Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 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; Impact Factor: 2.58) (Editor-in-chief: Christian Lovis MD MPH FACMI) is a PubMed/SCIE-indexed journal that focuses on clinical informatics, big data in health and health care, decision support for health professionals, electronic health records, ehealth infrastructures and implementation. In June 2020, the journal received an impact factor of 2.58. 

Published by JMIR Publications, JMIR Medical Informatics has a focus on applied, translational research, with a broad readership including clinicians, CIOs, engineers, industry and health informatics professionals.

JMIR Medical Informatics adheres to rigorous quality standards, involving a rapid and thorough peer-review process, professional copyediting, professional production of PDF, XHTML, and XML proofs (ready for deposit in PubMed Central/PubMed).


Recent Articles:

  • Source: freepik; Copyright: freepik; URL:; License: Licensed by JMIR.

    Decompensation in Critical Care: Early Prediction of Acute Heart Failure Onset


    Background: Heart failure is a leading cause of mortality and morbidity worldwide. Acute heart failure, broadly defined as rapid onset of new or worsening signs and symptoms of heart failure, often requires hospitalization and admission to the intensive care unit (ICU). This acute condition is highly heterogeneous and less well-understood as compared to chronic heart failure. The ICU, through detailed and continuously monitored patient data, provides an opportunity to retrospectively analyze decompensation and heart failure to evaluate physiological states and patient outcomes. Objective: The goal of this study is to examine the prevalence of cardiovascular risk factors among those admitted to ICUs and to evaluate combinations of clinical features that are predictive of decompensation events, such as the onset of acute heart failure, using machine learning techniques. To accomplish this objective, we leveraged tele-ICU data from over 200 hospitals across the United States. Methods: We evaluated the feasibility of predicting decompensation soon after ICU admission for 26,534 patients admitted without a history of heart failure with specific heart failure risk factors (ie, coronary artery disease, hypertension, and myocardial infarction) and 96,350 patients admitted without risk factors using remotely monitored laboratory, vital signs, and discrete physiological measurements. Multivariate logistic regression and random forest models were applied to predict decompensation and highlight important features from combinations of model inputs from dissimilar data. Results: The most prevalent risk factor in our data set was hypertension, although most patients diagnosed with heart failure were admitted to the ICU without a risk factor. The highest heart failure prediction accuracy was 0.951, and the highest area under the receiver operating characteristic curve was 0.9503 with random forest and combined vital signs, laboratory values, and discrete physiological measurements. Random forest feature importance also highlighted combinations of several discrete physiological features and laboratory measures as most indicative of decompensation. Timeline analysis of aggregate vital signs revealed a point of diminishing returns where additional vital signs data did not continue to improve results. Conclusions: Heart failure risk factors are common in tele-ICU data, although most patients that are diagnosed with heart failure later in an ICU stay presented without risk factors making a prediction of decompensation critical. Decompensation was predicted with reasonable accuracy using tele-ICU data, and optimal data extraction for time series vital signs data was identified near a 200-minute window size. Overall, results suggest combinations of laboratory measurements and vital signs are viable for early and continuous prediction of patient decompensation.

  • Looking for evidence-based treatments for a well-known disease using BMJ Best Practice. Source: BMJ Publishing Group Limited; Copyright: BMJ Publishing Group Limited; URL:; License: Licensed by the authors.

    Semantic Deep Learning: Prior Knowledge and a Type of Four-Term Embedding Analogy to Acquire Treatments for Well-Known Diseases


