Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Monday, March 11, 2019 at 4:00 PM to 4:30 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?


Journal Description

JMIR Medical Informatics (JMI, ISSN 2291-9694) (Editor-in-chief: Christian Lovis MD MPH FACMI) is a Pubmed/SCIE-indexed, top-rated, tier A journal with impact factor expected in 2019, which focuses on clinical informatics, big data in health and health care, decision support for health professionals, electronic health records, ehealth infrastructures and implementation. It has a focus on applied, translational research, with a broad readership including clinicians, CIOs, engineers, industry and health informatics professionals.

Published by JMIR Publications, publisher of the Journal of Medical Internet Research (JMIR), the leading eHealth/mHealth journal (Impact Factor 2018: 4.671), JMIR Med Inform has a slightly different scope (emphasizing more on applications for clinicians and health professionals rather than consumers/citizens, which is the focus of JMIR), publishes even faster, and also allows papers which are more technical or more formative than what would be published in the Journal of Medical Internet Research.

JMIR Medical Informatics is indexed in PubMed Central/PubMed, and has also been accepted for SCIE, with an official Clarivate impact factor 2018 expected to be released in 2019 (see announcement).

JMIR Medical Informatics adheres to the same quality standards as JMIR and all articles published here are also cross-listed in the Table of Contents of JMIR, the worlds' leading medical journal in health sciences / health services research and health informatics (


Recent Articles:

  • Monitoring chronic diseases. Source:; Copyright: marcus; URL:; License: Licensed by the authors.

    Toward Standardized Monitoring of Patients With Chronic Diseases in Primary Care Using Electronic Medical Records: Systematic Review


    Background: Long-term care for patients with chronic diseases poses a huge challenge in primary care. In particular, there is a deficit regarding monitoring and structured follow-up. Appropriate electronic medical records (EMRs) could help improving this but, so far, there are no evidence-based specifications concerning the indicators that should be monitored at regular intervals. Objective: The aim was to identify and collect a set of evidence-based indicators that could be used for monitoring chronic conditions at regular intervals in primary care using EMRs. Methods: We searched MEDLINE (Ovid), Embase (Elsevier), the Cochrane Library (Wiley), the reference lists of included studies and relevant reviews, and the content of clinical guidelines. We included primary studies and guidelines reporting about indicators that allow for the assessment of care and help monitor the status and process of disease for five chronic conditions, including type 2 diabetes mellitus, asthma, arterial hypertension, chronic heart failure, and osteoarthritis. Results: The use of the term “monitoring” in terms of disease management and long-term care for patients with chronic diseases is not widely used in the literature. Nevertheless, we identified a substantial number of disease-specific indicators that can be used for routine monitoring of chronic diseases in primary care by means of EMRs. Conclusions: To our knowledge, this is the first systematic review summarizing the existing scientific evidence on the standardized long-term monitoring of chronic diseases using EMRs. In a second step, our extensive set of indicators will serve as a generic template for evaluating their usability by means of an adapted Delphi procedure. In a third step, the indicators will be summarized into a user-friendly EMR layout.

  • Source: Boteng Huang; Copyright: Boteng Huang; URL:; License: Creative Commons Attribution + ShareAlike (CC-BY-SA).

    Development of a Consumer Health Vocabulary by Mining Health Forum Texts Based on Word Embedding: Semiautomatic Approach


    Background: The vocabulary gap between consumers and professionals in the medical domain hinders information seeking and communication. Consumer health vocabularies have been developed to aid such informatics applications. This purpose is best served if the vocabulary evolves with consumers’ language. Objective: Our objective is to develop a method for identifying and adding new terms to consumer health vocabularies, so that it can keep up with the constantly evolving medical knowledge and language use. Methods: In this paper, we propose a consumer health term–finding framework based on a distributed word vector space model. We first learned word vectors from a large-scale text corpus and then adopted a supervised method with existing consumer health vocabularies for learning vector representation of words, which can provide additional supervised fine tuning after unsupervised word embedding learning. With a fine-tuned word vector space, we identified pairs of professional terms and their consumer variants by their semantic distance in the vector space. A subsequent manual review of the extracted and labeled pairs of entities was conducted to validate the results generated by the proposed approach. The results were evaluated using mean reciprocal rank (MRR). Results: Manual evaluation showed that it is feasible to identify alternative medical concepts by using professional or consumer concepts as queries in the word vector space without fine tuning, but the results are more promising in the final fine-tuned word vector space. The MRR values indicated that on an average, a professional or consumer concept is about 14th closest to its counterpart in the word vector space without fine tuning, and the MRR in the final fine-tuned word vector space is 8. Furthermore, the results demonstrate that our method can collect abbreviations and common typos frequently used by consumers. Conclusions: By integrating a large amount of text information and existing consumer health vocabularies, our method outperformed several baseline ranking methods and is effective for generating a list of candidate terms for human review during consumer health vocabulary development.

