JMIR Publications

We are scheduled to perform a server upgrade on Thursday, November 30, 2017 between 4 and 6 PM Eastern Time.

Please refrain from submitting support requests related to server downtime during this window.

JMIR Medical Informatics

Clinical informatics, decision support for health professionals, electronic health records, and ehealth infrastructures.


Journal Description

JMIR Medical Informatics (JMI, ISSN 2291-9694) is a top-rated, tier A journal 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 2016: 5.175), 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 journal features a rapid and thorough peer-review process, professional copyediting, professional production of PDF, XHTML, and XML proofs (ready for deposit in PubMed Central/PubMed). The site is optimized for mobile and iPad use.

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:

  • Radiology CT technician and patient being scanned and diagnosed on CT. Source: iStock by Getty Images; Copyright: John Kellerman; URL:; License: Licensed by the authors.

    Standard Anatomic Terminologies: Comparison for Use in a Health Information Exchange–Based Prior Computed Tomography (CT) Alerting System


    Background: A health information exchange (HIE)–based prior computed tomography (CT) alerting system may reduce avoidable CT imaging by notifying ordering clinicians of prior relevant studies when a study is ordered. For maximal effectiveness, a system would alert not only for prior same CTs (exams mapped to the same code from an exam name terminology) but also for similar CTs (exams mapped to different exam name terminology codes but in the same anatomic region) and anatomically proximate CTs (exams in adjacent anatomic regions). Notification of previous same studies across an HIE requires mapping of local site CT codes to a standard terminology for exam names (such as Logical Observation Identifiers Names and Codes [LOINC]) to show that two studies with different local codes and descriptions are equivalent. Notifying of prior similar or proximate CTs requires an additional mapping of exam codes to anatomic regions, ideally coded by an anatomic terminology. Several anatomic terminologies exist, but no prior studies have evaluated how well they would support an alerting use case. Objective: The aim of this study was to evaluate the fitness of five existing standard anatomic terminologies to support similar or proximate alerts of an HIE-based prior CT alerting system. Methods: We compared five standard anatomic terminologies (Foundational Model of Anatomy, Systematized Nomenclature of Medicine Clinical Terms, RadLex, LOINC, and LOINC/Radiological Society of North America [RSNA] Radiology Playbook) to an anatomic framework created specifically for our use case (Simple ANatomic Ontology for Proximity or Similarity [SANOPS]), to determine whether the existing terminologies could support our use case without modification. On the basis of an assessment of optimal terminology features for our purpose, we developed an ordinal anatomic terminology utility classification. We mapped samples of 100 random and the 100 most frequent LOINC CT codes to anatomic regions in each terminology, assigned utility classes for each mapping, and statistically compared each terminology’s utility class rankings. We also constructed seven hypothetical alerting scenarios to illustrate the terminologies’ differences. Results: Both RadLex and the LOINC/RSNA Radiology Playbook anatomic terminologies ranked significantly better (P<.001) than the other standard terminologies for the 100 most frequent CTs, but no terminology ranked significantly better than any other for 100 random CTs. Hypothetical scenarios illustrated instances where no standard terminology would support appropriate proximate or similar alerts, without modification. Conclusions: LOINC/RSNA Radiology Playbook and RadLex’s anatomic terminologies appear well suited to support proximate or similar alerts for commonly ordered CTs, but for less commonly ordered tests, modification of the existing terminologies with concepts and relations from SANOPS would likely be required. Our findings suggest SANOPS may serve as a framework for enhancing anatomic terminologies in support of other similar use cases.

  • A senior resident during tele-consultation process. Source: Image created by the Authors; Copyright: Kolsoum Deldar; URL:; License: Creative Commons Attribution (CC-BY).

