohammad %A Nowostawski,Mariusz %A Jameel,Roshan %+ Department of Computer Science, Norwegian University of Science and Technology, Teknologivegen 22, Gjovik, 2815, Norway, 47 46248610, sheikh.idrees99@gmail.com %K COVID-19 %K digital contact tracing %K privacy preservation %K security %K blockchain technology %K blockchain %K privacy %K contact tracing %K app %K surveillance %K security %D 2021 %7 9.2.2021 %9 Viewpoint %J JMIR Med Inform %G English %X The COVID-19 pandemic has caused substantial global disturbance by affecting more than 42 million people (as of the end of October 2020). Since there is no medication or vaccine available, the only way to combat it is to minimize transmission. Digital contact tracing is an effective technique that can be utilized for this purpose, as it eliminates the manual contact tracing process and could help in identifying and isolating affected people. However, users are reluctant to share their location and contact details due to concerns related to the privacy and security of their personal information, which affects its implementation and extensive adoption. Blockchain technology has been applied in various domains and has been proven to be an effective approach for handling data transactions securely, which makes it an ideal choice for digital contact tracing apps. The properties of blockchain such as time stamping and immutability of data may facilitate the retrieval of accurate information on the trail of the virus in a transparent manner, while data encryption assures the integrity of the information being provided. Furthermore, the anonymity of the user’s identity alleviates some of the risks related to privacy and confidentiality concerns. In this paper, we provide readers with a detailed discussion on the digital contact tracing mechanism and outline the apps developed so far to combat the COVID-19 pandemic. Moreover, we present the possible risks, issues, and challenges associated with the available contact tracing apps and analyze how the adoption of a blockchain-based decentralized network for handling the app could provide users with privacy-preserving contact tracing without compromising performance and efficiency. %M 33400677 %R 10.2196/25245 %U https://medinform.jmir.org/2021/2/e25245 %U https://doi.org/10.2196/25245 %U http://www.ncbi.nlm.nih.gov/pubmed/33400677 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 2 %P e25183 %T Driving Digital Transformation During a Pandemic: Case Study of Virtual Collaboration in a German Hospital %A Frick,Nicholas R J %A Möllmann,Henriette L %A Mirbabaie,Milad %A Stieglitz,Stefan %+ Department of IT-Strategy, MAINGAU Energie GmbH, Ringstraße 4, Obertshausen, 63179, Germany, 49 1711904454, nicholas.frick@maingau-energie.de %K digital transformation %K virtual collaboration %K digital health %K health care %K COVID-19 %K pandemic %K hospital %K collaboration %K virtual heath %K crisis %K case study %D 2021 %7 1.2.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: The COVID-19 pandemic has not only changed the private lives of millions of people but has significantly affected the collaboration of medical specialists throughout health care systems worldwide. Hospitals are making changes to their regular operations to slow the spread of SARS-CoV-2 while ensuring the treatment of emergency patients. These substantial changes affect the typical work setting of clinicians and require the implementation of organizational arrangements. Objective: In this study, we aim to increase our understanding of how digital transformation drives virtual collaboration among clinicians in hospitals in times of crisis, such as the COVID-19 pandemic. Methods: We present the lessons learned from an exploratory case study in which we observed the introduction of an information technology (IT) system for enhancing collaboration among clinicians in a German hospital. The results are based on 16 semistructured interviews with physicians from various departments and disciplines; the interviews were generalized to better understand and interpret the meaning of the statements. Results: Three key lessons and recommendations explain how digital transformation ensures goal-driven collaboration among clinicians. First, we found that implementing a disruptive change requires alignment of the mindsets of the stakeholders. Second, IT-enabled collaboration presupposes behavioral rules that must be followed. Third, transforming antiquated processes demands a suitable technological infrastructure. Conclusions: Digital transformation is being driven by the COVID-19 pandemic. However, the rapid introduction of IT-enabled collaboration reveals grievances concerning the digital dissemination of medical information along the patient treatment path. To avoid being caught unprepared by future crises, digital transformation must be further driven to ensure collaboration, and the diagnostic and therapeutic process must be opened to disruptive strategies. %M 33449905 %R 10.2196/25183 %U https://medinform.jmir.org/2021/2/e25183 %U https://doi.org/10.2196/25183 %U http://www.ncbi.nlm.nih.gov/pubmed/33449905 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 2 %P e24785 %T Telehealth in the COVID-19 Era: A Balancing Act to Avoid Harm %A Reeves,J Jeffery %A Ayers,John W %A Longhurst,Christopher A %+ Department of Surgery, University of California San Diego, 9300 Campus Point Drive, MC7400, La Jolla, CA, 92037-7400, United States, 1 505 515 9844, jreeves@ucsd.edu %K telehealth %K patient safety %K COVID-19 %K coronavirus %K informatics %K safety %K harm %K risk %K access %K efficiency %K virtual care %D 2021 %7 1.2.2021 %9 Viewpoint %J J Med Internet Res %G English %X The telehealth revolution in response to COVID-19 has increased essential health care access during an unprecedented public health crisis. However, virtual patient care can also limit the patient-provider relationship, quality of examination, efficiency of health care delivery, and overall quality of care. As we witness the most rapidly adopted medical trend in modern history, clinicians are beginning to comprehend the many possibilities of telehealth, but its limitations also need to be understood. As outcomes are studied and federal regulations reconsidered, it is important to be precise in the virtual patient encounter approach. Herein, we offer some simple guidelines that could assist health care providers and clinic schedulers in determining the appropriateness of a telehealth visit by considering visit types, patient characteristics, and chief complaint or disease states. %M 33477104 %R 10.2196/24785 %U https://www.jmir.org/2021/2/e24785 %U https://doi.org/10.2196/24785 %U http://www.ncbi.nlm.nih.gov/pubmed/33477104 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 1 %P e24973 %T Deep Learning Models for Predicting Severe Progression in COVID-19-Infected Patients: Retrospective Study %A Ho,Thao Thi %A Park,Jongmin %A Kim,Taewoo %A Park,Byunggeon %A Lee,Jaehee %A Kim,Jin Young %A Kim,Ki Beom %A Choi,Sooyoung %A Kim,Young Hwan %A Lim,Jae-Kwang %A Choi,Sanghun %+ School of Mechanical Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu, 41566, Republic of Korea, 82 53 950 5578, s-choi@knu.ac.kr %K COVID-19 %K deep learning %K artificial neural network %K convolutional neural network %K lung CT %D 2021 %7 28.1.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: Many COVID-19 patients rapidly progress to respiratory failure with a broad range of severities. Identification of high-risk cases is critical for early intervention. Objective: The aim of this study is to develop deep learning models that can rapidly identify high-risk COVID-19 patients based on computed tomography (CT) images and clinical data. Methods: We analyzed 297 COVID-19 patients from five hospitals in Daegu, South Korea. A mixed artificial convolutional neural network (ACNN) model, combining an artificial neural network for clinical data and a convolutional neural network for 3D CT imaging data, was developed to classify these cases as either high risk of severe progression (ie, event) or low risk (ie, event-free). Results: Using the mixed ACNN model, we were able to obtain high classification performance using novel coronavirus pneumonia lesion images (ie, 93.9% accuracy, 80.8% sensitivity, 96.9% specificity, and 0.916 area under the curve [AUC] score) and lung segmentation images (ie, 94.3% accuracy, 74.7% sensitivity, 95.9% specificity, and 0.928 AUC score) for event versus event-free groups. Conclusions: Our study successfully differentiated high-risk cases among COVID-19 patients using imaging and clinical features. The developed model can be used as a predictive tool for interventions in aggressive therapies. %M 33455900 %R 10.2196/24973 %U http://medinform.jmir.org/2021/1/e24973/ %U https://doi.org/10.2196/24973 %U http://www.ncbi.nlm.nih.gov/pubmed/33455900 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 1 %P e24207 %T Federated Learning of Electronic Health Records to Improve Mortality Prediction in Hospitalized Patients With COVID-19: Machine Learning Approach %A Vaid,Akhil %A Jaladanki,Suraj K %A Xu,Jie %A Teng,Shelly %A Kumar,Arvind %A Lee,Samuel %A Somani,Sulaiman %A Paranjpe,Ishan %A De Freitas,Jessica K %A Wanyan,Tingyi %A Johnson,Kipp W %A Bicak,Mesude %A Klang,Eyal %A Kwon,Young Joon %A Costa,Anthony %A Zhao,Shan %A Miotto,Riccardo %A Charney,Alexander W %A Böttinger,Erwin %A Fayad,Zahi A %A Nadkarni,Girish N %A Wang,Fei %A Glicksberg,Benjamin S %+ The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, 770 Lexington Avenue, 14th Floor, New York, NY, 10065, United States, 1 (212) 731 7078, benjamin.glicksberg@mssm.edu %K federated learning %K COVID-19 %K machine learning %K electronic health records %D 2021 %7 27.1.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: Machine learning models require large datasets that may be siloed across different health care institutions. Machine learning studies that focus on COVID-19 have been limited to single-hospital data, which limits model generalizability. Objective: We aimed to use federated learning, a machine learning technique that avoids locally aggregating raw clinical data across multiple institutions, to predict mortality in hospitalized patients with COVID-19 within 7 days. Methods: Patient data were collected from the electronic health records of 5 hospitals within the Mount Sinai Health System. Logistic regression with L1 regularization/least absolute shrinkage and selection operator (LASSO) and multilayer perceptron (MLP) models were trained by using local data at each site. We developed a pooled model with combined data from all 5 sites, and a federated model that only shared parameters with a central aggregator. Results: The LASSOfederated model outperformed the LASSOlocal model at 3 hospitals, and the MLPfederated model performed better than the MLPlocal model at all 5 hospitals, as determined by the area under the receiver operating characteristic curve. The LASSOpooled model outperformed the LASSOfederated model at all hospitals, and the MLPfederated model outperformed the MLPpooled model at 2 hospitals. Conclusions: The federated learning of COVID-19 electronic health record data shows promise in developing robust predictive models without compromising patient privacy. %M 33400679 %R 10.2196/24207 %U http://medinform.jmir.org/2021/1/e24207/ %U https://doi.org/10.2196/24207 %U http://www.ncbi.nlm.nih.gov/pubmed/33400679 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 1 %P e21712 %T Giving Your Electronic Health Record a Checkup After COVID-19: A Practical Framework for Reviewing Clinical Decision Support in Light of the Telemedicine Expansion %A Feldman,Jonah %A Szerencsy,Adam %A Mann,Devin %A Austrian,Jonathan %A Kothari,Ulka %A Heo,Hye %A Barzideh,Sam %A Hickey,Maureen %A Snapp,Catherine %A Aminian,Rod %A Jones,Lauren %A Testa,Paul %+ Medical Center Information Technology, NYU Langone Health, 360 Park Ave South, 18th Floor, New York, NY, 10010, United States, 1 646 524 0300, jonah.feldman@nyulangone.org %K COVID-19 %K EHR %K clinical decision support %K telemedicine %K ambulatory care %K electronic health record %K framework %K implementation %D 2021 %7 27.1.