  • Source: Image created by the Authors; Copyright: The Authors; URL:; License: Creative Commons Attribution (CC-BY).

    Fast Healthcare Interoperability Resources, Clinical Quality Language, and Systematized Nomenclature of Medicine—Clinical Terms in Representing Clinical...


    Background: Evidence-based guidelines and recommendations can be transformed into “If-Then” Clinical Evidence Logic Statements (CELS). Imaging-related CELS were represented in standardized formats in the Harvard Medical School Library of Evidence (HLE). Objective: We aimed to (1) describe the representation of CELS using established Systematized Nomenclature of Medicine—Clinical Terms (SNOMED CT), Clinical Quality Language (CQL), and Fast Healthcare Interoperability Resources (FHIR) standards and (2) assess the limitations of using these standards to represent imaging-related CELS. Methods: This study was exempt from review by the Institutional Review Board as it involved no human subjects. Imaging-related clinical recommendations were extracted from evidence sources and translated into CELS. The clinical terminologies of CELS were represented using SNOMED CT and the condition-action logic was represented in CQL and FHIR. Numbers of fully and partially represented CELS were tallied. Results: A total of 765 CELS were represented in the HLE as of December 2018. We were able to fully represent 137 of 765 (17.9%) CELS using SNOMED CT, CQL, and FHIR. We were able to represent terms using SNOMED CT in the temporal component for action (“Then”) statements in CQL and FHIR in 755 of 765 (98.7%) CELS. Conclusions: CELS were represented as shareable clinical decision support (CDS) knowledge artifacts using existing standards—SNOMED CT, FHIR, and CQL—to promote and accelerate adoption of evidence-based practice. Limitations to standardization persist, which could be minimized with an add-on set of standard terms and value sets and by adding time frames to the CQL framework.

  • Source: Pexels; Copyright:; URL:; License: Licensed by the authors.

    Identifying Clinical Terms in Medical Text Using Ontology-Guided Machine Learning


    Background: Automatic recognition of medical concepts in unstructured text is an important component of many clinical and research applications, and its accuracy has a large impact on electronic health record analysis. The mining of medical concepts is complicated by the broad use of synonyms and nonstandard terms in medical documents. Objective: We present a machine learning model for concept recognition in large unstructured text, which optimizes the use of ontological structures and can identify previously unobserved synonyms for concepts in the ontology. Methods: We present a neural dictionary model that can be used to predict if a phrase is synonymous to a concept in a reference ontology. Our model, called the Neural Concept Recognizer (NCR), uses a convolutional neural network to encode input phrases and then rank medical concepts based on the similarity in that space. It uses the hierarchical structure provided by the biomedical ontology as an implicit prior embedding to better learn embedding of various terms. We trained our model on two biomedical ontologies—the Human Phenotype Ontology (HPO) and Systematized Nomenclature of Medicine - Clinical Terms (SNOMED-CT). Results: We tested our model trained on HPO by using two different data sets: 288 annotated PubMed abstracts and 39 clinical reports. We achieved 1.7%-3% higher F1-scores than those for our strongest manually engineered rule-based baselines (P=.003). We also tested our model trained on the SNOMED-CT by using 2000 Intensive Care Unit discharge summaries from MIMIC (Multiparameter Intelligent Monitoring in Intensive Care) and achieved 0.9%-1.3% higher F1-scores than those of our baseline. The results of our experiments show high accuracy of our model as well as the value of using the taxonomy structure of the ontology in concept recognition. Conclusion: Most popular medical concept recognizers rely on rule-based models, which cannot generalize well to unseen synonyms. In addition, most machine learning methods typically require large corpora of annotated text that cover all classes of concepts, which can be extremely difficult to obtain for biomedical ontologies. Without relying on large-scale labeled training data or requiring any custom training, our model can be efficiently generalized to new synonyms and performs as well or better than state-of-the-art methods custom built for specific ontologies.

  • Source: Image created by the Authors; Copyright: The Authors; URL:; License: Creative Commons Attribution (CC-BY).

    Use of Telemedicine to Screen Patients in the Emergency Department: Matched Cohort Study Evaluating Efficiency and Patient Safety of Telemedicine