    Background: How to treat a disease remains to be the most common type of clinical question. Obtaining evidence-based answers from biomedical literature is difficult. Analogical reasoning with embeddings from deep learning (embedding analogies) may extract such biomedical facts, although the state-of-the-art focuses on pair-based proportional (pairwise) analogies such as man:woman::king:queen (“queen = −man +king +woman”). Objective: This study aimed to systematically extract disease treatment statements with a Semantic Deep Learning (SemDeep) approach underpinned by prior knowledge and another type of 4-term analogy (other than pairwise). Methods: As preliminaries, we investigated Continuous Bag-of-Words (CBOW) embedding analogies in a common-English corpus with five lines of text and observed a type of 4-term analogy (not pairwise) applying the 3CosAdd formula and relating the semantic fields person and death: “dagger = −Romeo +die +died” (search query: −Romeo +die +died). Our SemDeep approach worked with pre-existing items of knowledge (what is known) to make inferences sanctioned by a 4-term analogy (search query −x +z1 +z2) from CBOW and Skip-gram embeddings created with a PubMed systematic reviews subset (PMSB dataset). Stage1: Knowledge acquisition. Obtaining a set of terms, candidate y, from embeddings using vector arithmetic. Some n-gram pairs from the cosine and validated with evidence (prior knowledge) are the input for the 3cosAdd, seeking a type of 4-term analogy relating the semantic fields disease and treatment. Stage 2: Knowledge organization. Identification of candidates sanctioned by the analogy belonging to the semantic field treatment and mapping these candidates to unified medical language system Metathesaurus concepts with MetaMap. A concept pair is a brief disease treatment statement (biomedical fact). Stage 3: Knowledge validation. An evidence-based evaluation followed by human validation of biomedical facts potentially useful for clinicians. Results: We obtained 5352 n-gram pairs from 446 search queries by applying the 3CosAdd. The microaveraging performance of MetaMap for candidate y belonging to the semantic field treatment was F-measure=80.00% (precision=77.00%, recall=83.25%). We developed an empirical heuristic with some predictive power for clinical winners, that is, search queries bringing candidate y with evidence of a therapeutic intent for target disease x. The search queries -asthma +inhaled_corticosteroids +inhaled_corticosteroid and -epilepsy +valproate +antiepileptic_drug were clinical winners, finding eight evidence-based beneficial treatments. Conclusions: Extracting treatments with therapeutic intent by analogical reasoning from embeddings (423K n-grams from the PMSB dataset) is an ambitious goal. Our SemDeep approach is knowledge-based, underpinned by embedding analogies that exploit prior knowledge. Biomedical facts from embedding analogies (4-term type, not pairwise) are potentially useful for clinicians. The heuristic offers a practical way to discover beneficial treatments for well-known diseases. Learning from deep learning models does not require a massive amount of data. Embedding analogies are not limited to pairwise analogies; hence, analogical reasoning with embeddings is underexploited.

  • Maier Institute Dementia Research Dashboard. Source: The Authors / Placeit; Copyright: The Authors / Placeit; URL:; License: Licensed by JMIR.

    Analysis of Benzodiazepine Prescription Practices in Elderly Appalachians with Dementia via the Appalachian Informatics Platform: Longitudinal Study


    Background: Caring for the growing dementia population with complex health care needs in West Virginia has been challenging due to its large, sizably rural-dwelling geriatric population and limited resource availability. Objective: This paper aims to illustrate the application of an informatics platform to drive dementia research and quality care through a preliminary study of benzodiazepine (BZD) prescription patterns and its effects on health care use by geriatric patients. Methods: The Maier Institute Data Mart, which contains clinical and billing data on patients aged 65 years and older (N=98,970) seen within our clinics and hospital, was created. Relevant variables were analyzed to identify BZD prescription patterns and calculate related charges and emergency department (ED) use. Results: Nearly one-third (4346/13,910, 31.24%) of patients with dementia received at least one BZD prescription, 20% more than those without dementia. More women than men received at least one BZD prescription. On average, patients with dementia and at least one BZD prescription sustained higher charges and visited the ED more often than those without one. Conclusions: The Appalachian Informatics Platform has the potential to enhance dementia care and research through a deeper understanding of dementia, data enrichment, risk identification, and care gap analysis.

  • Source: Pexels; Copyright: Pixabay; URL:; License: Public Domain (CC0).