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: The transformation of health care during COVID-19, with the rapid expansion of telemedicine visits, presents new challenges to chronic care and preventive health providers. Clinical decision support (CDS) is critically important to chronic care providers, and CDS malfunction is common during times of change. It is essential to regularly reassess an organization's ambulatory CDS program to maintain care quality. This is especially true after an immense change, like the COVID-19 telemedicine expansion. Objective: Our objective is to reassess the ambulatory CDS program at a large academic medical center in light of telemedicine's expansion in response to the COVID-19 pandemic. Methods: Our clinical informatics team devised a practical framework for an intrapandemic ambulatory CDS assessment focused on the impact of the telemedicine expansion. This assessment began with a quantitative analysis comparing CDS alert performance in the context of in-person and telemedicine visits. Board-certified physician informaticists then completed a formal workflow review of alerts with inferior performance in telemedicine visits. Informaticists then reported on themes and optimization opportunities through the existing CDS governance structure. Results: Our assessment revealed that 10 of our top 40 alerts by volume were not firing as expected in telemedicine visits. In 3 of the top 5 alerts, providers were significantly less likely to take action in telemedicine when compared to office visits. Cumulatively, alerts in telemedicine encounters had an action taken rate of 5.3% (3257/64,938) compared to 8.3% (19,427/233,636) for office visits. Observations from a clinical informaticist workflow review included the following: (1) Telemedicine visits have different workflows than office visits. Some alerts developed for the office were not appearing at the optimal time in the telemedicine workflow. (2) Missing clinical data is a common reason for the decreased alert firing seen in telemedicine visits. (3) Remote patient monitoring and patient-reported clinical data entered through the portal could replace data collection usually completed in the office by a medical assistant or registered nurse. Conclusions: In a large academic medical center at the pandemic epicenter, an intrapandemic ambulatory CDS assessment revealed clinically significant CDS malfunctions that highlight the importance of reassessing ambulatory CDS performance after the telemedicine expansion. %M 33400683 %R 10.2196/21712 %U http://medinform.jmir.org/2021/1/e21712/ %U https://doi.org/10.2196/21712 %U http://www.ncbi.nlm.nih.gov/pubmed/33400683 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 1 %P e25149 %T Interoperable Platform to Report Polymerase Chain Reaction SARS-CoV-2 Tests From Laboratories to the Chilean Government: Development and Implementation Study %A Guinez-Molinos,Sergio %A Andrade,José María %A Medina Negrete,Alejandro %A Espinoza Vidal,Sonia %A Rios,Elvis %+ Laboratory of Biomedical Informatics, School of Medicine, Universidad de Talca, Campus San Miguel, Avda. San Miguel S/N, Talca, 3460000, Chile, 56 71 2418820, sguinez@utalca.cl %K COVID-19 %K SARS-CoV-2 %K interoperability %K laboratory information system %K HL7 FHIR %K PCR %D 2021 %7 20.1.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: Testing, traceability, and isolation actions are a central strategy defined by the World Health Organization to contain the COVID-19 pandemic. In this sense, the countries have had difficulties in counting the number of people infected with SARS-CoV-2. Errors in reporting results are a common factor, as well as the lack of interoperability between laboratories and governments. Approaches aimed at sending spreadsheets via email expose patients’ privacy and have increased the probability of errors due to retyping, which generates a delay in the notification of results. Objective: This study aims to design and develop an interoperable platform to report polymerase chain reaction (PCR) SARS-CoV-2 tests from laboratories to the Chilean government. Methods: The methodology to design and develop the interoperable platform was comprised of six well-structured stages: (1) creation of a minimum data set for PCR SARS-CoV-2 tests, (2) modeling processes and end points where institutions interchange information, (3) standards and interoperability design, (4) software development, (5) software testing, and (6) software implementation. Results: The interoperable Fast Healthcare Interoperability Resources (FHIR) platform to report PCR SARS-CoV-2 tests from laboratories to the Chilean government was successfully implemented. The platform was designed, developed, tested, and implemented following a structured methodology. The platform’s performance to 1000 requests resulted in a response time of 240 milliseconds, throughput of 28.3 requests per second, and process management time of 131 milliseconds. The security was assured through a private network exclusive to the Ministry of Health to ensure confidentiality and integrity. The authorization and authentication of laboratories were implemented with a JavaScript Object Notation Web Token. All the PCR SARS-CoV-2 tests were accessible through an application programming interface gateway with valid credentials and the right access control list. Conclusions: The platform was implemented and is currently being used by UC Christus Laboratory. The platform is secure. It was tested adequately for confidentiality, secure authorization, authentication, and message integrity. This platform simplifies the reporting of PCR SARS-CoV-2 tests and reduces the time and probability of mistakes in counting positive cases. The interoperable solution with FHIR is working successfully and is open for the community, laboratories, and any institution that needs to report PCR SARS-CoV-2 tests. %M 33417587 %R 10.2196/25149 %U http://medinform.jmir.org/2021/1/e25149/ %U https://doi.org/10.2196/25149 %U http://www.ncbi.nlm.nih.gov/pubmed/33417587 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 1 %P e22753 %T A Low-Cost, Ear-Contactless Electronic Stethoscope Powered by Raspberry Pi for Auscultation of Patients With COVID-19: Prototype Development and Feasibility Study %A Yang,Chuan %A Zhang,Wei %A Pang,Zhixuan %A Zhang,Jing %A Zou,Deling %A Zhang,Xinzhong %A Guo,Sicong %A Wan,Jiye %A Wang,Ke %A Pang,Wenyue %+ Department of Cardiology, Shengjing Hospital of China Medical University, 36 Sanhao Street, Shenyang, 110004, China, 86 18940258063, pangwy@sj-hospital.org %K stethoscope %K auscultation %K COVID-19 %K Raspberry Pi %K Python %K ear-contactless %K low-cost %K phonocardiogram %K digital health %D 2021 %7 19.1.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: Chest examination by auscultation is essential in patients with COVID-19, especially those with poor respiratory conditions, such as severe pneumonia and respiratory dysfunction, and intensive cases who are intubated and whose breathing is assisted with a ventilator. However, proper auscultation of these patients is difficult when medical workers wear personal protective equipment and when it is necessary to minimize contact with patients. Objective: The objective of our study was to design and develop a low-cost electronic stethoscope enabling ear-contactless auscultation and digital storage of data for further analysis. The clinical feasibility of our device was assessed in comparison to a standard electronic stethoscope. Methods: We developed a prototype of the ear-contactless electronic stethoscope, called Auscul Pi, powered by Raspberry Pi and Python. Our device enables real-time capture of auscultation sounds with a microspeaker instead of an earpiece, and it can store data files for later analysis. We assessed the feasibility of using this stethoscope by detecting abnormal heart and respiratory sounds from 8 patients with heart failure or structural heart diseases and from 2 healthy volunteers and by comparing the results with those from a 3M Littmann electronic stethoscope. Results: We were able to conveniently operate Auscul Pi and precisely record the patients’ auscultation sounds. Auscul Pi showed similar real-time recording and playback performance to the Littmann stethoscope. The phonocardiograms of data obtained with the two stethoscopes were consistent and could be aligned with the cardiac cycles of the corresponding electrocardiograms. Pearson correlation analysis of amplitude data from the two types of phonocardiograms showed that Auscul Pi was correlated with the Littmann stethoscope with coefficients of 0.3245-0.5570 for healthy participants (P<.001) and of 0.3449-0.5138 among 4 patients (P<.001). Conclusions: Auscul Pi can be used for auscultation in clinical practice by applying real-time ear-contactless playback followed by quantitative analysis. Auscul Pi may allow accurate auscultation when medical workers are wearing protective suits and have difficulties in examining patients with COVID-19. Trial Registration: ChiCTR.org.cn ChiCTR2000033830; http://www.chictr.org.cn/showproj.aspx?proj=54971. %M 33436354 %R 10.2196/22753 %U https://medinform.jmir.org/2021/1/e22753 %U https://doi.org/10.2196/22753 %U http://www.ncbi.nlm.nih.gov/pubmed/33436354 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 1 %P e23811 %T Role of Machine Learning Techniques to Tackle the COVID-19 Crisis: Systematic Review %A Syeda,Hafsa Bareen %A Syed,Mahanazuddin %A Sexton,Kevin Wayne %A Syed,Shorabuddin %A Begum,Salma %A Syed,Farhanuddin %A Prior,Fred %A Yu Jr,Feliciano %+ Department of Biomedical Informatics, University of Arkansas for Medical Sciences, 4301 W Markham #469, Little Rock, AR, 72205, United States, 1 5016131443, ssyed@uams.edu %K COVID-19 %K coronavirus %K SARS-CoV-2 %K artificial intelligence %K machine learning %K deep learning %K systematic review %K epidemiology %K pandemic %K neural network %D 2021 %7 11.1.2021 %9 Review %J JMIR Med Inform %G English %X Background: SARS-CoV-2, the novel coronavirus responsible for COVID-19, has caused havoc worldwide, with patients presenting a spectrum of complications that have pushed health care experts to explore new technological solutions and treatment plans. Artificial Intelligence (AI)–based technologies have played a substantial role in solving complex problems, and several organizations have been swift to adopt and customize these technologies in response to the challenges posed by the COVID-19 pandemic. Objective: The objective of this study was to conduct a systematic review of the literature on the role of AI as a comprehensive and decisive technology to fight the COVID-19 crisis in the fields of epidemiology, diagnosis, and disease progression. Methods: A systematic search of PubMed, Web of Science, and CINAHL databases was performed according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) guidelines to identify all potentially relevant studies published and made available online between December 1, 