    Background: Early efforts to incorporate telemedicine into Emergency Medicine focused on connecting remote treatment clinics to larger emergency departments (EDs) and providing remote consultation services to EDs with limited resources. Owing to continued ED overcrowding, some EDs have used telemedicine to increase the number of providers during surges of patient visits and offer scheduled “home” face-to-face, on-screen encounters. In this study, we used remote on-screen telemedicine providers in the “screening-in-triage” role. Objective: This study aimed to compare the efficiency and patient safety of in-person screening and telescreening. Methods: This cohort study, matched for days and proximate hours, compared the performance of real-time remote telescreening and in-person screening at a single urban academic ED over 22 weeks in the spring and summer of 2016. The study involved 337 standard screening hours and 315 telescreening hours. The primary outcome measure was patients screened per hour. Additional outcomes were rates of patients who left without being seen, rates of analgesia ordered by the screener, and proportion of patients with chest pain receiving or prescribed a standard set of tests and medications. Results: In-person screeners evaluated 1933 patients over 337 hours (5.7 patients per hour), whereas telescreeners evaluated 1497 patients over 315 hours (4.9 patients per hour; difference=0.8; 95% CI 0.5-1.2). Split analysis revealed that for the final 3 weeks of the evaluation, the patient-per-hour rate differential was neither clinically relevant nor statistically discernable (difference=0.2; 95% CI –0.7 to 1.2). There were fewer patients who left without being seen during in-person screening than during telescreening (2.6% vs 3.8%; difference=–1.2; 95% CI –2.4 to 0.0). However, compared to prior year-, date-, and time-matched data on weekdays from 1 am to 3 am, a period previously void of provider screening, telescreening decreased the rate of patients LWBS from 25.1% to 4.5% (difference=20.7%; 95% CI 10.1-31.2). Analgesia was ordered more frequently by telescreeners than by in-person screeners (51.2% vs 31.6%; difference=19.6%; 95% CI 12.1-27.1). There was no difference in standard care received by patients with chest pain between telescreening and in-person screening (29.4% vs 22.4%; difference=7.0%; 95% CI –3.4 to 17.4). Conclusions: Although the efficiency of telescreening, as measured by the rate of patients seen per hour, was lower early in the study period, telescreening achieved the same level of efficiency as in-person screening by the end of the pilot study. Adding telescreening during 1-3 am on weekdays dramatically decreased the number of patients who left without being seen compared to historic data. Telescreening was an effective and safe way for this ED to expand the hours in which patients were screened by a health care provider in triage.

  • The babelDr interface. Source: Image created by the authors; Copyright: The Authors; URL:; License: Licensed by JMIR.

    A Speech-Enabled Fixed-Phrase Translator for Emergency Settings: Crossover Study


    Background: In the context of the current refugee crisis, emergency services often have to deal with patients who have no language in common with the staff. As interpreters are not always available, especially in emergency settings, medical personnel rely on alternative solutions such as machine translation, which raises reliability and data confidentiality issues, or medical fixed-phrase translators, which sometimes lack usability. A collaboration between Geneva University Hospitals and Geneva University led to the development of BabelDr, a new type of speech-enabled fixed-phrase translator. Similar to other fixed-phrase translators (such as Medibabble or UniversalDoctor), it relies on a predefined list of pretranslated sentences, but instead of searching for sentences in this list, doctors can freely ask questions. Objective: This study aimed to assess if a translation tool, such as BabelDr, can be used by doctors to perform diagnostic interviews under emergency conditions and to reach a correct diagnosis. In addition, we aimed to observe how doctors interact with the system using text and speech and to investigate if speech is a useful modality in this context. Methods: We conducted a crossover study in December 2017 at Geneva University Hospitals with 12 French-speaking doctors (6 doctors working at the outpatient emergency service and 6 general practitioners who also regularly work in this service). They were asked to use the BabelDr tool to diagnose two standardized Arabic-speaking patients (one male and one female). The patients received a priori list of symptoms for the condition they presented with and were instructed to provide a negative or noncommittal answer for all other symptoms during the diagnostic interview. The male patient was standardized for nephritic colic and the female, for cystitis. Doctors used BabelDr as the only means of communication with the patient and were asked to make their diagnosis at the end of the dialogue. The doctors also completed a satisfaction questionnaire. Results: All doctors were able to reach the correct diagnosis based on the information collected using BabelDr. They all agreed that the system helped them reach a conclusion, even if one-half felt constrained by the tool and some considered that they could not ask enough questions to reach a diagnosis. Overall, participants used more speech than text, thus confirming that speech is an important functionality in this type of tool. There was a negative association (P=.02) between the percentage of successful speech interactions (spoken sentences sent for translation) and the number of translated text items, showing that the doctors used more text when they had no success with speech. Conclusions: In emergency settings, when no interpreter is available, speech-enabled fixed-phrase translators can be a good alternative to reliably collect information from the patient.

  • Processing of clinical notes of chronic diseases using NLP. Source: Envato; Copyright: halfpoint; URL:; License: Licensed by the authors.

    Natural Language Processing of Clinical Notes on Chronic Diseases: Systematic Review