    Assessment of the Robustness of Convolutional Neural Networks in Labeling Noise by Using Chest X-Ray Images From Multiple Centers


    Background: Computer-aided diagnosis on chest x-ray images using deep learning is a widely studied modality in medicine. Many studies are based on public datasets, such as the National Institutes of Health (NIH) dataset and the Stanford CheXpert dataset. However, these datasets are preprocessed by classical natural language processing, which may cause a certain extent of label errors. Objective: This study aimed to investigate the robustness of deep convolutional neural networks (CNNs) for binary classification of posteroanterior chest x-ray through random incorrect labeling. Methods: We trained and validated the CNN architecture with different noise levels of labels in 3 datasets, namely, Asan Medical Center-Seoul National University Bundang Hospital (AMC-SNUBH), NIH, and CheXpert, and tested the models with each test set. Diseases of each chest x-ray in our dataset were confirmed by a thoracic radiologist using computed tomography (CT). Receiver operating characteristic (ROC) and area under the curve (AUC) were evaluated in each test. Randomly chosen chest x-rays of public datasets were evaluated by 3 physicians and 1 thoracic radiologist. Results: In comparison with the public datasets of NIH and CheXpert, where AUCs did not significantly drop to 16%, the AUC of the AMC-SNUBH dataset significantly decreased from 2% label noise. Evaluation of the public datasets by 3 physicians and 1 thoracic radiologist showed an accuracy of 65%-80%. Conclusions: The deep learning–based computer-aided diagnosis model is sensitive to label noise, and computer-aided diagnosis with inaccurate labels is not credible. Furthermore, open datasets such as NIH and CheXpert need to be distilled before being used for deep learning–based computer-aided diagnosis.

  • Monitoring patient vital signs on tablet PC. Source: 123RF; Copyright: scanrail; URL:; License: Creative Commons Attribution + Noncommercial + NoDerivatives (CC-BY-NC-ND).

    Prediction of Cardiac Arrest in the Emergency Department Based on Machine Learning and Sequential Characteristics: Model Development and Retrospective...


    Background: The development and application of clinical prediction models using machine learning in clinical decision support systems is attracting increasing attention. Objective: The aims of this study were to develop a prediction model for cardiac arrest in the emergency department (ED) using machine learning and sequential characteristics and to validate its clinical usefulness. Methods: This retrospective study was conducted with ED patients at a tertiary academic hospital who suffered cardiac arrest. To resolve the class imbalance problem, sampling was performed using propensity score matching. The data set was chronologically allocated to a development cohort (years 2013 to 2016) and a validation cohort (year 2017). We trained three machine learning algorithms with repeated 10-fold cross-validation. Results: The main performance parameters were the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC). The random forest algorithm (AUROC 0.97; AUPRC 0.86) outperformed the recurrent neural network (AUROC 0.95; AUPRC 0.82) and the logistic regression algorithm (AUROC 0.92; AUPRC=0.72). The performance of the model was maintained over time, with the AUROC remaining at least 80% across the monitored time points during the 24 hours before event occurrence. Conclusions: We developed a prediction model of cardiac arrest in the ED using machine learning and sequential characteristics. The model was validated for clinical usefulness by chronological visualization focused on clinical usability.

  • Source: freepik; Copyright: pressfoto; URL:; License: Licensed by JMIR.

    Improving Diagnostic Classification of Stillbirths and Neonatal Deaths Using ICD-PM (International Classification of Diseases for Perinatal Mortality) Codes:...


    Background: Stillbirths and neonatal deaths have long been imperfectly classified and recorded worldwide. In Hong Kong, the current code system is deficient (>90% cases with unknown causes) in providing the diagnoses of perinatal mortality cases. Objective: The objective of this study was to apply the International Classification of Diseases for Perinatal Mortality (ICD-PM) system to existing perinatal death data. Further, the aim was to assess whether there was any change in the classifications of perinatal deaths compared with the existing classification system and identify any areas in which future interventions can be made. Methods: We applied the ICD-PM (with International Statistical Classification of Diseases and Related Health Problems, 10th Revision) code system to existing perinatal death data in Kwong Wah Hospital, Hong Kong, to improve diagnostic classification. The study included stillbirths (after 24 weeks gestation) and neonatal deaths (from birth to 28 days). The retrospective data (5 years) from May 1, 2012, to April 30, 2017, were recoded by the principal investigator (HML) applying the ICD-PM, then validated by an overseas expert (EA) after she reviewed the detailed case summaries. The prospective application of ICD-PM from May 1, 2017, to April 30, 2019, was performed during the monthly multidisciplinary perinatal meetings and then also validated by EA for agreement. Results: We analyzed the data of 34,920 deliveries, and 119 cases were included for analysis (92 stillbirths and 27 neonatal deaths). The overall agreement with EA of our codes using the ICD-PM was 93.2% (111/119); 92% (78/85) for the 5 years of retrospective codes and 97% (33/34) for the 2 years of prospective codes (P=.44). After the application of the ICD-PM, the overall proportion of unknown causes of perinatal mortality dropped from 34.5% (41/119) to 10.1% (12/119) of cases (P<.001). Conclusions: Using the ICD-PM would lead to a better classification of perinatal deaths, reduce the proportion of unknown diagnoses, and clearly link the maternal conditions with these perinatal deaths.