2019, and June 27, 2020. The search syntax was built using keywords specific to COVID-19 and AI. Results: The search strategy resulted in 419 articles published and made available online during the aforementioned period. Of these, 130 publications were selected for further analyses. These publications were classified into 3 themes based on AI applications employed to combat the COVID-19 crisis: Computational Epidemiology, Early Detection and Diagnosis, and Disease Progression. Of the 130 studies, 71 (54.6%) focused on predicting the COVID-19 outbreak, the impact of containment policies, and potential drug discoveries, which were classified under the Computational Epidemiology theme. Next, 40 of 130 (30.8%) studies that applied AI techniques to detect COVID-19 by using patients’ radiological images or laboratory test results were classified under the Early Detection and Diagnosis theme. Finally, 19 of the 130 studies (14.6%) that focused on predicting disease progression, outcomes (ie, recovery and mortality), length of hospital stay, and number of days spent in the intensive care unit for patients with COVID-19 were classified under the Disease Progression theme. Conclusions: In this systematic review, we assembled studies in the current COVID-19 literature that utilized AI-based methods to provide insights into different COVID-19 themes. Our findings highlight important variables, data types, and available COVID-19 resources that can assist in facilitating clinical and translational research. %M 33326405 %R 10.2196/23811 %U http://medinform.jmir.org/2021/1/e23811/ %U https://doi.org/10.2196/23811 %U http://www.ncbi.nlm.nih.gov/pubmed/33326405 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 1 %P e25435 %T Using an Extended Technology Acceptance Model to Understand the Factors Influencing Telehealth Utilization After Flattening the COVID-19 Curve in South Korea: Cross-sectional Survey Study %A An,Min Ho %A You,Seng Chan %A Park,Rae Woong %A Lee,Seongwon %+ Department of Biomedical Informatics, Ajou University School of Medicine, 164, World cup-ro, Yeongtong-gu, Suwon, 16499, Republic of Korea, 82 31 219 4471, seongwon.lee.16@gmail.com %K telemedicine %K telehealth %K COVID-19 %K pandemic %K model %K South Korea %K acceptance %K anxiety %K cross-sectional %D 2021 %7 8.1.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: Although telehealth is considered a key component in combating the worldwide crisis caused by COVID-19, the factors that influence its acceptance by the general population after the flattening of the COVID-19 curve remain unclear. Objective: We aimed to identify factors affecting telehealth acceptance, including anxiety related to COVID-19, after the initial rapid spread of the disease in South Korea. Methods: We proposed an extended technology acceptance model (TAM) and performed a cross-sectional survey of individuals aged ≥30 years. In total, 471 usable responses were collected. Confirmatory factor analysis was used to examine the validity of measurements, and the partial least squares (PLS) method was used to investigate factors influencing telehealth acceptance and the impacts of COVID-19. Results: PLS analysis showed that increased accessibility, enhanced care, and ease of telehealth use had positive effects on its perceived usefulness (P=.002, P<.001, and P<.001, respectively). Furthermore, perceived usefulness, ease, and privacy/discomfort significantly impacted the acceptance of telehealth (P<.001, P<.001, and P<.001, respectively). However, anxiety toward COVID-19 was not associated with telehealth acceptance (P=.112), and this insignificant relationship was consistent in the cluster (n=216, 46%) of respondents with chronic diseases (P=.185). Conclusions: Increased accessibility, enhanced care, usefulness, ease of use, and privacy/discomfort are decisive variables affecting telehealth acceptance in the Korean general population, whereas anxiety about COVID-19 is not. This study may lead to a tailored promotion of telehealth after the pandemic subsides. %M 33395397 %R 10.2196/25435 %U http://medinform.jmir.org/2021/1/e25435/ %U https://doi.org/10.2196/25435 %U http://www.ncbi.nlm.nih.gov/pubmed/33395397 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 12 %P e25442 %T An Artificial Intelligence Model to Predict the Mortality of COVID-19 Patients at Hospital Admission Time Using Routine Blood Samples: Development and Validation of an Ensemble Model %A Ko,Hoon %A Chung,Heewon %A Kang,Wu Seong %A Park,Chul %A Kim,Do Wan %A Kim,Seong Eun %A Chung,Chi Ryang %A Ko,Ryoung Eun %A Lee,Hooseok %A Seo,Jae Ho %A Choi,Tae-Young %A Jaimes,Rafael %A Kim,Kyung Won %A Lee,Jinseok %+ Biomedical Engineering, Wonkwang University, Iksan Daero, Iksan, 54538, Republic of Korea, 82 1638506970, gonasago@gmail.com %K COVID-19 %K artificial intelligence %K blood samples %K mortality prediction %D 2020 %7 23.12.2020 %9 Original Paper %J J Med Internet Res %G English %X Background: COVID-19, which is accompanied by acute respiratory distress, multiple organ failure, and death, has spread worldwide much faster than previously thought. However, at present, it has limited treatments. Objective: To overcome this issue, we developed an artificial intelligence (AI) model of COVID-19, named EDRnet (ensemble learning model based on deep neural network and random forest models), to predict in-hospital mortality using a routine blood sample at the time of hospital admission. Methods: We selected 28 blood biomarkers and used the age and gender information of patients as model inputs. To improve the mortality prediction, we adopted an ensemble approach combining deep neural network and random forest models. We trained our model with a database of blood samples from 361 COVID-19 patients in Wuhan, China, and applied it to 106 COVID-19 patients in three Korean medical institutions. Results: In the testing data sets, EDRnet provided high sensitivity (100%), specificity (91%), and accuracy (92%). To extend the number of patient data points, we developed a web application (BeatCOVID19) where anyone can access the model to predict mortality and can register his or her own blood laboratory results. Conclusions: Our new AI model, EDRnet, accurately predicts the mortality rate for COVID-19. It is publicly available and aims to help health care providers fight COVID-19 and improve patients’ outcomes. %M 33301414 %R 10.2196/25442 %U http://www.jmir.org/2020/12/e25442/ %U https://doi.org/10.2196/25442 %U http://www.ncbi.nlm.nih.gov/pubmed/33301414 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 8 %N 12 %P e20567 %T Global Infectious Disease Surveillance and Case Tracking System for COVID-19: Development Study %A Lee,Hsiu-An %A Kung,Hsin-Hua %A Lee,Yuarn-Jang %A Chao,Jane C-J %A Udayasankaran,Jai Ganesh %A Fan,Hueng-Chuen %A Ng,Kwok-Keung %A Chang,Yu-Kang %A Kijsanayotin,Boonchai %A Marcelo,Alvin B %A Hsu,Chien-Yeh %+ Department of Information Management, National Taipei University of Nursing and Health Sciences, 365 Ming-te Road, Peitou District, Taipei, 11219, Taiwan, 886 28227101, cyhsu@ntunhs.edu.tw %K blockchain %K infectious disease surveillance %K international collaboration %K HL7 FHIR %K COVID-19 defense %K COVID-19 %D 2020 %7 22.12.2020 %9 Original Paper %J JMIR Med Inform %G English %X Background: COVID-19 has affected more than 180 countries and is the first known pandemic to be caused by a new virus. COVID-19’s emergence and rapid spread is a global public health and economic crisis. However, investigations into the disease, patient-tracking mechanisms, and case report transmissions are both labor-intensive and slow. Objective: The pandemic has overwhelmed health care systems, forcing hospitals and medical facilities to find effective ways to share data. This study aims to design a global infectious disease surveillance and case tracking system that can facilitate the detection and control of COVID-19. Methods: The International Patient Summary (IPS; an electronic health record that contains essential health care information about a patient) was used. The IPS was designed to support the used case scenario for unplanned cross-border care. The design, scope, utility, and potential for reuse of the IPS for unplanned cross-border care make it suitable for situations like COVID-19. The Fast Healthcare Interoperability Resources confirmed that IPS data, which includes symptoms, therapies, medications, and laboratory data, can be efficiently transferred and exchanged on the system for easy access by physicians. To protect privacy, patient data are deidentified. All systems are protected by blockchain architecture, including data encryption, validation, and exchange of records. Results: To achieve worldwide COVID-19 surveillance, a global infectious disease information exchange must be enacted. The COVID-19 surveillance system was designed based on blockchain architecture. The IPS was used to exchange case study information among physicians. After being verified, physicians can upload IPS files and receive IPS data from other global cases. The system includes a daily IPS uploading and enhancement plan, which covers real-time uploading through the interoperation of the clinic system, with the module based on the Open Application Programming Interface architecture. Through the treatment of different cases, drug treatments, and the exchange of treatment results, the disease spread can be controlled, and treatment methods can be funded. In the Infectious Disease Case Tracking module, we can track the moving paths of infectious disease cases. The location information recorded in the blockchain is used to check the locations of different cases. The Case Tracking module was established for the Centers for Disease Control and Prevention to track cases and prevent disease spread. Conclusions: We created the IPS of infectious diseases for physicians treating patients with COVID-19. Our system can help health authorities respond quickly to the transmission and spread of unknown diseases, and provides a system for information retrieval on disease transmission. In addition, this system can help researchers form trials and analyze data from different countries. A common forum to facilitate the mutual sharing of experiences, best practices, therapies, useful medications, and clinical intervention outcomes from research in various countries could help control an unknown virus. This system could be an effective tool for global collaboration in evidence-based efforts to fight COVID-19. %M 33320826 %R 10.2196/20567 %U http://medinform.jmir.org/2020/12/e20567/ %U https://doi.org/10.2196/20567 %U http://www.ncbi.nlm.nih.gov/pubmed/33320826 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 8 %N 12 %P e24544 %T Growth of Ambulatory Virtual Visits and Differential Use by Patient Sociodemographics at One Urban Academic Medical Center During the COVID-19 Pandemic: Retrospective Analysis %A Gilson,Sarah F %A Umscheid,Craig A %A Laiteerapong,Neda %A Ossey,Graeme %A Nunes,Kenneth J %A Shah,Sachin D %+ Department of Medicine, University of Chicago, 5841 S Maryland Ave, MC 3051, Chicago, IL, 60637, United States, 1 773 834 8455, sdshah@uchicago.edu %K telemedicine %K telehealth %K video visit %K telephone visit %K virtual visit %K COVID-19 %K age %K sex %K race %K insurance %K demographic %K retrospective %D 2020 %7 4.12.2020 %9 Original Paper %J JMIR Med Inform %G English %X Background: Despite widespread interest in the use of virtual (ie, telephone and video) visits for ambulatory patient care during the COVID-19 pandemic, studies examining their adoption during the pandemic