    Background: Novel approaches that complement and go beyond evidence-based medicine are required in the domain of chronic diseases, given the growing incidence of such conditions on the worldwide population. A promising avenue is the secondary use of electronic health records (EHRs), where patient data are analyzed to conduct clinical and translational research. Methods based on machine learning to process EHRs are resulting in improved understanding of patient clinical trajectories and chronic disease risk prediction, creating a unique opportunity to derive previously unknown clinical insights. However, a wealth of clinical histories remains locked behind clinical narratives in free-form text. Consequently, unlocking the full potential of EHR data is contingent on the development of natural language processing (NLP) methods to automatically transform clinical text into structured clinical data that can guide clinical decisions and potentially delay or prevent disease onset. Objective: The goal of the research was to provide a comprehensive overview of the development and uptake of NLP methods applied to free-text clinical notes related to chronic diseases, including the investigation of challenges faced by NLP methodologies in understanding clinical narratives. Methods: Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed and searches were conducted in 5 databases using “clinical notes,” “natural language processing,” and “chronic disease” and their variations as keywords to maximize coverage of the articles. Results: Of the 2652 articles considered, 106 met the inclusion criteria. Review of the included papers resulted in identification of 43 chronic diseases, which were then further classified into 10 disease categories using the International Classification of Diseases, 10th Revision. The majority of studies focused on diseases of the circulatory system (n=38) while endocrine and metabolic diseases were fewest (n=14). This was due to the structure of clinical records related to metabolic diseases, which typically contain much more structured data, compared with medical records for diseases of the circulatory system, which focus more on unstructured data and consequently have seen a stronger focus of NLP. The review has shown that there is a significant increase in the use of machine learning methods compared to rule-based approaches; however, deep learning methods remain emergent (n=3). Consequently, the majority of works focus on classification of disease phenotype with only a handful of papers addressing extraction of comorbidities from the free text or integration of clinical notes with structured data. There is a notable use of relatively simple methods, such as shallow classifiers (or combination with rule-based methods), due to the interpretability of predictions, which still represents a significant issue for more complex methods. Finally, scarcity of publicly available data may also have contributed to insufficient development of more advanced methods, such as extraction of word embeddings from clinical notes. Conclusions: Efforts are still required to improve (1) progression of clinical NLP methods from extraction toward understanding; (2) recognition of relations among entities rather than entities in isolation; (3) temporal extraction to understand past, current, and future clinical events; (4) exploitation of alternative sources of clinical knowledge; and (5) availability of large-scale, de-identified clinical corpora.

  • Source: Freepik; Copyright: jeswin; URL:; License: Licensed by JMIR.

    Understanding of and Barriers to Electronic Health Record Patient Portal Access in a Culturally Diverse Pediatric Population


    Background: Electronic health records (EHRs) have become a standard in the health care setting. In an effort to improve health literacy, foster doctor-patient communication, and ease the transition from adolescent to adult care, our institution created a policy that allows patients aged between 13 and 17 years to have EHR portal access. A literature review revealed predictable differences in portal registration among different ethnicities and socioeconomic statuses. Consequently, a cross-sectional survey was developed to investigate barriers to EHR portal access in a sample of culturally diverse adolescents. Objective: The aim of this study was to assess for barriers to EHR portal access in a culturally diverse adolescent population. Methods: A 42-item anonymous survey was completed by 97 adolescents aged between 13 and 18 years, attending general pediatrics clinics. The results were analyzed using descriptive statistics and t tests. Results: The average participant age was 15.5 (SD 1.5) years with 60% (58/97) male and 40% (39/97) female. Participants were 44% (43/97) black, 41% (40/97) Hispanic, 9% (9/97) Caucasian, 3% (3/97) Asian, and 2% (2/97) others. There were statistically significant differences in perceptions of confidentiality in age (13 to 15 years vs 16 to 18 years; P=.001) and insurance status (government vs private; P=.012) but not in gender, ethnicity, or parental education level. Younger adolescents with governmental insurance were more confident in the level of confidentiality with their physician. A total of 94% of participants had heard of the term EHR, but only 55% were familiar with its function. Furthermore, 77% of patients primarily accessed the internet through phones, and 50% of participants knew that patients aged under 18 years could obtain care for mental health, substance abuse, sexual health, and pregnancy. Conclusions: This research has identified gaps in EHR technology with regard to the pediatric patient population. The results of our survey show that adolescents may have misconceptions regarding the doctor-patient relationship, their ability to obtain care, and the modalities present in an EHR. As technology progresses, it is essential to have a deeper understanding of adolescents’ perceptions of confidentiality, technology, and available resources to design an EHR system that encourages patient education and communication while limiting barriers to care.

  • Source: Adobe Stock; Copyright: Maxim Pavlov; URL:; License: Licensed by the authors.

    Natural Language Processing for the Identification of Silent Brain Infarcts From Neuroimaging Reports