    A Data Model for Teleconsultation in Managing High-Risk Pregnancies: Design and Preliminary Evaluation


    Background: Teleconsultation is a guarantor for virtual supervision of clinical professors on clinical decisions made by medical residents in teaching hospitals. Type, format, volume, and quality of exchanged information have a great influence on the quality of remote clinical decisions or tele-decisions. Thus, it is necessary to develop a reliable and standard model for these clinical relationships. Objective: The goal of this study was to design and evaluate a data model for teleconsultation in the management of high-risk pregnancies. Methods: This study was implemented in three phases. In the first phase, a systematic review, a qualitative study, and a Delphi approach were done in selected teaching hospitals. Systematic extraction and localization of diagnostic items to develop the tele-decision clinical archetypes were performed as the second phase. Finally, the developed model was evaluated using predefined consultation scenarios. Results: Our review study has shown that present medical consultations have no specific structure or template for patient information exchange. Furthermore, there are many challenges in the remote medical decision-making process, and some of them are related to the lack of the mentioned structure. The evaluation phase of our research has shown that data quality (P<.001), adequacy (P<.001), organization (P<.001), confidence (P<.001), and convenience (P<.001) had more scores in archetype-based consultation scenarios compared with routine-based ones. Conclusions: Our archetype-based model could acquire better and higher scores in the data quality, adequacy, organization, confidence, and convenience dimensions than ones with routine scenarios. It is probable that the suggested archetype-based teleconsultation model may improve the quality of physician-physician remote medical consultations.

  • Source:; Copyright: George Hodan; URL:; License: Public Domain (CC0).

    Examining Tensions That Affect the Evaluation of Technology in Health Care: Considerations for System Decision Makers From the Perspective of Industry and...


    Virtual technologies have the potential to mitigate a range of challenges for health care systems. Despite the widespread use of mobile devices in everyday life, they currently have a limited role in health service delivery and clinical care. Efforts to integrate the fast-paced consumer technology market with health care delivery exposes tensions among patients, providers, vendors, evaluators, and system decision makers. This paper explores the key tensions between the high bar for evidence prior to market approval that guides health care regulatory decisions and the “fail fast” reality of the technology industry. We examine three core tensions: balancing user needs versus system needs, rigor versus responsiveness, and the role of pre- versus postmarket evidence generation. We use these to elaborate on the structure and appropriateness of evaluation mechanisms for virtual care solutions. Virtual technologies provide a foundation for personalized, patient-centered medicine on the user side, coupled with a broader understanding of impact on the system side. However, mechanisms for stakeholder discussion are needed to clarify the nature of the health technology marketplace and the drivers of evaluation priorities.

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

    Adverse Drug Event Discovery Using Biomedical Literature: A Big Data Neural Network Adventure


    Background: The study of adverse drug events (ADEs) is a tenured topic in medical literature. In recent years, increasing numbers of scientific articles and health-related social media posts have been generated and shared daily, albeit with very limited use for ADE study and with little known about the content with respect to ADEs. Objective: The aim of this study was to develop a big data analytics strategy that mines the content of scientific articles and health-related Web-based social media to detect and identify ADEs. Methods: We analyzed the following two data sources: (1) biomedical articles and (2) health-related social media blog posts. We developed an intelligent and scalable text mining solution on big data infrastructures composed of Apache Spark, natural language processing, and machine learning. This was combined with an Elasticsearch No-SQL distributed database to explore and visualize ADEs. Results: The accuracy, precision, recall, and area under receiver operating characteristic of the system were 92.7%, 93.6%, 93.0%, and 0.905, respectively, and showed better results in comparison with traditional approaches in the literature. This work not only detected and classified ADE sentences from big data biomedical literature but also scientifically visualized ADE interactions. Conclusions: To the best of our knowledge, this work is the first to investigate a big data machine learning strategy for ADE discovery on massive datasets downloaded from PubMed Central and social media. This contribution illustrates possible capacities in big data biomedical text analysis using advanced computational methods with real-time update from new data published on a daily basis.

  • Source: The Authors /; Copyright: JMIR Publications; URL:; License: Creative Commons Attribution (CC-BY).

    Search and Graph Database Technologies for Biomedical Semantic Indexing: Experimental Analysis