by race, sex, age, or insurance are lacking. Moreover, there have been limited evaluations to date of the impact of these sociodemographic factors on the use of telephone versus video visits. Such assessments are crucial to identify, understand, and address differences in care delivery across patient populations, particularly those that could affect access to or quality of care. Objective: The aim of this study was to examine changes in ambulatory visit volume and type (ie, in-person vs virtual and telephone vs video visits) by patient sociodemographics during the COVID-19 pandemic at one urban academic medical center. Methods: We compared volumes and patient sociodemographics (age, sex, race, insurance) for visits during the first 11 weeks following the COVID-19 national emergency declaration (March 15 to May 31, 2020) to visits in the corresponding weeks in 2019. Additionally, for visits during the COVID-19 study period, we examined differences in visit type (ie, in-person versus virtual, and telephone versus video visits) by sociodemographics using multivariate logistic regression. Results: Total visit volumes in the COVID-19 study period comprised 51.4% of the corresponding weeks in 2019 (n=80,081 vs n=155,884 visits). Although patient sociodemographics between the COVID-19 study period in 2020 and the corresponding weeks in 2019 were similar, 60.5% (n=48,475) of the visits were virtual, compared to 0% in 2019. Of the virtual visits, 61.2% (n=29,661) were video based, and 38.8% (n=18,814) were telephone based. In the COVID-19 study period, virtual (vs in-person) visits were more likely among patients with race categorized as other (vs White) and patients with Medicare (vs commercial) insurance and less likely for men, patients aged 0-17 years, 65-74 years, or ≥75 years (compared to patients aged 18-45 years), and patients with Medicaid insurance or insurance categorized as other. Among virtual visits, compared to telephone visits, video visits were more likely to be adopted by patients aged 0-17 years (vs 18-45 years), but less likely for all other age groups, men, Black (vs White) patients, and patients with Medicare or Medicaid (vs commercial) insurance. Conclusions: Virtual visits comprised the majority of ambulatory visits during the COVID-19 study period, of which a majority were by video. Sociodemographic differences existed in the use of virtual versus in-person and video versus telephone visits. To ensure equitable care delivery, we present five policy recommendations to inform the further development of virtual visit programs and their reimbursement. %M 33191247 %R 10.2196/24544 %U https://medinform.jmir.org/2020/12/e24544 %U https://doi.org/10.2196/24544 %U http://www.ncbi.nlm.nih.gov/pubmed/33191247 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 8 %N 11 %P e19524 %T Applying eHealth for Pandemic Management in Saudi Arabia in the Context of COVID-19: Survey Study and Framework Proposal %A Alsharif,Abdullah %+ Department of Management Information Systems, College of Business Administration-Yanbu, Taibah University, 14 Khlaf Alkhfigee Street 8314, Iskan, Medinah, PO Box 344, Saudi Arabia, 966 542578585, alsharifa@taibahu.edu.sa %K COVID-19 %K eHealth framework %K infectious disease %K pandemic %K eHealth %K public health %D 2020 %7 26.11.2020 %9 Original Paper %J JMIR Med Inform %G English %X Background: The increased frequency of epidemics such as Middle East respiratory syndrome, severe acute respiratory syndrome, Ebola virus, and Zika virus has created stress on health care management and operations as well as on relevant stakeholders. In addition, the recent COVID-19 outbreak has been creating challenges for various countries and their respective health care organizations in managing and controlling the pandemic. One of the most important observations during the recent outbreak is the lack of effective eHealth frameworks for managing and controlling pandemics. Objective: The aims of this study are to review the current National eHealth Strategy of Saudi Arabia and to propose an integrated eHealth framework that can be effective for managing health care operations and services during pandemics. Methods: A questionnaire-based survey was administered to 316 health care professionals to review the current national eHealth framework of Saudi Arabia and identify the objectives, factors, and components that are key for managing and controlling pandemics. Purposive sampling was used to collect responses from diverse experts, including physicians, technical experts, nurses, administrative experts, and pharmacists. The survey was administered at five hospitals in Saudi Arabia by forwarding the survey link using a web-based portal. A sample population of 350 was achieved, which was filtered to exclude incomplete and ineligible samples, giving a sample of 316 participants. Results: Of the 316 participants, 187 (59.2%) found the current eHealth framework to be ineffective, and more than 50% of the total participants stated that the framework lacked some essential components and objectives. Additional components and objectives focusing on using eHealth for managing information, creating awareness, increasing accessibility and reachability, promoting self-management and self-collaboration, promoting electronic services, and extensive stakeholder engagement were considered to be the most important factors by more than 80% of the total participants. Conclusions: Managing pandemics requires an effective and efficient eHealth framework that can be used to manage various health care services by integrating different eHealth components and collaborating with all stakeholders. %M 33035174 %R 10.2196/19524 %U http://medinform.jmir.org/2020/11/e19524/ %U https://doi.org/10.2196/19524 %U http://www.ncbi.nlm.nih.gov/pubmed/33035174 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 8 %N 11 %P e21604 %T Prediction of COVID-19 Severity Using Chest Computed Tomography and Laboratory Measurements: Evaluation Using a Machine Learning Approach %A Li,Daowei %A Zhang,Qiang %A Tan,Yue %A Feng,Xinghuo %A Yue,Yuanyi %A Bai,Yuhan %A Li,Jimeng %A Li,Jiahang %A Xu,Youjun %A Chen,Shiyu %A Xiao,Si-Yu %A Sun,Muyan %A Li,Xiaona %A Zhu,Fang %+ Department of Cardiovascular Ultrasound, The People's Hospital of China Medical University & The People's Hospital of Liaoning Province, No 33, Wenyi Road, Shenhe District, Shenyang, 110016, China, 86 2483283333, zfmoon024@163.com %K COVID-19 %K severe case prediction %K computerized tomography %K machine learning %K CT %K scan %K detection %K prediction %K model %D 2020 %7 17.11.2020 %9 Original Paper %J JMIR Med Inform %G English %X Background: Most of the mortality resulting from COVID-19 has been associated with severe disease. Effective treatment of severe cases remains a challenge due to the lack of early detection of the infection. Objective: This study aimed to develop an effective prediction model for COVID-19 severity by combining radiological outcome with clinical biochemical indexes. Methods: A total of 46 patients with COVID-19 (10 severe, 36 nonsevere) were examined. To build the prediction model, a set of 27 severe and 151 nonsevere clinical laboratory records and computerized tomography (CT) records were collected from these patients. We managed to extract specific features from the patients’ CT images by using a recently published convolutional neural network. We also trained a machine learning model combining these features with clinical laboratory results. Results: We present a prediction model combining patients’ radiological outcomes with their clinical biochemical indexes to identify severe COVID-19 cases. The prediction model yielded a cross-validated area under the receiver operating characteristic (AUROC) score of 0.93 and an F1 score of 0.89, which showed a 6% and 15% improvement, respectively, compared to the models based on laboratory test features only. In addition, we developed a statistical model for forecasting COVID-19 severity based on the results of patients’ laboratory tests performed before they were classified as severe cases; this model yielded an AUROC score of 0.81. Conclusions: To our knowledge, this is the first report predicting the clinical progression of COVID-19, as well as forecasting severity, based on a combined analysis using laboratory tests and CT images. %M 33038076 %R 10.2196/21604 %U http://medinform.jmir.org/2020/11/e21604/ %U https://doi.org/10.2196/21604 %U http://www.ncbi.nlm.nih.gov/pubmed/33038076 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 8 %N 11 %P e21648 %T Toward Preparing a Knowledge Base to Explore Potential Drugs and Biomedical Entities Related to COVID-19: Automated Computational Approach %A Khan,Junaed Younus %A Khondaker,Md Tawkat Islam %A Hoque,Iram Tazim %A Al-Absi,Hamada R H %A Rahman,Mohammad Saifur %A Guler,Reto %A Alam,Tanvir %A Rahman,M Sohel %+ College of Science and Engineering, Hamad Bin Khalifa University, PO Box 34110, Education City, Doha, Qatar, 974 44542277, talam@hbku.edu.qa %K COVID-19 %K 2019-nCoV %K coronavirus %K SARS-CoV-2 %K SARS %K remdesivir %K statin %K statins %K dexamethasone %K ivermectin %K hydroxychloroquine %D 2020 %7 10.11.2020 %9 Original Paper %J JMIR Med Inform %G English %X Background: Novel coronavirus disease 2019 (COVID-19) is taking a huge toll on public health. Along with the non-therapeutic preventive measurements, scientific efforts are currently focused, mainly, on the development of vaccines and pharmacological treatment with existing drugs. Summarizing evidences from scientific literatures on the discovery of treatment plan of COVID-19 under a platform would help the scientific community to explore the opportunities in a systematic fashion. Objective: The aim of this study is to explore the potential drugs and biomedical entities related to coronavirus related diseases, including COVID-19, that are mentioned on scientific literature through an automated computational approach. Methods: We mined the information from publicly available scientific literature and related public resources. Six topic-specific dictionaries, including human genes, human miRNAs, diseases, Protein Databank, drugs, and drug side effects, were integrated to mine all scientific evidence related to COVID-19. We employed an automated literature mining and labeling system through a novel approach to measure the effectiveness of drugs against diseases based on natural language processing, sentiment analysis, and deep learning. We also applied the concept of cosine similarity to confidently infer the associations between diseases and genes. Results: Based on the literature mining, we identified 1805 diseases, 2454 drugs, 1910 genes that are related to coronavirus related diseases including COVID-19. Integrating the extracted information, we developed the first knowledgebase platform dedicated to COVID-19, which highlights potential list of drugs and related biomedical entities. For COVID-19, we highlighted multiple case studies on existing drugs along with a confidence score for their applicability in the treatment plan. Based on our computational method, we found Remdesivir, Statins, Dexamethasone, and Ivermectin could be considered as potential effective drugs to improve clinical status and lower mortality in patients hospitalized with COVID-19. We also found that Hydroxychloroquine could not be considered as an effective drug for COVID-19. The resulting knowledgebase is made available as an open source tool, named COVID-19Base. Conclusions: Proper investigation of the mined biomedical entities along with the identified interactions