    Background: Silent brain infarction (SBI) is defined as the presence of 1 or more brain lesions, presumed to be because of vascular occlusion, found by neuroimaging (magnetic resonance imaging or computed tomography) in patients without clinical manifestations of stroke. It is more common than stroke and can be detected in 20% of healthy elderly people. Early detection of SBI may mitigate the risk of stroke by offering preventative treatment plans. Natural language processing (NLP) techniques offer an opportunity to systematically identify SBI cases from electronic health records (EHRs) by extracting, normalizing, and classifying SBI-related incidental findings interpreted by radiologists from neuroimaging reports. Objective: This study aimed to develop NLP systems to determine individuals with incidentally discovered SBIs from neuroimaging reports at 2 sites: Mayo Clinic and Tufts Medical Center. Methods: Both rule-based and machine learning approaches were adopted in developing the NLP system. The rule-based system was implemented using the open source NLP pipeline MedTagger, developed by Mayo Clinic. Features for rule-based systems, including significant words and patterns related to SBI, were generated using pointwise mutual information. The machine learning models adopted convolutional neural network (CNN), random forest, support vector machine, and logistic regression. The performance of the NLP algorithm was compared with a manually created gold standard. The gold standard dataset includes 1000 radiology reports randomly retrieved from the 2 study sites (Mayo and Tufts) corresponding to patients with no prior or current diagnosis of stroke or dementia. 400 out of the 1000 reports were randomly sampled and double read to determine interannotator agreements. The gold standard dataset was equally split to 3 subsets for training, developing, and testing. Results: Among the 400 reports selected to determine interannotator agreement, 5 reports were removed due to invalid scan types. The interannotator agreements across Mayo and Tufts neuroimaging reports were 0.87 and 0.91, respectively. The rule-based system yielded the best performance of predicting SBI with an accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 0.991, 0.925, 1.000, 1.000, and 0.990, respectively. The CNN achieved the best score on predicting white matter disease (WMD) with an accuracy, sensitivity, specificity, PPV, and NPV of 0.994, 0.994, 0.994, 0.994, and 0.994, respectively. Conclusions: We adopted a standardized data abstraction and modeling process to developed NLP techniques (rule-based and machine learning) to detect incidental SBIs and WMDs from annotated neuroimaging reports. Validation statistics suggested a high feasibility of detecting SBIs and WMDs from EHRs using NLP.

  • Source: Freepik; Copyright: katemangostar; URL:; License: Licensed by JMIR.

    The Use of Artificially Intelligent Self-Diagnosing Digital Platforms by the General Public: Scoping Review


    Background: Self-diagnosis is the process of diagnosing or identifying a medical condition in oneself. Artificially intelligent digital platforms for self-diagnosis are becoming widely available and are used by the general public; however, little is known about the body of knowledge surrounding this technology. Objective: The objectives of this scoping review were to (1) systematically map the extent and nature of the literature and topic areas pertaining to digital platforms that use computerized algorithms to provide users with a list of potential diagnoses and (2) identify key knowledge gaps. Methods: The following databases were searched: PubMed (Medline), Scopus, Association for Computing Machinery Digital Library, Institute of Electrical and Electronics Engineers, Google Scholar, Open Grey, and ProQuest Dissertations and Theses. The search strategy was developed and refined with the assistance of a librarian and consisted of 3 main concepts: (1) self-diagnosis; (2) digital platforms; and (3) public or patients. The search generated 2536 articles from which 217 were duplicates. Following the Tricco et al 2018 checklist, 2 researchers screened the titles and abstracts (n=2316) and full texts (n=104), independently. A total of 19 articles were included for review, and data were retrieved following a data-charting form that was pretested by the research team. Results: The included articles were mainly conducted in the United States (n=10) or the United Kingdom (n=4). Among the articles, topic areas included accuracy or correspondence with a doctor’s diagnosis (n=6), commentaries (n=2), regulation (n=3), sociological (n=2), user experience (n=2), theoretical (n=1), privacy and security (n=1), ethical (n=1), and design (n=1). Individuals who do not have access to health care and perceive to have a stigmatizing condition are more likely to use this technology. The accuracy of this technology varied substantially based on the disease examined and platform used. Women and those with higher education were more likely to choose the right diagnosis out of the potential list of diagnoses. Regulation of this technology is lacking in most parts of the world; however, they are currently under development. Conclusions: There are prominent research gaps in the literature surrounding the use of artificially intelligent self-diagnosing digital platforms. Given the variety of digital platforms and the wide array of diseases they cover, measuring accuracy is cumbersome. More research is needed to understand the user experience and inform regulations.

  • Source: Phanie; Copyright: Alamy Stock Photo; URL:; License: Licensed by the authors.

    Clinical Requirements of Future Patient Monitoring in the Intensive Care Unit: Qualitative Study