    Background: Biomedical semantic indexing is a very useful support tool for human curators in their efforts for indexing and cataloging the biomedical literature. Objective: The aim of this study was to describe a system to automatically assign Medical Subject Headings (MeSH) to biomedical articles from MEDLINE. Methods: Our approach relies on the assumption that similar documents should be classified by similar MeSH terms. Although previous work has already exploited the document similarity by using a k-nearest neighbors algorithm, we represent documents as document vectors by search engine indexing and then compute the similarity between documents using cosine similarity. Once the most similar documents for a given input document are retrieved, we rank their MeSH terms to choose the most suitable set for the input document. To do this, we define a scoring function that takes into account the frequency of the term into the set of retrieved documents and the similarity between the input document and each retrieved document. In addition, we implement guidelines proposed by human curators to annotate MEDLINE articles; in particular, the heuristic that says if 3 MeSH terms are proposed to classify an article and they share the same ancestor, they should be replaced by this ancestor. The representation of the MeSH thesaurus as a graph database allows us to employ graph search algorithms to quickly and easily capture hierarchical relationships such as the lowest common ancestor between terms. Results: Our experiments show promising results with an F1 of 69% on the test dataset. Conclusions: To the best of our knowledge, this is the first work that combines search and graph database technologies for the task of biomedical semantic indexing. Due to its horizontal scalability, ElasticSearch becomes a real solution to index large collections of documents (such as the bibliographic database MEDLINE). Moreover, the use of graph search algorithms for accessing MeSH information could provide a support tool for cataloging MEDLINE abstracts in real time.

  • Mother and daughter with staff in Intensive Care Unit. Source:; Copyright: Monkey Business Images; URL:; License: Licensed by the authors.

    Predicting Unplanned Transfers to the Intensive Care Unit: A Machine Learning Approach Leveraging Diverse Clinical Elements


    Background: Early warning scores aid in the detection of pediatric clinical deteriorations but include limited data inputs, rarely include data trends over time, and have limited validation. Objective: Machine learning methods that make use of large numbers of predictor variables are now commonplace. This work examines how different types of predictor variables derived from the electronic health record affect the performance of predicting unplanned transfers to the intensive care unit (ICU) at three large children’s hospitals. Methods: We trained separate models with data from three different institutions from 2011 through 2013 and evaluated models with 2014 data. Cases consisted of patients who transferred from the floor to the ICU and met one or more of 5 different priori defined criteria for suspected unplanned transfers. Controls were patients who were never transferred to the ICU. Predictor variables for the models were derived from vitals, labs, acuity scores, and nursing assessments. Classification models consisted of L1 and L2 regularized logistic regression and neural network models. We evaluated model performance over prediction horizons ranging from 1 to 16 hours. Results: Across the three institutions, the c-statistic values for our best models were 0.892 (95% CI 0.875-0.904), 0.902 (95% CI 0.880-0.923), and 0.899 (95% CI 0.879-0.919) for the task of identifying unplanned ICU transfer 6 hours before its occurrence and achieved 0.871 (95% CI 0.855-0.888), 0.872 (95% CI 0.850-0.895), and 0.850 (95% CI 0.825-0.875) for a prediction horizon of 16 hours. For our first model at 80% sensitivity, this resulted in a specificity of 80.5% (95% CI 77.4-83.7) and a positive predictive value of 5.2% (95% CI 4.5-6.2). Conclusions: Feature-rich models with many predictor variables allow for patient deterioration to be predicted accurately, even up to 16 hours in advance.

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

    Patient Portal Utilization Among Ethnically Diverse Low Income Older Adults: Observational Study


    Background: Patient portals can improve patient communication with providers, provide patients with greater health information access, and help improve patient decision making, if they are used. Because research on factors facilitating and limiting patient portal utilization has not been conceptually based, no leverage points have been indicated for improving utilization. Objective: The primary objective for this analysis was to use a conceptual framework to determine potentially modifiable factors affecting patient portal utilization by older adults (aged 55 years and older) who receive care at clinics that serve low income and ethnically diverse communities. The secondary objective was to delineate how patient portal utilization is associated with perceived usefulness and usability. Methods: Patients from one urban and two rural clinics serving low income patients were recruited and completed interviewer-administered questionnaires on patient portal utilization. Results: A total of 200 ethnically diverse patients completed questionnaires, of which 41 (20.5%) patients reported utilizing portals. Education, social support, and frequent Internet utilization improve the odds of patient portal utilization; receiving health care at a rural clinic decreases the odds of portal utilization. Conclusions: Leverage points to address disparities in patient portal utilization include providing training for older adults in patient portal utilization, involving spouses or other care partners in this training, and making information technology access available at public places in rural and urban communities.

  • The 2016 Beijing Health Conference and Datathon. Source: Image created by the Authors; Copyright: The Authors; URL:; License: Public Domain (CC0).