  • Source: Pexels; Copyright: CDC: Center for Disease Control; URL:; License: Licensed by JMIR.

    A Predictive Model Based on Machine Learning for the Early Detection of Late-Onset Neonatal Sepsis: Development and Observational Study


    Background: Neonatal sepsis is associated with most cases of mortalities and morbidities in the neonatal intensive care unit (NICU). Many studies have developed prediction models for the early diagnosis of bloodstream infections in newborns, but there are limitations to data collection and management because these models are based on high-resolution waveform data. Objective: The aim of this study was to examine the feasibility of a prediction model by using noninvasive vital sign data and machine learning technology. Methods: We used electronic medical record data in intensive care units published in the Medical Information Mart for Intensive Care III clinical database. The late-onset neonatal sepsis (LONS) prediction algorithm using our proposed forward feature selection technique was based on NICU inpatient data and was designed to detect clinical sepsis 48 hours before occurrence. The performance of this prediction model was evaluated using various feature selection algorithms and machine learning models. Results: The performance of the LONS prediction model was found to be comparable to that of the prediction models that use invasive data such as high-resolution vital sign data, blood gas estimations, blood cell counts, and pH levels. The area under the receiver operating characteristic curve of the 48-hour prediction model was 0.861 and that of the onset detection model was 0.868. The main features that could be vital candidate markers for clinical neonatal sepsis were blood pressure, oxygen saturation, and body temperature. Feature generation using kurtosis and skewness of the features showed the highest performance. Conclusions: The findings of our study confirmed that the LONS prediction model based on machine learning can be developed using vital sign data that are regularly measured in clinical settings. Future studies should conduct external validation by using different types of data sets and actual clinical verification of the developed model.

  • Source: The Authors/Placeit; Copyright: The Authors/Placeit; URL:; License: Licensed by JMIR.

    Document-Level Biomedical Relation Extraction Using Graph Convolutional Network and Multihead Attention: Algorithm Development and Validation


    Background: Automatically extracting relations between chemicals and diseases plays an important role in biomedical text mining. Chemical-disease relation (CDR) extraction aims at extracting complex semantic relationships between entities in documents, which contain intrasentence and intersentence relations. Most previous methods did not consider dependency syntactic information across the sentences, which are very valuable for the relations extraction task, in particular, for extracting the intersentence relations accurately. Objective: In this paper, we propose a novel end-to-end neural network based on the graph convolutional network (GCN) and multihead attention, which makes use of the dependency syntactic information across the sentences to improve CDR extraction task. Methods: To improve the performance of intersentence relation extraction, we constructed a document-level dependency graph to capture the dependency syntactic information across sentences. GCN is applied to capture the feature representation of the document-level dependency graph. The multihead attention mechanism is employed to learn the relatively important context features from different semantic subspaces. To enhance the input representation, the deep context representation is used in our model instead of traditional word embedding. Results: We evaluate our method on CDR corpus. The experimental results show that our method achieves an F-measure of 63.5%, which is superior to other state-of-the-art methods. In the intrasentence level, our method achieves a precision, recall, and F-measure of 59.1%, 81.5%, and 68.5%, respectively. In the intersentence level, our method achieves a precision, recall, and F-measure of 47.8%, 52.2%, and 49.9%, respectively. Conclusions: The GCN model can effectively exploit the across sentence dependency information to improve the performance of intersentence CDR extraction. Both the deep context representation and multihead attention are helpful in the CDR extraction task.