    Background: In the intensive care unit (ICU), continuous patient monitoring is essential to detect critical changes in patients’ health statuses and to guide therapy. The implementation of digital health technologies for patient monitoring may further improve patient safety. However, most monitoring devices today are still based on technologies from the 1970s. Objective: The aim of this study was to evaluate statements by ICU staff on the current patient monitoring systems and their expectations for future technological developments in order to investigate clinical requirements and barriers to the implementation of future patient monitoring. Methods: This prospective study was conducted at three intensive care units of a German university hospital. Guideline-based interviews with ICU staff—5 physicians, 6 nurses, and 4 respiratory therapists—were recorded, transcribed, and analyzed using the grounded theory approach. Results: Evaluating the current monitoring system, ICU staff put high emphasis on usability factors such as intuitiveness and visualization. Trend analysis was rarely used; inadequate alarm management as well as the entanglement of monitoring cables were rated as potential patient safety issues. For a future system, the importance of high usability was again emphasized; wireless, noninvasive, and interoperable monitoring sensors were desired; mobile phones for remote patient monitoring and alarm management optimization were needed; and clinical decision support systems based on artificial intelligence were considered useful. Among perceived barriers to implementation of novel technology were lack of trust, fear of losing clinical skills, fear of increasing workload, and lack of awareness of available digital technologies. Conclusions: This qualitative study on patient monitoring involves core statements from ICU staff. To promote a rapid and sustainable implementation of digital health solutions in the ICU, all health care stakeholders must focus more on user-derived findings. Results on alarm management or mobile devices may be used to prepare ICU staff to use novel technology, to reduce alarm fatigue, to improve medical device usability, and to advance interoperability standards in intensive care medicine. For digital transformation in health care, increasing the trust and awareness of ICU staff in digital health technology may be an essential prerequisite. Trial Registration: NCT03514173; (Archived by WebCite at

  • Source: Flickr; Copyright: UC Davis College of Engineering; URL:; License: Creative Commons Attribution (CC-BY).

    Privacy-Preserving Analysis of Distributed Biomedical Data: Designing Efficient and Secure Multiparty Computations Using Distributed Statistical Learning Theory


    Background: Biomedical research often requires large cohorts and necessitates the sharing of biomedical data with researchers around the world, which raises many privacy, ethical, and legal concerns. In the face of these concerns, privacy experts are trying to explore approaches to analyzing the distributed data while protecting its privacy. Many of these approaches are based on secure multiparty computations (SMCs). SMC is an attractive approach allowing multiple parties to collectively carry out calculations on their datasets without having to reveal their own raw data; however, it incurs heavy computation time and requires extensive communication between the involved parties. Objective: This study aimed to develop usable and efficient SMC applications that meet the needs of the potential end-users and to raise general awareness about SMC as a tool that supports data sharing. Methods: We have introduced distributed statistical computing (DSC) into the design of secure multiparty protocols, which allows us to conduct computations on each of the parties’ sites independently and then combine these computations to form 1 estimator for the collective dataset, thus limiting communication to the final step and reducing complexity. The effectiveness of our privacy-preserving model is demonstrated through a linear regression application. Results: Our secure linear regression algorithm was tested for accuracy and performance using real and synthetic datasets. The results showed no loss of accuracy (over nonsecure regression) and very good performance (20 min for 100 million records). Conclusions: We used DSC to securely calculate a linear regression model over multiple datasets. Our experiments showed very good performance (in terms of the number of records it can handle). We plan to extend our method to other estimators such as logistic regression.

Citing this Article

Right click to copy or hit: ctrl+c (cmd+c on mac)

Latest Submissions Open for Peer-Review:

View All Open Peer Review Articles
  • The Influence of Scribes on Patient-Physician Communication Within Primary Care Encounters

    Date Submitted: May 23, 2019

    Open Peer Review Period: May 24, 2019 - May 31, 2019

    Background: With the increased adoption of EHR systems, documentation-related burdens have been increasing for healthcare providers. Recent estimates indicate that primary care providers spend about o...

    Background: With the increased adoption of EHR systems, documentation-related burdens have been increasing for healthcare providers. Recent estimates indicate that primary care providers spend about one-half of their workday interacting with the EHR, of which about half is focused on clerical tasks. To reduce documentation burdens associated with the EHR, healthcare systems and physician practices are increasingly implementing medical scribes to assist providers with real-time documentation. Despite the promise of scribes, few studies have investigated their effect on the clinical encounters, particularly in regards to patient-provider communication. Objective: The purpose of this study was to understand how patient-physician communication in primary care clinical encounters was affected with and without the use of scribes. Methods: We employed a convergent mixed methods design among a sample of three physician-scribe pairs, and 34 patient participants randomly assigned to have a scribe present or not within a clinical encounter. We conducted patient surveys focused on perceptions of patient-provider communication and satisfaction with the encounter, video recorded clinical encounters, and conducted physician interviews about their experiences with scribes. Results: Overall, survey results revealed that patients across both arms reported very high satisfaction regarding communication with their physician, their physician’s use of the EHR, and their satisfaction with their care, with very little variability. Video recording analysis supported patient survey data by demonstrating physicians in scribed and non-scribed encounters both had high measures of communication. Furthermore, video recordings revealed that the presence of scribes had very little effect on the clinical encounter. Conclusions: From a patient perspective, scribes are an acceptable addition to clinical encounters. Although they do not have much impact on patient perceptions of satisfaction, and their impact on the clinical encounter itself was minimal, their potential to reduce documentation-related burden on physicians is important. Physicians noted important issues related to scribes, including important considerations for implementing scribe programs, the role of scribes in patient interactions, how physicians work with scribes, characteristics of good scribes, and the role of scribes in physician workflow.