    Promoting Secondary Analysis of Electronic Medical Records in China: Summary of the PLAGH-MIT Critical Data Conference and Health Datathon


    Electronic health records (EHRs) have been widely adopted among modern hospitals to collect and track clinical data. Secondary analysis of EHRs could complement the traditional randomized control trial (RCT) research model. However, most researchers in China lack either the technical expertise or the resources needed to utilize EHRs as a resource. In addition, a climate of cross-disciplinary collaboration to gain insights from EHRs, a crucial component of a learning healthcare system, is not prevalent. To address these issues, members from the Massachusetts Institute of Technology (MIT) and the People’s Liberation Army General Hospital (PLAGH) organized the first clinical data conference and health datathon in China, which provided a platform for clinicians, statisticians, and data scientists to team up and address information gaps in the intensive care unit (ICU).

  • Changing paper-based clinical processes workflows through open source EHR solutions. Source: Authors; Copyright: Authors; License: Creative Commons Attribution (CC-BY).

    Open-Source Electronic Health Record Systems for Low-Resource Settings: Systematic Review


    Background: Despite the great impact of information and communication technologies on clinical practice and on the quality of health services, this trend has been almost exclusive to developed countries, whereas countries with poor resources suffer from many economic and social issues that have hindered the real benefits of electronic health (eHealth) tools. As a component of eHealth systems, electronic health records (EHRs) play a fundamental role in patient management and effective medical care services. Thus, the adoption of EHRs in regions with a lack of infrastructure, untrained staff, and ill-equipped health care providers is an important task. However, the main barrier to adopting EHR software in low- and middle-income countries is the cost of its purchase and maintenance, which highlights the open-source approach as a good solution for these underserved areas. Objective: The aim of this study was to conduct a systematic review of open-source EHR systems based on the requirements and limitations of low-resource settings. Methods: First, we reviewed existing literature on the comparison of available open-source solutions. In close collaboration with the University of Gondar Hospital, Ethiopia, we identified common limitations in poor resource environments and also the main requirements that EHRs should support. Then, we extensively evaluated the current open-source EHR solutions, discussing their strengths and weaknesses, and their appropriateness to fulfill a predefined set of features relevant for low-resource settings. Results: The evaluation methodology allowed assessment of several key aspects of available solutions that are as follows: (1) integrated applications, (2) configurable reports, (3) custom reports, (4) custom forms, (5) interoperability, (6) coding systems, (7) authentication methods, (8) patient portal, (9) access control model, (10) cryptographic features, (11) flexible data model, (12) offline support, (13) native client, (14) Web client,(15) other clients, (16) code-based language, (17) development activity, (18) modularity, (19) user interface, (20) community support, and (21) customization. The quality of each feature is discussed for each of the evaluated solutions and a final comparison is presented. Conclusions: There is a clear demand for open-source, reliable, and flexible EHR systems in low-resource settings. In this study, we have evaluated and compared five open-source EHR systems following a multidimensional methodology that can provide informed recommendations to other implementers, developers, and health care professionals. We hope that the results of this comparison can guide decision making when needing to adopt, install, and maintain an open-source EHR solution in low-resource settings.

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

    Ranking Medical Terms to Support Expansion of Lay Language Resources for Patient Comprehension of Electronic Health Record Notes: Adapted Distant Supervision...