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

    Identifying and Predicting Intentional Self-Harm in Electronic Health Record Clinical Notes: Deep Learning Approach


    Background: Suicide is an important public health concern in the United States and around the world. There has been significant work examining machine learning approaches to identify and predict intentional self-harm and suicide using existing data sets. With recent advances in computing, deep learning applications in health care are gaining momentum. Objective: This study aimed to leverage the information in clinical notes using deep neural networks (DNNs) to (1) improve the identification of patients treated for intentional self-harm and (2) predict future self-harm events. Methods: We extracted clinical text notes from electronic health records (EHRs) of 835 patients with International Classification of Diseases (ICD) codes for intentional self-harm and 1670 matched controls who never had any intentional self-harm ICD codes. The data were divided into training and holdout test sets. We tested a number of algorithms on clinical notes associated with the intentional self-harm codes using the training set, including several traditional bag-of-words–based models and 2 DNN models: a convolutional neural network (CNN) and a long short-term memory model. We also evaluated the predictive performance of the DNNs on a subset of patients who had clinical notes 1 to 6 months before the first intentional self-harm event. Finally, we evaluated the impact of a pretrained model using Word2vec (W2V) on performance. Results: The area under the receiver operating characteristic curve (AUC) for the CNN on the phenotyping task, that is, the detection of intentional self-harm in clinical notes concurrent with the events was 0.999, with an F1 score of 0.985. In the predictive task, the CNN achieved the highest performance with an AUC of 0.882 and an F1 score of 0.769. Although pretraining with W2V shortened the DNN training time, it did not improve performance. Conclusions: The strong performance on the first task, namely, phenotyping based on clinical notes, suggests that such models could be used effectively for surveillance of intentional self-harm in clinical text in an EHR. The modest performance on the predictive task notwithstanding, the results using DNN models on clinical text alone are competitive with other reports in the literature using risk factors from structured EHR data.

  • Source:; Copyright: Priscilla Du Preez; URL:; License: Licensed by JMIR.

    Depression Risk Prediction for Chinese Microblogs via Deep-Learning Methods: Content Analysis


    Background: Depression is a serious personal and public mental health problem. Self-reporting is the main method used to diagnose depression and to determine the severity of depression. However, it is not easy to discover patients with depression owing to feelings of shame in disclosing or discussing their mental health conditions with others. Moreover, self-reporting is time-consuming, and usually leads to missing a certain number of cases. Therefore, automatic discovery of patients with depression from other sources such as social media has been attracting increasing attention. Social media, as one of the most important daily communication systems, connects large quantities of people, including individuals with depression, and provides a channel to discover patients with depression. In this study, we investigated deep-learning methods for depression risk prediction using data from Chinese microblogs, which have potential to discover more patients with depression and to trace their mental health conditions. Objective: The aim of this study was to explore the potential of state-of-the-art deep-learning methods on depression risk prediction from Chinese microblogs. Methods: Deep-learning methods with pretrained language representation models, including bidirectional encoder representations from transformers (BERT), robustly optimized BERT pretraining approach (RoBERTa), and generalized autoregressive pretraining for language understanding (XLNET), were investigated for depression risk prediction, and were compared with previous methods on a manually annotated benchmark dataset. Depression risk was assessed at four levels from 0 to 3, where 0, 1, 2, and 3 denote no inclination, and mild, moderate, and severe depression risk, respectively. The dataset was collected from the Chinese microblog Weibo. We also compared different deep-learning methods with pretrained language representation models in two settings: (1) publicly released pretrained language representation models, and (2) language representation models further pretrained on a large-scale unlabeled dataset collected from Weibo. Precision, recall, and F1 scores were used as performance evaluation measures. Results: Among the three deep-learning methods, BERT achieved the best performance with a microaveraged F1 score of 0.856. RoBERTa achieved the best performance with a macroaveraged F1 score of 0.424 on depression risk at levels 1, 2, and 3, which represents a new benchmark result on the dataset. The further pretrained language representation models demonstrated improvement over publicly released prediction models. Conclusions: We applied deep-learning methods with pretrained language representation models to automatically predict depression risk using data from Chinese microblogs. The experimental results showed that the deep-learning methods performed better than previous methods, and have greater potential to discover patients with depression and to trace their mental health conditions.

  • Source: iStock by Getty Images; Copyright: Minerva Studio; URL:; License: Licensed by the authors.