  • Deep Learning Based Tobacco Products Classification

    Date Submitted: May 19, 2019

    Open Peer Review Period: May 22, 2019 - Jul 17, 2019

    Background: Various images and videos are uploaded every day or even every second on Instagram. These publicly available images are easily accessible as a result of uncontrolled Internet use by young...

    Background: Various images and videos are uploaded every day or even every second on Instagram. These publicly available images are easily accessible as a result of uncontrolled Internet use by young people and children. Shared images include tobacco products and can be encouraging for young people and children when they are accessible. Objective: In this study, it is aimed to detect tobacco and tobacco products with various Convolutional Neural Networks (CNNs) and to limit the access of young users to these detected tobacco products over the Internet. Methods: A total of 1607 public images were collected from Instagram, and feature vectors were extracted with various CNNs, which proved to be successful in the competitions and CNN was determined to be proper for detect tobacco products. Results: MobileNet gave the highest results 99.1% as weighted average. The feature vector of the input images are extracted with CNNs and classified with the latest fully connected layer. Conclusions: The classification of the tobacco products of 4 different classes was studied by using the networks and the classification performance rate was obtained as 100% for 322 test images via MobileNet. In this way, the content that is encouraging for children can be censored or filtered with a high accuracy rate and a secure Internet environment can be provided.

  • From random Brownian motion of particles to high automation laboratory: a brief history of correlation time

    Date Submitted: May 10, 2019

    Open Peer Review Period: May 15, 2019 - Jul 10, 2019

    Background: Laboratory automation is the actual frontier for the increase of productivity and reduction of samples turnaround time (TAT), in turn used as a key indicator of laboratory performance. How...

    Background: Laboratory automation is the actual frontier for the increase of productivity and reduction of samples turnaround time (TAT), in turn used as a key indicator of laboratory performance. However, due to the statistical distribution of TAT values, classical parameters (mean, standard deviation, percentiles) fail to describe each single sample processing “story”. Objective: The driving idea of the present work is to assimilate the samples flow in an automation laboratory to the movement of molecules in solution by means of Dynamic Light Scattering Correlation Function analysis expansion Methods: TAT values from 10000 samples were used to build a correlation function. Through a time course, each sample perfectly correlates with its initial status (no results available) until its specific TAT value is reached and assumes a value of 1; after the TAT is reached (produced results) it no more correlates and its status value becomes 0. The generated correlation function is simply the normalized progressive timing sum of all analyzed samples status conditions at each specific time. Results: By correlation function analysis, several parameters to describe the general performance of the system as well as each individual sample status are derived and applied to monitor the efficiency of the automation chain in real time mode Conclusions: Our original approach to laboratory automation leads to the possibility of determining measurable criteria able to describe the entire system capacity to buffer and reduce problems both on the full performance or on spot samples, consequently developing a new tool to evaluate different or improved performing systems. Clinical Trial: none

  • Utilizing Twitter Data Analysis and Deep Learning to Identify Drug Use

    Date Submitted: May 10, 2019

    Open Peer Review Period: May 13, 2019 - Jul 8, 2019

    Background: The collection and examination of social media has become a useful mechanism for studying the mental activity and behavior tendencies of users. Objective: Through the analysis of a collect...

    Background: The collection and examination of social media has become a useful mechanism for studying the mental activity and behavior tendencies of users. Objective: Through the analysis of a collected set of Twitter data, a model will be developed for predicting positively referenced, drug-related tweets. From this, trends and correlations can be determined. Methods: Twitter social media tweets and attribute data were collected and processed using topic pertaining keywords, such as drug slang and use-conditions (methods of drug consumption). Potential candidates were preprocessed resulting in a dataset 3,696,150 rows. The predictive classification power of multiple methods was compared including regression, decision trees, and CNN-based classifiers. For the latter, a deep learning approach was implemented to screen and analyze the semantic meaning of the tweets. Results: The logistic regression and decision tree models utilized 12,142 data points for training and 1041 data points for testing. The results calculated from the logistic regression models respectively displayed an accuracy of 54.56% and 57.44%, and an AUC of 0.58. While an improvement, the decision tree concluded with an accuracy of 63.40% and an AUC of 0.68. All these values implied a low predictive capability with little to no discrimination. Conversely, the CNN-based classifiers presented a heavy improvement, between the two models tested. The first was trained with 2,661 manually labeled samples, while the other included synthetically generated tweets culminating in 12,142 samples. The accuracy scores were 76.35% and 82.31%, with an AUC of 0.90 and 0.91. Using association rule mining in conjunction with the CNN-based classifier showed a high likelihood for keywords such as “smoke”, “cocaine”, and “marijuana” triggering a drug-positive classification. Conclusions: Predictive analysis without a CNN is limited and possibly fruitless. Attribute-based models presented little predictive capability and were not suitable for analyzing this type of data. The semantic meaning of the tweets needed to be utilized, giving the CNN-based classifier an advantage over other solutions. Additionally, commonly mentioned drugs had a level of correspondence with frequently used illicit substances, proving the practical usefulness of this system. Lastly, the synthetically generated set provided increased scores, improving the predictive capability. Clinical Trial: None

  • Developing a Reproducible Microbiome Data Analysis Pipeline Using the Amazon Web Services Cloud for a Cancer Research Group

    Date Submitted: May 9, 2019

    Open Peer Review Period: May 13, 2019 - Jul 8, 2019

    Background: Cloud computing for microbiome data sets can significantly increase the working efficiencies and expedite the translation of research findings into clinical practice. Amazon Web Services (...