    Background: Medical terms are a major obstacle for patients to comprehend their electronic health record (EHR) notes. Clinical natural language processing (NLP) systems that link EHR terms to lay terms or definitions allow patients to easily access helpful information when reading through their EHR notes, and have shown to improve patient EHR comprehension. However, high-quality lay language resources for EHR terms are very limited in the public domain. Because expanding and curating such a resource is a costly process, it is beneficial and even necessary to identify terms important for patient EHR comprehension first. Objective: We aimed to develop an NLP system, called adapted distant supervision (ADS), to rank candidate terms mined from EHR corpora. We will give EHR terms ranked as high by ADS a higher priority for lay language annotation—that is, creating lay definitions for these terms. Methods: Adapted distant supervision uses distant supervision from consumer health vocabulary and transfer learning to adapt itself to solve the problem of ranking EHR terms in the target domain. We investigated 2 state-of-the-art transfer learning algorithms (ie, feature space augmentation and supervised distant supervision) and designed 5 types of learning features, including distributed word representations learned from large EHR data for ADS. For evaluating ADS, we asked domain experts to annotate 6038 candidate terms as important or nonimportant for EHR comprehension. We then randomly divided these data into the target-domain training data (1000 examples) and the evaluation data (5038 examples). We compared ADS with 2 strong baselines, including standard supervised learning, on the evaluation data. Results: The ADS system using feature space augmentation achieved the best average precision, 0.850, on the evaluation set when using 1000 target-domain training examples. The ADS system using supervised distant supervision achieved the best average precision, 0.819, on the evaluation set when using only 100 target-domain training examples. The 2 ADS systems both performed significantly better than the baseline systems (P<.001 for all measures and all conditions). Using a rich set of learning features contributed to ADS’s performance substantially. Conclusions: ADS can effectively rank terms mined from EHRs. Transfer learning improved ADS’s performance even with a small number of target-domain training examples. EHR terms prioritized by ADS were used to expand a lay language resource that supports patient EHR comprehension. The top 10,000 EHR terms ranked by ADS are available upon request.

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

    Adopting Telemedicine for the Self-Management of Hypertension: Systematic Review


    Background: Hypertension is a chronic condition that affects adults of all ages. In the United States, 1 in 3 adults has hypertension, and about half of the hypertensive population is adequately controlled. This costs the nation US $46 billion each year in health care services and medications required for treatment and missed workdays. Finding easier ways of managing this condition is key to successful treatment. Objective: A solution to reduce visits to physicians for chronic conditions is to utilize telemedicine. Research is limited on the effects of utilizing telemedicine in health care facilities. There are potential benefits for implementing telemedicine programs with patients dealing with chronic conditions. The purpose of this review was to weigh the facilitators against the barriers for implementing telemedicine. Methods: Searches were methodically conducted in the Cumulative Index to Nursing and Allied Health Literature Complete (CINAHL Complete) via Elton B Stephens Company (EBSCO) and PubMed (which queries MEDLINE) to collect information about self-management of hypertension through the use of telemedicine. Results: Results identify facilitators and barriers corresponding to the implementation of self-management of hypertension using telemedicine. The most common facilitators include increased access, increase in health and quality, patient knowledge and involvement, technology growth with remote monitoring, cost-effectiveness, and increased convenience/ease. The most prevalent barriers include lack of evidence, self-management difficult to maintain, no long-term results/more areas to address, and long-term added workload commitment. Conclusions: This review guides health care professionals in incorporating new practices and identifying the best methods to introduce telemedicine into their practices. Understanding the facilitators and barriers to implementation is important, as is understanding how these factors will impact a successful implementation of telemedicine in the area of self-management of hypertension.

  • Health eRIDE Facebook page (montage). Source: Pro-Change Behavior Systems, Inc. /; Copyright: JMIR Publications; URL:; License: Creative Commons Attribution (CC-BY).

    Pain Self-Management for Veterans: Development and Pilot Test of a Stage-Based Mobile-Optimized Intervention