    Predicting the Development of Type 2 Diabetes in a Large Australian Cohort Using Machine-Learning Techniques: Longitudinal Survey Study


    Background: Previous conventional models for the prediction of diabetes could be updated by incorporating the increasing amount of health data available and new risk prediction methodology. Objective: We aimed to develop a substantially improved diabetes risk prediction model using sophisticated machine-learning algorithms based on a large retrospective population cohort of over 230,000 people who were enrolled in the study during 2006-2017. Methods: We collected demographic, medical, behavioral, and incidence data for type 2 diabetes mellitus (T2DM) in over 236,684 diabetes-free participants recruited from the 45 and Up Study. We predicted and compared the risk of diabetes onset in these participants at 3, 5, 7, and 10 years based on three machine-learning approaches and the conventional regression model. Results: Overall, 6.05% (14,313/236,684) of the participants developed T2DM during an average 8.8-year follow-up period. The 10-year diabetes incidence in men was 8.30% (8.08%-8.49%), which was significantly higher (odds ratio 1.37, 95% CI 1.32-1.41) than that in women at 6.20% (6.00%-6.40%). The incidence of T2DM was doubled in individuals with obesity (men: 17.78% [17.05%-18.43%]; women: 14.59% [13.99%-15.17%]) compared with that of nonobese individuals. The gradient boosting machine model showed the best performance among the four models (area under the curve of 79% in 3-year prediction and 75% in 10-year prediction). All machine-learning models predicted BMI as the most significant factor contributing to diabetes onset, which explained 12%-50% of the variance in the prediction of diabetes. The model predicted that if BMI in obese and overweight participants could be hypothetically reduced to a healthy range, the 10-year probability of diabetes onset would be significantly reduced from 8.3% to 2.8% (P<.001). Conclusions: A one-time self-reported survey can accurately predict the risk of diabetes using a machine-learning approach. Achieving a healthy BMI can significantly reduce the risk of developing T2DM.

  • Source: freepik; Copyright: freepik; URL:; License: Licensed by JMIR.

    Development and Evaluation of a Smart Contract–Enabled Blockchain System for Home Care Service Innovation: Mixed Methods Study


    Background: In the home care industry, the assignment and tracking of care services are controlled by care centers that are centralized in nature and prone to inefficient information transmission. A lack of trust among the involved parties, information opaqueness, and large manual manipulation result in lower process efficiency. Objective: This study aimed to explore and demonstrate the application of blockchain and smart contract technologies to innovate/renovate home care services for harvesting the desired blockchain benefits of process transparency, traceability, and interoperability. Methods: An object-oriented analysis/design combined with a unified modeling language tool was used to construct the architecture of the proposed home care service system. System feasibility was evaluated via an implementation test, and a questionnaire survey was performed to collect opinions from home care service respondents knowledgeable about blockchain and smart contracts. Results: According to the comparative analysis results, the proposed design outperformed the existing system in terms of traceability, system efficiency, and process automation. Moreover, for the questionnaire survey, the quantitative analysis results showed that the proposed blockchain-based system had significantly (P<.001) higher mean scores (when compared with the existing system) in terms of important factors, including timeliness, workflow efficiency, automatic notifications, insurance functionality, and auditable traceability. In summary, blockchain-based home care service participants will be able to enjoy improved efficiency, better transparency, and higher levels of process automation. Conclusions: Blockchain and smart contracts can provide valuable benefits to the home care service industry via distributed data management and process automation. The proposed system enhances user experiences by mitigating human intervention and improving service interoperability, transparency/traceability, and real-time response to home care service events. Efforts in exploring and integrating blockchain-based home care services with emerging technologies, such as the internet of things and artificial intelligence, are expected to provide further benefits and therefore are subject to future research.

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
  • What databases should we include in a comprehensive search strategy protocol for systematic reviews of artificial intelligence?

    Date Submitted: Jul 27, 2020

    Open Peer Review Period: Jul 27, 2020 - Sep 21, 2020

    This is a commentary of the article by Choudhury and Asan entitled, “Role of Artificial Intelligence in Patient Safety Outcomes: Systematic Literature Review”....

    This is a commentary of the article by Choudhury and Asan entitled, “Role of Artificial Intelligence in Patient Safety Outcomes: Systematic Literature Review”.