among those would help the research community to discover possible ways for the therapeutic treatment of COVID-19. %M 33055059 %R 10.2196/21648 %U http://medinform.jmir.org/2020/11/e21648/ %U https://doi.org/10.2196/21648 %U http://www.ncbi.nlm.nih.gov/pubmed/33055059 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 11 %P e24225 %T An Easy-to-Use Machine Learning Model to Predict the Prognosis of Patients With COVID-19: Retrospective Cohort Study %A Kim,Hyung-Jun %A Han,Deokjae %A Kim,Jeong-Han %A Kim,Daehyun %A Ha,Beomman %A Seog,Woong %A Lee,Yeon-Kyeng %A Lim,Dosang %A Hong,Sung Ok %A Park,Mi-Jin %A Heo,JoonNyung %+ The Armed Forces Medical Command, 81 Saemaeul-ro 177beon-gil, Bundang-gu, Seongnam, , Republic of Korea, 82 31 725 5490, jnheo@jnheo.com %K COVID-19 %K machine learning %K prognosis %K SARS-CoV-2 %K severe acute respiratory syndrome coronavirus 2 %D 2020 %7 9.11.2020 %9 Original Paper %J J Med Internet Res %G English %X Background: Prioritizing patients in need of intensive care is necessary to reduce the mortality rate during the COVID-19 pandemic. Although several scoring methods have been introduced, many require laboratory or radiographic findings that are not always easily available. Objective: The purpose of this study was to develop a machine learning model that predicts the need for intensive care for patients with COVID-19 using easily obtainable characteristics—baseline demographics, comorbidities, and symptoms. Methods: A retrospective study was performed using a nationwide cohort in South Korea. Patients admitted to 100 hospitals from January 25, 2020, to June 3, 2020, were included. Patient information was collected retrospectively by the attending physicians in each hospital and uploaded to an online case report form. Variables that could be easily provided were extracted. The variables were age, sex, smoking history, body temperature, comorbidities, activities of daily living, and symptoms. The primary outcome was the need for intensive care, defined as admission to the intensive care unit, use of extracorporeal life support, mechanical ventilation, vasopressors, or death within 30 days of hospitalization. Patients admitted until March 20, 2020, were included in the derivation group to develop prediction models using an automated machine learning technique. The models were externally validated in patients admitted after March 21, 2020. The machine learning model with the best discrimination performance was selected and compared against the CURB-65 (confusion, urea, respiratory rate, blood pressure, and 65 years of age or older) score using the area under the receiver operating characteristic curve (AUC). Results: A total of 4787 patients were included in the analysis, of which 3294 were assigned to the derivation group and 1493 to the validation group. Among the 4787 patients, 460 (9.6%) patients needed intensive care. Of the 55 machine learning models developed, the XGBoost model revealed the highest discrimination performance. The AUC of the XGBoost model was 0.897 (95% CI 0.877-0.917) for the derivation group and 0.885 (95% CI 0.855-0.915) for the validation group. Both the AUCs were superior to those of CURB-65, which were 0.836 (95% CI 0.825-0.847) and 0.843 (95% CI 0.829-0.857), respectively. Conclusions: We developed a machine learning model comprising simple patient-provided characteristics, which can efficiently predict the need for intensive care among patients with COVID-19. %M 33108316 %R 10.2196/24225 %U http://www.jmir.org/2020/11/e24225/ %U https://doi.org/10.2196/24225 %U http://www.ncbi.nlm.nih.gov/pubmed/33108316 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 11 %P e24018 %T Machine Learning to Predict Mortality and Critical Events in a Cohort of Patients With COVID-19 in New York City: Model Development and Validation %A Vaid,Akhil %A Somani,Sulaiman %A Russak,Adam J %A De Freitas,Jessica K %A Chaudhry,Fayzan F %A Paranjpe,Ishan %A Johnson,Kipp W %A Lee,Samuel J %A Miotto,Riccardo %A Richter,Felix %A Zhao,Shan %A Beckmann,Noam D %A Naik,Nidhi %A Kia,Arash %A Timsina,Prem %A Lala,Anuradha %A Paranjpe,Manish %A Golden,Eddye %A Danieletto,Matteo %A Singh,Manbir %A Meyer,Dara %A O'Reilly,Paul F %A Huckins,Laura %A Kovatch,Patricia %A Finkelstein,Joseph %A Freeman,Robert M. %A Argulian,Edgar %A Kasarskis,Andrew %A Percha,Bethany %A Aberg,Judith A %A Bagiella,Emilia %A Horowitz,Carol R %A Murphy,Barbara %A Nestler,Eric J %A Schadt,Eric E %A Cho,Judy H %A Cordon-Cardo,Carlos %A Fuster,Valentin %A Charney,Dennis S %A Reich,David L %A Bottinger,Erwin P %A Levin,Matthew A %A Narula,Jagat %A Fayad,Zahi A %A Just,Allan C %A Charney,Alexander W %A Nadkarni,Girish N %A Glicksberg,Benjamin S %+ The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, 770 Lexington St., New York, NY, United States, 1 212 731 7078, benjamin.glicksberg@mssm.edu %K machine learning %K COVID-19 %K electronic health record %K TRIPOD %K clinical informatics %K prediction %K mortality %K EHR %K cohort %K hospital %K performance %D 2020 %7 6.11.2020 %9 Original Paper %J J Med Internet Res %G English %X Background: COVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking. Objective: The aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points. Methods: We used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19–positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions. Results: Upon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction. Conclusions: We externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes. %M 33027032 %R 10.2196/24018 %U https://www.jmir.org/2020/11/e24018 %U https://doi.org/10.2196/24018 %U http://www.ncbi.nlm.nih.gov/pubmed/33027032 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 11 %P e22280 %T Adoption of Digital Technologies in Health Care During the COVID-19 Pandemic: Systematic Review of Early Scientific Literature %A Golinelli,Davide %A Boetto,Erik %A Carullo,Gherardo %A Nuzzolese,Andrea Giovanni %A Landini,Maria Paola %A Fantini,Maria Pia %+ Department of Biomedical and Neuromotor Sciences, University of Bologna, via San Giacomo 12, Bologna, 40126, Italy, 39 0512094830, erik.boetto@gmail.com %K COVID-19 %K SARS-CoV-2 %K pandemic %K digital heath %K review %K literature %K mitigate %K impact %K eHealth %D 2020 %7 6.11.2020 %9 Review %J J Med Internet Res %G English %X Background: The COVID-19 pandemic is favoring digital transitions in many industries and in society as a whole. Health care organizations have responded to the first phase of the pandemic by rapidly adopting digital solutions and advanced technology tools. Objective: The aim of this review is to describe the digital solutions that have been reported in the early scientific literature to mitigate the impact of COVID-19 on individuals and health systems. Methods: We conducted a systematic review of early COVID-19–related literature (from January 1 to April 30, 2020) by searching MEDLINE and medRxiv with appropriate terms to find relevant literature on the use of digital technologies in response to the pandemic. We extracted study characteristics such as the paper title, journal, and publication date, and we categorized the retrieved papers by the type of technology and patient needs addressed. We built a scoring rubric by cross-classifying the patient needs with the type of technology. We also extracted information and classified each technology reported by the selected articles according to health care system target, grade of innovation, and scalability to other geographical areas. Results: The search identified 269 articles, of which 124 full-text articles were assessed and included in the review after screening. Most of the selected articles addressed the use of digital technologies for diagnosis, surveillance, and prevention. We report that most of these digital solutions and innovative technologies have been proposed for the diagnosis of COVID-19. In particular, within the reviewed articles, we identified numerous suggestions on the use of artificial intelligence (AI)–powered tools for the diagnosis and screening of COVID-19. Digital technologies are also useful for prevention and surveillance measures, such as contact-tracing apps and monitoring of internet searches and social media usage. Fewer scientific contributions address the use of digital technologies for lifestyle empowerment or patient engagement. Conclusions: In the field of diagnosis, digital solutions that integrate with traditional methods, such as AI-based diagnostic algorithms based both on imaging and clinical data, appear to be promising. For surveillance, digital apps have already proven their effectiveness; however, problems related to privacy and usability remain. For other patient needs, several solutions have been proposed, such as telemedicine or telehealth tools. These tools have long been available, but this historical moment may actually be favoring their definitive large-scale adoption. It is worth taking advantage of the impetus provided by the crisis; it is also important to keep track of the digital solutions currently being proposed to implement best practices and models of care in future and to adopt at least some of the solutions proposed in the scientific literature, especially in national health systems, which have proved to be particularly resistant to the digital transition in recent years. %M 33079693 %R 10.2196/22280 %U http://www.jmir.org/2020/11/e22280/ %U https://doi.org/10.2196/22280 %U http://www.ncbi.nlm.nih.gov/pubmed/33079693 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 11 %P e23361 %T openEHR Archetype Use and Reuse Within Multilingual Clinical Data Sets: Case Study %A Leslie,Heather %+ Atomica Informatics, Fitzroy, Australia, 61 418966670, heather.leslie@atomicainformatics.com %K openEHR %K archetype %K template %K reuse %K clinical informatics %K COVID-19 %K standard %K crowd sourced %K data set %K data quality %K multilingual %K EHR %K electronic health record %K SARS-CoV-2 %D 2020 %7 2.11.2020 %9 Original Paper %J J Med Internet Res %G English %X Background: Despite electronic health records being in existence for over 50 years, our ability to exchange health data remains frustratingly limited. Commonly used clinical content standards, and the information models that underpin them, are primarily related to health data exchange, and so are usually document- or message-focused. In contrast, over the past 12 years, the Clinical Models program at openEHR International has gradually established a governed, coordinated, and coherent ecosystem of clinical information models, known as openEHR archetypes. Each archetype is designed as a maximal data set for a universal use-case, intended for reuse across various health data sets, known as openEHR templates. To date, only anecdotal evidence has been available to indicate if the hypothesis of archetype reuse across templates is feasible and scalable. As a response to the COVID-19 pandemic, between February and July 2020, 7 openEHR templates were independently created to represent COVID-19–related data sets for symptom screening, confirmed infection reporting, clinical decision support, and research. Each of the templates prioritized reuse of existing use-case agnostic archetypes found in openEHR International's online Clinical Knowledge Manager tool as much as possible. This study is the first opportunity to investigate archetype reuse within a range of diverse, multilingual openEHR templates. Objective: This study aims to investigate the use and reuse of openEHR archetypes across the 7 openEHR templates as an initial investigation about the reuse