    Background: Chronic pain is a significant public health burden affecting more Americans than cardiovascular disease, diabetes, and cancer combined. Veterans are disproportionately affected by chronic pain. Among previously deployed soldiers and veterans, the prevalence of chronic pain is estimated between 44% and 60%. Objective: The objective of this research was to develop and pilot-test Health eRide: Your Journey to Managing Pain, a mobile pain self-management program for chronic musculoskeletal pain for veterans. Based on the transtheoretical model of behavior change, the intervention is tailored to veterans’ stage of change for adopting healthy strategies for pain self-management and their preferred strategies. It also addresses stress management and healthy sleep, two components of promising integrated treatments for veterans with pain and co-occurring conditions, including posttraumatic stress disorder (PTSD) and traumatic brain injury. In addition, Health eRide leverages gaming principles, text messaging (short message service, SMS), and social networking to increase engagement and retention. Methods: Pilot test participants were 69 veterans recruited in-person and by mail at a Veterans Health Administration facility, by community outreach, and by a Web-based survey company. Participants completed a mobile-delivered baseline assessment and Health eRide intervention session. During the next 30 days, they had access to a Personal Activity Center with additional stage-matched activities and information and had the option of receiving tailored text messages. Pre-post assessments, administered at baseline and the 30-day follow-up, included measures of pain, pain impact, use of pain self-management strategies, PTSD, and percentage in the Action or Maintenance stage for adopting pain self-management, managing stress, and practicing healthy sleep habits. Global impressions of change and program acceptability and usability were also assessed at follow-up. Results: Among the 44 veterans who completed the 30-day post assessment, there were statistically significant pre-post reductions in pain (P<.001) and pain impact (P<.001); there was some reduction in symptoms of PTSD (P=.05). There were significant pre-post increases in the percentage of participants in the Action or Maintenance stage for adopting pain self-management (P=.01) and for managing stress (P<.001) but not for practicing healthy sleep habits (P=.11). The global impressions of change measure showed that a majority had experienced some level of improvement. User ratings of acceptability were quite high; ratings of usability fell slightly below the mean for digital programs. Conclusions: Preliminary data demonstrate the potential impact of the Health eRide program for chronic musculoskeletal pain for veterans. The results underscore that simultaneously addressing other behaviors may be a promising approach to managing pain and comorbid conditions. Additional formative research is required to complete development of the Health eRide program and to address areas of usability requiring improvement. A randomized trial with longer follow-up is needed to demonstrate the program’s long-term effects on pain and pain self-management.

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
  • Diabetes Related Behavior Modification Knowledge Transfer To Primary Care Via Integrated Digital Health Platform

    Date Submitted: Dec 11, 2017

    Open Peer Review Period: Dec 12, 2017 - Feb 6, 2018

    Background: Effective diabetes self-management that rests on the behavior of an individual can improve outcomes, decrease the risk of complications, reduce diabetes related hospitalizations and costs....

    Background: Effective diabetes self-management that rests on the behavior of an individual can improve outcomes, decrease the risk of complications, reduce diabetes related hospitalizations and costs. Objective: To develop and evaluate a computerized decision support platform called “Diabetes Web-Centric Information and Support Environment (DWISE)” that assist primary care practitioners (PCP) in applying standardized behavior change strategies and clinical practice guidelines (CPG)-based recommendations to an individual patient and, empower the patient with the skills and knowledge to self-manage their diabetes through planned, personalized and pervasive behavior change strategies. Methods: Healthcare Knowledge Management approach is used to implement DWISE that features the following functionalities: (i) Assessment of PCP’s readiness to administer validated behavior change interventions to patients with diabetes patients; (ii) Educational support to PCP to help them offer behavior change interventions to patients; (iii) Access to evidence-based material, such as the CDA CPG, to the PCP; (iv) Development of personalized patient self-management programs to help patients with diabetes achieve healthy behaviors to meet CDA targets for managing type 2 diabetes; (v) Educational support for patients to help them achieve behavior change; (vi) Monitoring the patients’ progress in adhering to their behavior change program and motivating them to be in compliance with their program. DWISE offers these functionalities through an interactive web-based interface to PCP, whereas the patient’s self-management program and associated behavior interventions are delivered through mobile patient diary on the smart phones and tablets Results: DWISE has been tested for its usability, functionality usefulness and acceptance through a series of qualitative studies. For the PCP tool, most usability problems were associated with the navigation of the tool, and the presentation, formatting, understandability and suitability of the content. For the patient tool, most issues are related to the tool’s screen layout and design features, understandability of the content, clarity of the labels used and navigation across the tool. Facilitators and barriers to DWISE use in shared decision-making environment have also been identified. Conclusions: This work has provided a unique e-health solution to translate complex healthcare knowledge in terms of easy-to use, evidence-informed, point-of-care decision aids for PCP and patients The results are been used to guide the necessary modification of DWISE. Clinical Trial: N/A

  • Development of an eHealth system to capture and analyze patient sensor and self-report data: Potential applications to improve cancer care delivery

    Date Submitted: Nov 29, 2017

    Open Peer Review Period: Nov 30, 2017 - Jan 25, 2018

    Background: “COMPASS” (“Capturing and Analyzing Sensor and Self-Report Data for Clinicians and Researchers) is an eHealth platform designed to improve cancer care delivery through passive monito...

