Digital Determinants of Health: Health data poverty amplifies existing health disparities-A scoping review.

Artificial intelligence (AI) and machine learning (ML) have an immense potential to transform healthcare as already demonstrated in various medical specialties. This scoping review focuses on the factors that influence health data poverty, by conducting a literature review, analysis, and appraisal of results. Health data poverty is often an unseen factor which leads to perpetuating or exacerbating health disparities. Improvements or failures in addressing health data poverty will directly impact the effectiveness of AI/ML systems. The potential causes are complex and may enter anywhere along the development process. The initial results highlighted studies with common themes of health disparities (72%), AL/ML bias (28%) and biases in input data (18%). To properly evaluate disparities that exist we recommend a strengthened effort to generate unbiased equitable data, improved understanding of the limitations of AI/ML tools, and rigorous regulation with continuous monitoring of the clinical outcomes of deployed tools.

Adoption of Electronic Medical Records for Chronic Disease Care in Kenyan Refugee Camps: Quantitative and Qualitative Prospective Evaluation.

Background: Noncommunicable disease (NCD) prevention and control in humanitarian emergencies is a well-recognized need, but there is little evidence to guide responses, leading to varying care delivery. The Sana.NCD mobile health (mHealth) app, initially developed in Lebanon, is the only known mHealth tool for NCD management designed to increase care quality and coverage for providers in humanitarian settings. Objective: We evaluated a specialized mHealth app consisting of an abbreviated medical record for patients with hypertension or diabetes, adapted for a Kenyan refugee camp setting. Methods: We tested an adapted version of the Sana.NCD app (diabetes and hypertension medical record) in an 11-month (May 2021 to March 2022) quantitative and qualitative prospective evaluation in Kenya's Hagadera refugee camp. Leveraging the rollout of a general electronic medical record (EMR) system in the Kakuma refugee camp, we compared a specialized NCD management app to a general EMR. We analyzed secondary data collected from the Sana.NCD app for 1539 patients, EMR data for 68 patients with NCD from Kakuma's surgical and outpatient departments, and key informant interviews that focused on Hagadera clinic staff perceptions of the Sana.NCD app. Results: The Hagadera NCD clinic reported 18,801 consultations, 42.1% (n=7918) of which were reported in the NCD app. The Kakuma EMR reported 350,776 visits, of which 9385 (2.7%) were for NCDs (n=4264, 1.2% hypertension; n=2415, 0.7% diabetes). The completeness of reporting was used as a quality-of-care metric. Age, sex, prescribed medicines, random blood sugar, and smoking status were consistently reported in both the NCD app (>98%) and EMR (100%), whereas comorbidities, complications, hemoglobin A1c, and diet were rarely reported in either platform (≤7% NCD app; 0% EMR). The number of visits, BMI, physical activity, and next visit were frequently reported in the NCD app (≥99%) but not in the EMR (≤15%). In the NCD app, the completeness of reporting was high across the implementation period, with little meaningful change. Although not significantly changed during the study, elevated blood sugar (P=.82) and blood pressure (P=.12) were reported for sizable proportions of patients in the first (302/481, 62.8%, and 599/1094, 54.8%, respectively) and last (374/602, 62.1%, and 720/1395, 51.6%, respectively) study quarters. Providers were satisfied with the app, as it standardized patient information and made consultations easier. Providers also indicated that access to historic patient information was easier, benefiting NCD control and follow-up. Conclusions: A specialized record for NCDs outperformed a more general record intended for use in all patients in terms of reporting completeness. This CommCare-based NCD app can easily be rolled out in similar humanitarian settings with minimal adaptation. However, the adaptation of technologies to the local context and use case is critical for uptake and ensuring that workflows and time burden do not outweigh the benefits of EMRs.

Big data and machine learning in critical care: Opportunities for collaborative research.

The introduction of clinical information systems (CIS) in Intensive Care Units (ICUs) offers the possibility of storing a huge amount of machine-ready clinical data that can be used to improve patient outcomes and the allocation of resources, as well as suggest topics for randomized clinical trials. Clinicians, however, usually lack the necessary training for the analysis of large databases. In addition, there are issues referred to patient privacy and consent, and data quality. Multidisciplinary collaboration among clinicians, data engineers, machine-learning experts, statisticians, epidemiologists and other information scientists may overcome these problems. A multidisciplinary event (Critical Care Datathon) was held in Madrid (Spain) from 1 to 3 December 2017. Under the auspices of the Spanish Critical Care Society (SEMICYUC), the event was organized by the Massachusetts Institute of Technology (MIT) Critical Data Group (Cambridge, MA, USA), the Innovation Unit and Critical Care Department of San Carlos Clinic Hospital, and the Life Supporting Technologies group of Madrid Polytechnic University. After presentations referred to big data in the critical care environment, clinicians, data scientists and other health data science enthusiasts and lawyers worked in collaboration using an anonymized database (MIMIC III). Eight groups were formed to answer different clinical research questions elaborated prior to the meeting. The event produced analyses for the questions posed and outlined several future clinical research opportunities. Foundations were laid to enable future use of ICU databases in Spain, and a timeline was established for future meetings, as an example of how big data analysis tools have tremendous potential in our field.