of information models across data sets used for a variety of clinical purposes. Methods: Analysis of both the number of occurrences of archetypes and patterns of occurrence within 7 discrete templates was carried out at the archetype or clinical concept level. Results: Across all 7 templates collectively, 203 instances of 58 unique archetypes were used. The most frequently used archetype occurred 24 times across 4 of the 7 templates. Total data points per template ranged from 40 to 179. Archetype instances per template ranged from 10 to 62. Unique archetype occurrences ranged from 10 to 28. Existing archetype reuse of use-case agnostic archetypes ranged from 40% to 90%. Total reuse of use-case agnostic archetypes ranged from 40% to 100%. Conclusions: Investigation of the amount of archetype reuse across the 7 openEHR templates in this initial study has demonstrated significant reuse of archetypes, even across unanticipated, novel modeling challenges and multilingual deployments. While the trigger for the development of each of these templates was the COVID-19 pandemic, the templates represented a variety of types of data sets: symptom screening, infection report, clinical decision support for diagnosis and treatment, and secondary use or research. The findings support the openEHR hypothesis that it is possible to create a shared, public library of standards-based, vendor-neutral clinical information models that can be reused across a diverse range of health data sets. %M 33035176 %R 10.2196/23361 %U https://www.jmir.org/2020/11/e23361 %U https://doi.org/10.2196/23361 %U http://www.ncbi.nlm.nih.gov/pubmed/33035176 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 10 %P e21801 %T Clinical Characteristics and Prognostic Factors for Intensive Care Unit Admission of Patients With COVID-19: Retrospective Study Using Machine Learning and Natural Language Processing %A Izquierdo,Jose Luis %A Ancochea,Julio %A , %A Soriano,Joan B %+ Hospital Universitario de La Princesa, Diego de León 62, Madrid, 28005, Spain, 34 618867769, jbsoriano2@gmail.com %K artificial intelligence %K big data %K COVID-19 %K electronic health records %K tachypnea %K SARS-CoV-2 %K predictive model %D 2020 %7 28.10.2020 %9 Original Paper %J J Med Internet Res %G English %X Background: Many factors involved in the onset and clinical course of the ongoing COVID-19 pandemic are still unknown. Although big data analytics and artificial intelligence are widely used in the realms of health and medicine, researchers are only beginning to use these tools to explore the clinical characteristics and predictive factors of patients with COVID-19. Objective: Our primary objectives are to describe the clinical characteristics and determine the factors that predict intensive care unit (ICU) admission of patients with COVID-19. Determining these factors using a well-defined population can increase our understanding of the real-world epidemiology of the disease. Methods: We used a combination of classic epidemiological methods, natural language processing (NLP), and machine learning (for predictive modeling) to analyze the electronic health records (EHRs) of patients with COVID-19. We explored the unstructured free text in the EHRs within the Servicio de Salud de Castilla-La Mancha (SESCAM) Health Care Network (Castilla-La Mancha, Spain) from the entire population with available EHRs (1,364,924 patients) from January 1 to March 29, 2020. We extracted related clinical information regarding diagnosis, progression, and outcome for all COVID-19 cases. Results: A total of 10,504 patients with a clinical or polymerase chain reaction–confirmed diagnosis of COVID-19 were identified; 5519 (52.5%) were male, with a mean age of 58.2 years (SD 19.7). Upon admission, the most common symptoms were cough, fever, and dyspnea; however, all three symptoms occurred in fewer than half of the cases. Overall, 6.1% (83/1353) of hospitalized patients required ICU admission. Using a machine-learning, data-driven algorithm, we identified that a combination of age, fever, and tachypnea was the most parsimonious predictor of ICU admission; patients younger than 56 years, without tachypnea, and temperature <39 degrees Celsius (or >39 ºC without respiratory crackles) were not admitted to the ICU. In contrast, patients with COVID-19 aged 40 to 79 years were likely to be admitted to the ICU if they had tachypnea and delayed their visit to the emergency department after being seen in primary care. Conclusions: Our results show that a combination of easily obtainable clinical variables (age, fever, and tachypnea with or without respiratory crackles) predicts whether patients with COVID-19 will require ICU admission. %M 33090964 %R 10.2196/21801 %U http://www.jmir.org/2020/10/e21801/ %U https://doi.org/10.2196/21801 %U http://www.ncbi.nlm.nih.gov/pubmed/33090964 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 8 %N 10 %P e23680 %T Feasibility of Asynchronous and Automated Telemedicine in Otolaryngology: Prospective Cross-Sectional Study %A Cha,Dongchul %A Shin,Seung Ho %A Kim,Jungghi %A Eo,Tae Seong %A Na,Gina %A Bae,Seonghoon %A Jung,Jinsei %A Kim,Sung Huhn %A Moon,In Seok %A Choi,Jaeyoung %A Park,Yu Rang %+ Department of Biomedical Systems Informatics, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Republic of Korea, 82 2 2228 2363, yurangpark@yuhs.ac %K telemedicine %K otolaryngology %K otology %K automated diagnosis %K asynchronous %K COVID-19 %K diagnosis %K feasibility %K cross-sectional %D 2020 %7 19.10.2020 %9 Original Paper %J JMIR Med Inform %G English %X Background: COVID-19 often causes respiratory symptoms, making otolaryngology offices one of the most susceptible places for community transmission of the virus. Thus, telemedicine may benefit both patients and physicians. Objective: This study aims to explore the feasibility of telemedicine for the diagnosis of all otologic disease types. Methods: A total of 177 patients were prospectively enrolled, and the patient’s clinical manifestations with otoendoscopic images were written in the electrical medical records. Asynchronous diagnoses were made for each patient to assess Top-1 and Top-2 accuracy, and we selected 20 cases to conduct a survey among four different otolaryngologists to assess the accuracy, interrater agreement, and diagnostic speed. We also constructed an experimental automated diagnosis system and assessed Top-1 accuracy and diagnostic speed. Results: Asynchronous diagnosis showed Top-1 and Top-2 accuracies of 77.40% and 86.44%, respectively. In the selected 20 cases, the Top-2 accuracy of the four otolaryngologists was on average 91.25% (SD 7.50%), with an almost perfect agreement between them (Cohen kappa=0.91). The automated diagnostic model system showed 69.50% Top-1 accuracy. Otolaryngologists could diagnose an average of 1.55 (SD 0.48) patients per minute, while the machine learning model was capable of diagnosing on average 667.90 (SD 8.3) patients per minute. Conclusions: Asynchronous telemedicine in otology is feasible owing to the reasonable Top-2 accuracy when assessed by experienced otolaryngologists. Moreover, enhanced diagnostic speed while sustaining the accuracy shows the possibility of optimizing medical resources to provide expertise in areas short of physicians. %M 33027033 %R 10.2196/23680 %U http://medinform.jmir.org/2020/10/e23680/ %U https://doi.org/10.2196/23680 %U http://www.ncbi.nlm.nih.gov/pubmed/33027033 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 8 %N 10 %P e21628 %T A Computer-Interpretable Guideline for COVID-19: Rapid Development and Dissemination %A Nan,Shan %A Tang,Tianhua %A Feng,Hongshuo %A Wang,Yijie %A Li,Mengyang %A Lu,Xudong %A Duan,Huilong %+ College of Biomedical Engineering and Instrumental Science, Zhejiang University, Zhouyiqing Building, 512, 38 Zheda Road, Hangzhou, Hangzhou, 310027, China, 86 13957118891, lvxd@zju.edu.cn %K COVID-19 %K guideline %K CDSS %K openEHR %K Guideline Definition Language %K development %K dissemination %K electronic health record %K algorithm %D 2020 %7 1.10.2020 %9 Original Paper %J JMIR Med Inform %G English %X Background: COVID-19 is a global pandemic that is affecting more than 200 countries worldwide. Efficient diagnosis and treatment are crucial to combat the disease. Computer-interpretable guidelines (CIGs) can aid the broad global adoption of evidence-based diagnosis and treatment knowledge. However, currently, no internationally shareable CIG exists. Objective: The aim of this study was to establish a rapid CIG development and dissemination approach and apply it to develop a shareable CIG for COVID-19. Methods: A 6-step rapid CIG development and dissemination approach was designed and applied. Processes, roles, and deliverable artifacts were specified in this approach to eliminate ambiguities during development of the CIG. The Guideline Definition Language (GDL) was used to capture the clinical rules. A CIG for COVID-19 was developed by translating, interpreting, annotating, extracting, and formalizing the Chinese COVID-19 diagnosis and treatment guideline. A prototype application was implemented to validate the CIG. Results: We used 27 archetypes for the COVID-19 guideline. We developed 18 GDL rules to cover the diagnosis and treatment suggestion algorithms in the narrative guideline. The CIG was further translated to object data model and Drools rules to facilitate its use by people who do not employ the non-openEHR archetype. The prototype application validated the correctness of the CIG with a public data set. Both the GDL rules and Drools rules have been disseminated on GitHub. Conclusions: Our rapid CIG development and dissemination approach accelerated the pace of COVID-19 CIG development. A validated COVID-19 CIG is now available to the public. %M 32931443 %R 10.2196/21628 %U https://medinform.jmir.org/2020/10/e21628 %U https://doi.org/10.2196/21628 %U http://www.ncbi.nlm.nih.gov/pubmed/32931443 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 8 %N 9 %P e20477 %T Applying Blockchain Technology to Address the Crisis of Trust During the COVID-19 Pandemic %A Khurshid,Anjum %+ The University of Texas at Austin, 1701 Trinity Street, Austin, TX, 78712, United States, 1 5124955225, anjum.khurshid@austin.utexas.edu %K blockchain %K privacy %K trust %K contact tracing %K COVID-19 %K coronavirus %D 2020 %7 22.9.2020 %9 Viewpoint %J JMIR Med Inform %G English %X Background: The widespread death and disruption caused by the COVID-19 pandemic has revealed deficiencies of existing institutions regarding the protection of human health and well-being. Both a lack of accurate and timely data and pervasive misinformation are causing increasing harm and growing tension between data privacy and public health concerns. Objective: This aim of this paper is to describe how blockchain, with its distributed trust networks and cryptography-based security, can provide solutions to data-related trust problems. Methods: Blockchain is being applied in innovative ways that are relevant to the current COVID-19 crisis. We describe examples of the challenges faced by existing technologies to track medical supplies and infected patients and how blockchain technology applications may help in these situations. Results: This exploration of existing and potential applications of blockchain technology for medical care shows how the distributed governance structure and privacy-preserving features of blockchain can be used to create “trustless” systems that can help resolve the tension between maintaining privacy and addressing public health needs in the fight against