    Background: “COMPASS” (“Capturing and Analyzing Sensor and Self-Report Data for Clinicians and Researchers) is an eHealth platform designed to improve cancer care delivery through passive monitoring of patients’ health status and delivering customizable reports to clinicians. Based on data from sensors and context-driven administration of patient-reported outcome (PRO) measures, key indices of patients’ functional status can be collected between regular clinic visits, supporting clinicians in the delivery of patient care. Objective: The aim of the first phase of this project was to systematically collect input from oncology providers and patients on potential clinical applications for COMPASS in order to refine the system. Methods: Ten clinicians representing various oncology specialties and disciplines completed semi-structured interviews designed to solicit clinician input on how COMPASS can best support clinical care delivery. Three cancer patients tested a prototype of COMPASS for 7 days and provided feedback. Interview data was tabulated using thematic content analysis (TCA) to identify the most clinically relevant objective and PRO domains. Results: TCA revealed that clinicians were most interested in monitoring vital statistics, symptoms and functional status, including physical activity level (n=9), weight (n=5), fatigue (n=9), sleep quality (n=8) and anxiety. Patients (2 in active treatment, 1 in remission) reported that they would use such a device, were enthusiastic about their clinicians monitoring their health status, especially the tracking of symptoms, and felt knowing their clinicians were monitoring and reviewing their health status provided valuable reassurance. Patients would however like to provide some context to their data. Conclusions: Clinicians and patients both articulated potential benefits of the COMPASS system in improving cancer care. From a clinician standpoint, data needs to be easily interpretable and actionable. The fact that patients and clinicians both see potential value in eHealth systems suggests wider adoption and utilization could prove to be a useful tool for improving care delivery.

  • Potential application of connected tuberculosis diagnostics for real-time surveillance of drug resistant TB transmission

    Date Submitted: Nov 1, 2017

    Open Peer Review Period: Nov 2, 2017 - Dec 28, 2017

    Background: Tuberculosis (TB) is the top killer infectious disease in the world, and yet the surveillance of this disease is still paper-based. Rifampicin resistant TB (RR-TB) is an urgent public heal...

    Background: Tuberculosis (TB) is the top killer infectious disease in the world, and yet the surveillance of this disease is still paper-based. Rifampicin resistant TB (RR-TB) is an urgent public health crisis, and the World Health Organization has endorsed since 2010 a series of rapid diagnostic tests (RDTs) that allowed rapid detection of drug resistant strains and produced large volumes of data. In parallel, most high burden countries have adopted connectivity solutions that allow linking of diagnostics, real-time capture and shared repository of these test results. However, these connected diagnostics and readily available test results are not utilised to their full capacity as we have yet to capitalize on fully understanding the relationship between test results and specific rpoB mutations to elucidate its potential application on real-time surveillance. Objective: We aimed to validate and analyse RDT data in detail, and propose the potential use of connected diagnostics and associated test results for real-time evaluation of RR-TB transmission. Methods: From the Belgian Coordinated Collections of Microorganisms at the Institute of Tropical Medicine, 107 RR-TB strains harbouring 34 unique rpoB mutations, including 30 within the Rifampicin Resistance Determining Region (RRDR), were selected. These strains were subjected to XpertMTB/RIF (Cepheid), GenoTypeMTBDRplusv2.0 (Hain LifeScience GmbH), and GenoscholarNTM+MDRTBII (Nipro), the results of which were validated against the strains’ available rpoB gene sequences. The reproducibility of the results was determined, and the probe reactions were analysed and visualised, and proposed for potential use in evaluating transmission. Results: TB diagnostic test results, particularly the RDT probe reactions detected the majority of RRDR mutations tested, although a few critical discrepancies between observed probe reactions and manufacturer claims were found. Based on published frequencies of probe reactions and RRDR mutations, we found specific probe reactions with high potential use in transmission studies namely XpertMTB/RIF probes A, Bdelayed, C, Edelayed; GenotypeMTBDRplusv2.0 WT2, WT5, WT6; and GenoscholarNTM+MDRTBII S1, S3. Additionally, inspection of probe reactions of disputed mutations may potentially resolve discordance between genotypic and phenotypic test results. Conclusions: We propose a novel approach for potential real-time detection of RR-TB transmission through fully utilizing connected TB diagnostics and shared repository of test results. To our knowledge, this is the first pragmatic and scalable work in response to the consensus of world-renowned TB experts in 2016 on the potential of diagnostic connectivity for accelerated efforts toward TB elimination. This is evidenced by the ability of our proposed approach to facilitate comparison of probe reactions between and among different RDTs used in the same setting. Integrating this proposed approach as a plug-in module to a connectivity platform will increase usefulness of connected TB diagnostics for RR-TB outbreak detection through real-time investigation of suspected RR-TB transmission cases based on epidemiological linking.