    Background: Cloud computing for microbiome data sets can significantly increase the working efficiencies and expedite the translation of research findings into clinical practice. Amazon Web Services (AWS) cloud provides an invaluable option for microbiome data storage, computation, and analysis. Objective: The purpose of this study was to develop a microbiome data analysis pipeline by using AWS cloud and conduct a proof-of-concept test for microbiome data storage, processing, and analysis. Methods: A multidisciplinary team was formed to develop and test a reproducible microbiome data analysis pipeline with multiple AWS cloud services that can be used for storage, computation, and data analysis. The microbiome data analysis pipeline developed in AWS was tested by using two data sets: 19 vaginal microbiome samples and 50 gut microbiome samples. Results: Using AWS features, we developed a microbiome data analysis pipeline that included Amazon Simple Storage Service (S3) for microbiome sequence storage, Linux Elastic Compute Cloud (EC2) instances (i.e., servers) for data computation and analysis, and security keys to create and manage the use of encryption for the pipeline. Bioinformatics and statistical tools (i.e., QIIME 2 and RStudio) were installed within Linux EC2 instances to run microbiome statistical analysis. The microbiome data analysis pipeline was performed through command-line interfaces within the Linux operating system or in Mac OS™ systems. Using this new pipeline, we were able to successfully process and analyze 50 gut microbiome samples within 4 hours at a very low cost. Gut microbiome findings regarding diversity, taxonomy, and abundance analyses were easily shared within our research team. Conclusions: Building a microbiome data analysis pipeline with AWS cloud is feasible. This pipeline is highly reliable, computationally powerful, and cost effective. Our AWS-based microbiome analysis pipeline (MAP-AWS) provides an efficient tool to conduct microbiome data analysis. Clinical Trial: NA

  • Issues Impacting Continuous Pulse Oximetry Monitoring and Wireless Clinical Notification System After Surgery

    Date Submitted: May 6, 2019

    Open Peer Review Period: May 9, 2019 - Jul 4, 2019

    Background: Background: Research has shown that introducing eHealth patient monitoring interventions can improve healthcare efficiency and clinical outcomes. VIGILANCE (The VItal siGns monItoring with...

    Background: Background: Research has shown that introducing eHealth patient monitoring interventions can improve healthcare efficiency and clinical outcomes. VIGILANCE (The VItal siGns monItoring with continuous puLse oximetry And wireless cliNiCal notification aftEr surgery) was a randomized controlled trial (n=2049) designed to assess the impact of continuous vital sign monitoring with alerts to nursing staff on the incidence of respiratory resuscitations with naloxone, code blues, and intensive care unit transfers in a cohort of post-surgical patients in a ward setting. This report identifies and evaluates key issues and challenges associated with introducing wireless monitoring systems into complex hospital infrastructure during the VIGILANCE eHealth intervention implementation. Potential solutions and suggestions for future implementation research are presented. Objective: Objectives: (1) to identify issues related to deployment of the eHealth intervention system of the VIGILANCE study, and (2) to evaluate the influence of these issues on intervention adoption. Methods: Methods: During the VIGILANCE study, issues affecting the implementation of the eHealth intervention were documented on case report forms, alarm event forms, and a nursing user feedback questionnaire. These data were collated by the research and nursing personnel and submitted to the research coordinator. In this evaluation report, the clinical adoption framework was used as a guide to organize the identified issues and evaluate their impact. Results: Results: Using the clinical adoption framework, we identified issues within the framework dimensions of ‘people’, ‘organization’ and ‘implementation’ at the meso level, as well as standards and funding issues at the macro level. Key issues included: nursing workflow changes, patient withdrawal, wireless network connectivity, false alarms, monitor malfunction, probe issues, and wireless network standards. At the micro level, these issues affected the quality of the service in terms of support provided, the quality of the information yielded by the monitors, and the functionality, reliability and performance of the monitoring system. As a result, these issues impacted ‘access’ through decreased ability of nurses to make complete use of the monitors; ‘care quality’ of the trial intervention through decreased effectiveness; and ‘productivity’ through interference in the coordination of care, and thus decreased clinical adoption of the monitoring system. Conclusions: Conclusion: Patient monitoring with eHealth technology in surgical wards has the potential to improve patient outcomes. However, proper planning that includes engagement of front-line nurses, installation of appropriate wireless network infrastructure, and use of comfortable cableless devices are required to maximize the potential of eHealth monitoring.