COVID-19. Conclusions: Blockchain relies on a distributed, robust, secure, privacy-preserving, and immutable record framework that can positively transform the nature of trust, value sharing, and transactions. A nationally coordinated effort to explore blockchain to address the deficiencies of existing systems and a partnership of academia, researchers, business, and industry are suggested to expedite the adoption of blockchain in health care. %M 32903197 %R 10.2196/20477 %U http://medinform.jmir.org/2020/9/e20477/ %U https://doi.org/10.2196/20477 %U http://www.ncbi.nlm.nih.gov/pubmed/32903197 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 8 %N 9 %P e19588 %T Nomogram for Predicting COVID-19 Disease Progression Based on Single-Center Data: Observational Study and Model Development %A Fan,Tao %A Hao,Bo %A Yang,Shuo %A Shen,Bo %A Huang,Zhixin %A Lu,Zilong %A Xiong,Rui %A Shen,Xiaokang %A Jiang,Wenyang %A Zhang,Lin %A Li,Donghang %A He,Ruyuan %A Meng,Heng %A Lin,Weichen %A Feng,Haojie %A Geng,Qing %+ Renmin Hospital, Wuhan University, 238 Jiefang Road, Wuhan, 430060, China, 27 88041911 880419, gengqingwhu@whu.edu.cn %K coronavirus disease 2019 %K COVID-19 %K risk factors %K nomogram %D 2020 %7 8.9.2020 %9 Original Paper %J JMIR Med Inform %G English %X Background: In late December 2019, a pneumonia caused by SARS-CoV-2 was first reported in Wuhan and spread worldwide rapidly. Currently, no specific medicine is available to treat infection with COVID-19. Objective: The aims of this study were to summarize the epidemiological and clinical characteristics of 175 patients with SARS-CoV-2 infection who were hospitalized in Renmin Hospital of Wuhan University from January 1 to January 31, 2020, and to establish a tool to identify potential critical patients with COVID-19 and help clinical physicians prevent progression of this disease. Methods: In this retrospective study, clinical characteristics of 175 confirmed COVID-19 cases were collected and analyzed. Univariate analysis and least absolute shrinkage and selection operator (LASSO) regression were used to select variables. Multivariate analysis was applied to identify independent risk factors in COVID-19 progression. We established a nomogram to evaluate the probability of progression of the condition of a patient with COVID-19 to severe within three weeks of disease onset. The nomogram was verified using calibration curves and receiver operating characteristic curves. Results: A total of 18 variables were considered to be risk factors after the univariate regression analysis of the laboratory parameters (P<.05), and LASSO regression analysis screened out 10 risk factors for further study. The six independent risk factors revealed by multivariate Cox regression were age (OR 1.035, 95% CI 1.017-1.054; P<.001), CK level (OR 1.002, 95% CI 1.0003-1.0039; P=.02), CD4 count (OR 0.995, 95% CI 0.992-0.998; P=.002), CD8 % (OR 1.007, 95% CI 1.004-1.012, P<.001), CD8 count (OR 0.881, 95% CI 0.835-0.931; P<.001), and C3 count (OR 6.93, 95% CI 1.945-24.691; P=.003). The areas under the curve of the prediction model for 0.5-week, 1-week, 2-week and 3-week nonsevere probability were 0.721, 0.742, 0.87, and 0.832, respectively. The calibration curves showed that the model had good prediction ability within three weeks of disease onset. Conclusions: This study presents a predictive nomogram of critical patients with COVID-19 based on LASSO and Cox regression analysis. Clinical use of the nomogram may enable timely detection of potential critical patients with COVID-19 and instruct clinicians to administer early intervention to these patients to prevent the disease from worsening. %M 32866109 %R 10.2196/19588 %U http://medinform.jmir.org/2020/9/e19588/ %U https://doi.org/10.2196/19588 %U http://www.ncbi.nlm.nih.gov/pubmed/32866109 %0 Journal Article %@ 2291-5222 %I JMIR Publications %V 8 %N 9 %P e22321 %T A QR Code–Based Contact Tracing Framework for Sustainable Containment of COVID-19: Evaluation of an Approach to Assist the Return to Normal Activity %A Nakamoto,Ichiro %A Wang,Sheng %A Guo,Yan %A Zhuang,Weiqing %+ School of Internet Economics and Business, Fujian University of Technology, 999 Dongsanhuang Road, JinAn District, Fuzhou , China, 86 132 550 66365, fw107@foxmail.com %K COVID-19 %K coronavirus %K symptom-based %K quick response %K eHealth %K digital health %K telesurveillance %K pandemic %K epidemic %K interoperability %D 2020 %7 7.9.2020 %9 Viewpoint %J JMIR Mhealth Uhealth %G English %X We discuss a pandemic management framework using symptom-based quick response (QR) codes to contain the spread of COVID-19. In this approach, symptom-based QR health codes are issued by public health authorities. The codes do not retrieve the location data of the users; instead, two different colors are displayed to differentiate the health status of individuals. The QR codes are officially regarded as electronic certificates of individuals’ health status, and can be used for contact tracing, exposure risk self-triage, self-update of health status, health care appointments, and contact-free psychiatric consultations. This approach can be effectively deployed as a uniform platform interconnecting a variety of responders (eg, individuals, institutions, and public authorities) who are affected by the pandemic, which minimizes the errors of manual operation and the costs of fragmented coordination. At the same time, this approach enhances the promptness, interoperability, credibility, and traceability of containment measures. The proposed approach not only provides a supplemental mechanism for manual control measures but also addresses the partial failures of pandemic management tools in the abovementioned facets. The QR tool has been formally deployed in Fujian, a province located in southeast China that has a population of nearly 40 million people. All individuals aged ≥3 years were officially requested to present their QR code during daily public activities, such as when using public transportation systems, working at institutions, and entering or exiting schools. The deployment of this approach has achieved sizeable containment effects and played remarkable roles in shifting the negative gross domestic product (–6.8%) to a positive value by July 2020. The number of cumulative patients with COVID-19 in this setting was confined to 363, of whom 361 had recovered (recovery rate 99.4%) as of July 12, 2020. A simulation showed that if only partial measures of the framework were followed, the number of cumulative cases of COVID-19 could potentially increase ten-fold. This approach can serve as a reliable solution to counteract the emergency of a public health crisis; as a routine tool to enhance the level of public health; to accelerate the recovery of social activities; to assist decision making for policy makers; and as a sustainable measure that enables scalability. %M 32841151 %R 10.2196/22321 %U http://mhealth.jmir.org/2020/9/e22321/ %U https://doi.org/10.2196/22321 %U http://www.ncbi.nlm.nih.gov/pubmed/32841151 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 9 %P e20953 %T Telemonitoring for Patients With COVID-19: Recommendations for Design and Implementation %A Silven,Anna V %A Petrus,Annelieke H J %A Villalobos-Quesada,María %A Dirikgil,Ebru %A Oerlemans,Carlijn R %A Landstra,Cyril P %A Boosman,Hileen %A van Os,Hendrikus J A %A Blanker,Marco H %A Treskes,Roderick W %A Bonten,Tobias N %A Chavannes,Niels H %A Atsma,Douwe E %A Teng,Y K Onno %+ Department of Cardiology, Leiden University Medical Center, Albinusdreef 2, Leiden, 2333 ZA, Netherlands, 31 715262038, d.e.atsma@lumc.nl %K telemonitoring %K telemedicine %K eHealth %K digital health %K COVID-19 %D 2020 %7 2.9.2020 %9 Viewpoint %J J Med Internet Res %G English %X Despite significant efforts, the COVID-19 pandemic has put enormous pressure on health care systems around the world, threatening the quality of patient care. Telemonitoring offers the opportunity to carefully monitor patients with a confirmed or suspected case of COVID-19 from home and allows for the timely identification of worsening symptoms. Additionally, it may decrease the number of hospital visits and admissions, thereby reducing the use of scarce resources, optimizing health care capacity, and minimizing the risk of viral transmission. In this paper, we present a COVID-19 telemonitoring care pathway developed at a tertiary care hospital in the Netherlands, which combined the monitoring of vital parameters with video consultations for adequate clinical assessment. Additionally, we report a series of medical, scientific, organizational, and ethical recommendations that may be used as a guide for the design and implementation of telemonitoring pathways for COVID-19 and other diseases worldwide. %M 32833660 %R 10.2196/20953 %U https://www.jmir.org/2020/9/e20953 %U https://doi.org/10.2196/20953 %U http://www.ncbi.nlm.nih.gov/pubmed/32833660 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 8 %N 8 %P e20992 %T Nationwide Results of COVID-19 Contact Tracing in South Korea: Individual Participant Data From an Epidemiological Survey %A Lee,Seung Won %A Yuh,Woon Tak %A Yang,Jee Myung %A Cho,Yoon-Sik %A Yoo,In Kyung %A Koh,Hyun Yong %A Marshall,Dominic %A Oh,Donghwan %A Ha,Eun Kyo %A Han,Man Yong %A Yon,Dong Keon %+ Armed Force Medical Command, Republic of Korea Armed Forces, 81 Saemaeul-ro 177, Seongnam, 463-040, Republic of Korea, 82 2 6935 2476, yonkkang@gmail.com %K COVID-19 %K contact tracing %K coronavirus %K South Korea %K survey %K health data %K epidemiology %K transmission %D 2020 %7 25.8.2020 %9 Original Paper %J JMIR Med Inform %G English %X Background: Evidence regarding the effectiveness of contact tracing of COVID-19 and the related social distancing is limited and inconclusive. Objective: This study aims to investigate the epidemiological characteristics of SARS-CoV-2 transmission in South Korea and evaluate whether a social distancing campaign is effective in mitigating the spread of COVID-19. Methods: We used contract tracing data to investigate the epidemic characteristics of SARS-CoV-2 transmission in South Korea and evaluate whether a social distancing campaign was effective in mitigating the spread of COVID-19. We calculated the mortality rate for COVID-19 by infection type (cluster vs noncluster) and tested whether new confirmed COVID-19 trends changed after a social distancing campaign. Results: There were 2537 patients with confirmed COVID-19 who completed the epidemiologic survey: 1305 (51.4%) cluster cases and 1232 (48.6%) noncluster cases. The mortality rate was significantly higher in cluster cases linked to medical facilities (11/143, 7.70% vs 5/1232, 0.41%; adjusted percentage difference 7.99%; 95% CI 5.83 to 10.14) and long-term care facilities (19/221, 8.60% vs 5/1232, 0.41%; adjusted percentage difference 7.56%; 95% CI 5.66 to 9.47) than in noncluster cases. The change in trends of newly confirmed COVID-19 cases before and after the social distancing campaign was significantly negative in the entire cohort (adjusted trend difference –2.28; 95% CI –3.88 to –0.68) and the cluster infection group (adjusted trend difference –0.96; 95% CI –1.83 to –0.09). Conclusions: In a nationwide contact tracing study in South Korea, COVID-19 linked to medical and long-term care facilities significantly increased the risk of mortality compared to noncluster COVID-19. A social distancing campaign decreased the spread of COVID-19 in South Korea and differentially affected cluster infections of SARS-CoV-2. %M 32784189 %R 10.2196/20992 %U http://medinform.jmir.org/2020/8/e20992/ %U