  • Information Technology-Assisted Treatment Planning and Performance Assessment For Severe Thalassemia Care in a resource-limited setting

    Date Submitted: Oct 27, 2017

    Open Peer Review Period: Oct 28, 2017 - Dec 23, 2017

    Background: Successful models of information and communication technology (ICT) applied to cost-effective delivery of quality care in low- and middle-income countries (LMIC) are an increasing necessit...

    Background: Successful models of information and communication technology (ICT) applied to cost-effective delivery of quality care in low- and middle-income countries (LMIC) are an increasing necessity. Severe thalassemia (ST) is one of the most common life-threatening non-communicable diseases of children globally. Objective: To study the impact of ICT on quality of care for ST patients in LMIC. Methods: A total of 1110 patients with ST from 5 centers in India were followed over a one-year period. The impact of consistent use of a web-based application platform designed to assist comprehensive management of ST (ThalcareTM) on key indicators of quality of care such as minimum (pre-transfusion) hemoglobin, serum ferritin, liver size and spleen size was assessed. Results: For four centers, the improvement in mean pre-transfusion hemoglobin level was statistically very significant (P<0.001). Four out of five centers achieved reduction in mean ferritin levels with two displaying a highly significant drop in ferritin (P=0.003 and P=0.0002). One of the five centers did not record liver and spleen size on palpation, but out of the remaining 4 centers, 2 witnessed a strongly significant drop in liver and spleen size (P <0.01), 1 witnessed moderate drop (P= 0.05 for liver P =0.03 for spleen size) while the fourth witnessed a moderately increase in liver size (P =0.08) and insignificant change in spleen size (P=0.12). Conclusions: Implementation of Computer-Assisted Treatment Planning and Performance Assessment positively impacted on indices reflecting effective delivery of care to patients suffering from ST in LMIC consistently.

  • MIROR, An automated modular MRI clinical decision support system: an application in paediatric cancer diagnosis

    Date Submitted: Oct 25, 2017

    Open Peer Review Period: Oct 26, 2017 - Dec 21, 2017

    Background: Advances in magnetic resonance imaging (MRI) and the introduction of clinical decision support systems has underlined the need for an analysis tool to extract and analyse relevant informat...

    Background: Advances in magnetic resonance imaging (MRI) and the introduction of clinical decision support systems has underlined the need for an analysis tool to extract and analyse relevant information from MRI data to aid decision-making, prevent errors and enhance health care. Objective: The aim of this study was to design and develop a modular Medical Image Region of interest analysis tool and Repository (MIROR) for automatic processing, classification, evaluation and representation of advanced MRI data. Methods: The clinical decision support system was developed and evaluated for diffusion-weighted imaging of body tumours in children (cohort of 48 children, with 37 malignant and 11 benign tumours). Mevislab software and Python have been used for development of MIROR. Regions of interests were drawn around benign and malignant body tumours on different diffusion parametric maps and extracted information was used to discriminate the malignant from benign tumours. Results: Using MIROR, the various histogram parameters derived for each tumour case when compared with the information in the repository, provided additional information for tumour characterization and facilitated the discrimination between benign and malignant tumours. Clinical decision support system cross validation showed high sensitivity and specificity in discriminating between these tumour groups for various histogram parameters, 100 % for kurtosis and entropy 85% and 78% respectively over all parameters. Conclusions: MIROR as a diagnostic tool and repository allowed the interpretation and analysis of MRI images to be more accessible and comprehensive for clinicians. It aims to increase clinicians’ skillset by introducing newer techniques and up-to-date findings to their repertoire and make information from previous cases available to aid decision-making. The modular-based format of the tool allowed integration of analyses which are not readily available clinically and streamlines future developments. Clinical Trial: N/A