https://doi.org/10.2196/20992 %U http://www.ncbi.nlm.nih.gov/pubmed/32784189 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 8 %P e20773 %T Natural Language Processing for Rapid Response to Emergent Diseases: Case Study of Calcium Channel Blockers and Hypertension in the COVID-19 Pandemic %A Neuraz,Antoine %A Lerner,Ivan %A Digan,William %A Paris,Nicolas %A Tsopra,Rosy %A Rogier,Alice %A Baudoin,David %A Cohen,Kevin Bretonnel %A Burgun,Anita %A Garcelon,Nicolas %A Rance,Bastien %A , %+ Department of Biomedical Informatics, Necker-Enfant Malades Hospital, Assistance Publique – Hôpitaux de Paris (AP-HP), Bat Imagine, Bureau 145, 149 rue de Sèvres, Paris, 75015, France, 33 0624622355, antoine.neuraz@aphp.fr %K medication information %K natural language processing %K electronic health records %K COVID-19 %K public health %K response %K emergent disease %K informatics %D 2020 %7 14.8.2020 %9 Original Paper %J J Med Internet Res %G English %X Background: A novel disease poses special challenges for informatics solutions. Biomedical informatics relies for the most part on structured data, which require a preexisting data or knowledge model; however, novel diseases do not have preexisting knowledge models. In an emergent epidemic, language processing can enable rapid conversion of unstructured text to a novel knowledge model. However, although this idea has often been suggested, no opportunity has arisen to actually test it in real time. The current coronavirus disease (COVID-19) pandemic presents such an opportunity. Objective: The aim of this study was to evaluate the added value of information from clinical text in response to emergent diseases using natural language processing (NLP). Methods: We explored the effects of long-term treatment by calcium channel blockers on the outcomes of COVID-19 infection in patients with high blood pressure during in-patient hospital stays using two sources of information: data available strictly from structured electronic health records (EHRs) and data available through structured EHRs and text mining. Results: In this multicenter study involving 39 hospitals, text mining increased the statistical power sufficiently to change a negative result for an adjusted hazard ratio to a positive one. Compared to the baseline structured data, the number of patients available for inclusion in the study increased by 2.95 times, the amount of available information on medications increased by 7.2 times, and the amount of additional phenotypic information increased by 11.9 times. Conclusions: In our study, use of calcium channel blockers was associated with decreased in-hospital mortality in patients with COVID-19 infection. This finding was obtained by quickly adapting an NLP pipeline to the domain of the novel disease; the adapted pipeline still performed sufficiently to extract useful information. When that information was used to supplement existing structured data, the sample size could be increased sufficiently to see treatment effects that were not previously statistically detectable. %M 32759101 %R 10.2196/20773 %U http://www.jmir.org/2020/8/e20773/ %U https://doi.org/10.2196/20773 %U http://www.ncbi.nlm.nih.gov/pubmed/32759101 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 8 %N 7 %P e19866 %T The Role of Health Technology and Informatics in a Global Public Health Emergency: Practices and Implications From the COVID-19 Pandemic %A Ye,Jiancheng %+ Feinberg School of Medicine, Northwestern University, 633 N Saint Clair St, Chicago, IL, United States, 1 312 503 3690, jiancheng.ye@u.northwestern.edu %K health technology %K health information system %K COVID-19 %K artificial intelligence %K telemedicine %K big data %K privacy %D 2020 %7 14.7.2020 %9 Viewpoint %J JMIR Med Inform %G English %X At present, the coronavirus disease (COVID-19) is spreading around the world. It is a critical and important task to take thorough efforts to prevent and control the pandemic. Compared with severe acute respiratory syndrome and Middle East Respiratory Syndrome, COVID-19 spreads more rapidly owing to increased globalization, a longer incubation period, and unobvious symptoms. As the coronavirus has the characteristics of strong transmission and weak lethality, and since the large-scale increase of infected people may overwhelm health care systems, efforts are needed to treat critical patients, track and manage the health status of residents, and isolate suspected patients. The application of emerging health technologies and digital practices in health care, such as artificial intelligence, telemedicine or telehealth, mobile health, big data, 5G, and the Internet of Things, have become powerful “weapons” to fight against the pandemic and provide strong support in pandemic prevention and control. Applications and evaluations of all of these technologies, practices, and health delivery services are highlighted in this study. %M 32568725 %R 10.2196/19866 %U http://medinform.jmir.org/2020/7/e19866/ %U https://doi.org/10.2196/19866 %U http://www.ncbi.nlm.nih.gov/pubmed/32568725 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 6 %P e19938 %T Information Technology–Based Management of Clinically Healthy COVID-19 Patients: Lessons From a Living and Treatment Support Center Operated by Seoul National University Hospital %A Bae,Ye Seul %A Kim,Kyung Hwan %A Choi,Sae Won %A Ko,Taehoon %A Jeong,Chang Wook %A Cho,BeLong %A Kim,Min Sun %A Kang,EunKyo %+ Office of Hospital Information, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea, 82 2 2072 7600, kkh726@snu.ac.kr %K COVID-19 %K clinical informatics %K mobile app %K telemedicine %K hospital information system %K app %K health information technology %D 2020 %7 12.6.2020 %9 Original Paper %J J Med Internet Res %G English %X Background: South Korea took preemptive action against coronavirus disease (COVID-19) by implementing extensive testing, thorough epidemiological investigation, strict social distancing, and rapid treatment of patients according to disease severity. The Korean government entrusted large-scale hospitals with the operation of living and treatment support centers (LTSCs) for the management for clinically healthy COVID-19 patients. Objective: The aim of this paper is to introduce our experience implementing information and communications technology (ICT)-based remote patient management systems at a COVID-19 LTSC. Methods: We adopted new electronic health record templates, hospital information system (HIS) dashboards, cloud-based medical image sharing, a mobile app, and smart vital sign monitoring devices. Results: Enhancements were made to the HIS to assist in the workflow and care of patients in the LTSC. A dashboard was created for the medical staff to view the vital signs and symptoms of all patients. Patients used a mobile app to consult with their physician or nurse, answer questionnaires, and input self-measured vital signs; the results were uploaded to the hospital information system in real time. Cloud-based image sharing enabled interoperability between medical institutions. Korea’s strategy of aggressive mitigation has “flattened the curve” of the rate of infection. A multidisciplinary approach was integral to develop systems supporting patient care and management at the living and treatment support center as quickly as possible. Conclusions: Faced with a novel infectious disease, we describe the implementation and experience of applying an ICT-based patient management system in the LTSC affiliated with Seoul National University Hospital. ICT-based tools and applications are increasingly important in health care, and we hope that our experience will provide insight into future technology-based infectious disease responses. %M 32490843 %R 10.2196/19938 %U http://www.jmir.org/2020/6/e19938/ %U https://doi.org/10.2196/19938 %U http://www.ncbi.nlm.nih.gov/pubmed/32490843 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 6 %P e20239 %T Development of an openEHR Template for COVID-19 Based on Clinical Guidelines %A Li,Mengyang %A Leslie,Heather %A Qi,Bin %A Nan,Shan %A Feng,Hongshuo %A Cai,Hailing %A Lu,Xudong %A Duan,Huilong %+ College of Biomedical Engineering and Instrument Science, Zhejiang University, Room 512, Zhouyiqing Building, 38 Zheda Road, Hangzhou, Zhejiang, 310007, China, 86 13957118891, lvxd@zju.edu.cn %K coronavirus disease %K COVID-19 %K openEHR %K archetype %K template %K knowledge modeling %K clinical guidelines %D 2020 %7 10.6.2020 %9 Original Paper %J J Med Internet Res %G English %X Background: The coronavirus disease (COVID-19) was discovered in China in December 2019. It has developed into a threatening international public health emergency. With the exception of China, the number of cases continues to increase worldwide. A number of studies about disease diagnosis and treatment have been carried out, and many clinically proven effective results have been achieved. Although information technology can improve the transferring of such knowledge to clinical practice rapidly, data interoperability is still a challenge due to the heterogeneous nature of hospital information systems. This issue becomes even more serious if the knowledge for diagnosis and treatment is updated rapidly as is the case for COVID-19. An open, semantic-sharing, and collaborative-information modeling framework is needed to rapidly develop a shared data model for exchanging data among systems. openEHR is such a framework and is supported by many open software packages that help to promote information sharing and interoperability. Objective: This study aims to develop a shared data model based on the openEHR modeling approach to improve the interoperability among systems for the diagnosis and treatment of COVID-19. Methods: The latest Guideline of COVID-19 Diagnosis and Treatment in China was selected as the knowledge source for modeling. First, the guideline was analyzed and the data items used for diagnosis and treatment, and management were extracted. Second, the data items were classified and further organized into domain concepts with a mind map. Third, searching was executed in the international openEHR Clinical Knowledge Manager (CKM) to find the existing archetypes that could represent the concepts. New archetypes were developed for those concepts that could not be found. Fourth, these archetypes were further organized into a template using Ocean Template Editor. Fifth, a test case of data exchanging between the clinical data repository and clinical decision support system based on the template was conducted to verify the feasibility of the study. Results: A total of 203 data items were extracted from the guideline in China, and 16 domain concepts (16 leaf nodes in the mind map) were organized. There were 22 archetypes used to develop the template for all data items extracted from the guideline. All of them could be found in the CKM and reused directly. The archetypes and templates were reviewed and finally released in a public project within the CKM. The test case showed that the template can facilitate the data exchange and meet the requirements of decision support. Conclusions: This study has developed the openEHR template for COVID-19 based on the latest guideline from China using openEHR modeling methodology. It represented the capability of the methodology for rapidly modeling and sharing knowledge through reusing the existing archetypes, which is especially useful in a new and fast-changing area such as with COVID-19. %M 32496207 %R 10.2196/20239 %U http://www.jmir.org/2020/6/e20239/ %U https://doi.org/10.2196/20239 %U http://www.ncbi.nlm.nih.gov/pubmed/32496207