Feature selection and prediction of treatment failure in tuberculosis.

BACKGROUND: Tuberculosis is a major cause of morbidity and mortality in the developing world. Drug resistance, which is predicted to rise in many countries worldwide, threatens tuberculosis treatment and control. OBJECTIVE: To identify features associated with treatment failure and to predict which patients are at highest risk of treatment failure. METHODS: On a multi-country dataset managed by the National Institute of Allergy and Infectious Diseases we applied various machine learning techniques to identify factors statistically associated with treatment failure and to predict treatment failure based on baseline demographic and clinical characteristics alone. RESULTS: The complete-case analysis database consisted of 587 patients (68% males) with a median (p25-p75) age of 40 (30-51) years. Treatment failure occurred in approximately one fourth of the patients. The features most associated with treatment failure were patterns of drug sensitivity, imaging findings, findings in the microscopy Ziehl-Nielsen stain, education status, and employment status. The most predictive model was forward stepwise selection (AUC: 0.74), although most models performed at or above AUC 0.7. A sensitivity analysis using the 643 original patients filling the missing values with multiple imputation showed similar predictive features and generally increased predictive performance. CONCLUSION: Machine learning can help to identify patients at higher risk of treatment failure. Closer monitoring of these patients may decrease treatment failure rates and prevent emergence of antibiotic resistance. The use of inexpensive basic demographic and clinical features makes this approach attractive in low and middle-income countries.

Hacking Hackathons: Preparing the next generation for the multidisciplinary world of healthcare technology.

OBJECTIVE: Machine learning in healthcare, and innovative healthcare technology in general, require complex interactions within multidisciplinary teams. Healthcare hackathons are being increasingly used as a model for cross-disciplinary collaboration and learning. The aim of this study is to explore high school student learning experiences during a healthcare hackathon. By optimizing their learning experiences, we hope to prepare a future workforce that can bridge technical and health fields and work seamlessly across disciplines. METHODS: A qualitative exploratory study utilizing focus group interviews was conducted. Eight high school students from the hackathon were invited to participate in this study through convenience sampling Participating students (n = 8) were allocated into three focus groups. Semi structured interviews were completed, and transcripts evaluated using inductive thematic analysis. FINDINGS: Through the structured analysis of focus group transcripts three major themes emerged from the data: (1) Collaboration, (2) Transferable knowledge and skills, and (3) Expectations about hackathons. These themes highlight strengths and potential barriers when bringing this multidisciplinary approach to high school students and the healthcare community. CONCLUSION: This study found that students were empowered by the interdisciplinary experience during a hackathon and felt that the knowledge and skills gained could be applied in real world settings. However, addressing student expectations of hackathons prior to the event is an area for improvement. These findings have implications for future hackathons and can spur further research into using the hackathon model as an educational experience for learners of all ages.

Guidelines and mHealth to Improve Quality of Hypertension and Type 2 Diabetes Care for Vulnerable Populations in Lebanon: Longitudinal Cohort Study.

BACKGROUND: Given the protracted nature of the crisis in Syria, the large noncommunicable disease (NCD) caseload of Syrian refugees and host Lebanese, and the high costs of providing NCD care, the implications for Lebanon's health system are vast. OBJECTIVE: The aim of this study was to evaluate the effectiveness of treatment guidelines and a mobile health (mHealth) app on quality of care and health outcomes in primary care settings in Lebanon. METHODS: A longitudinal cohort study was implemented from January 2015 to August 2016 to evaluate the effectiveness of treatment guidelines and an mHealth app on quality of care and health outcomes for Syrian and Lebanese patients in Lebanese primary health care (PHC) facilities. RESULTS: Compared with baseline record extraction, recording of blood pressure (BP) readings (-11.4%, P<.001) and blood sugar measurements (-6.9%, P=.03) significantly decreased following the implementation of treatment guidelines. Recording of BP readings also decreased after the mHealth phase as compared with baseline (-8.4%, P=.001); however, recording of body mass index (BMI) reporting increased at the end of the mHealth phase from baseline (8.1%, P<.001) and the guidelines phase (7.7%, P<.001). There were a great proportion of patients for whom blood sugar, BP, weight, height, and BMI were recorded using the tablet compared with in paper records; however, only differences in BMI were statistically significant (31.6% higher in app data as compared with paper records; P<.001). Data extracted from the mHealth app showed that a higher proportion of providers offered lifestyle counseling compared with the counseling reported in patients' paper records (health diet counseling; 77.3% in app data vs 8.8% in paper records, P<.001 and physical activity counseling and 59.7% in app vs 7.1% in paper records, P<.001). There were statistically significant increases in all four measures of patient-provider interaction across study phases. Provider inquiry of medical history increased by 16.6% from baseline following guideline implementation and by 28.2% from baseline to mHealth implementation (P<.001). From baseline, patient report of provider inquiry regarding medication complications increased in the guidelines and mHealth phases by 12.9% and 59.6%, respectively, (P<.001). The proportion of patients reporting that providers asked other questions relevant to their illness increased from baseline through guidelines implementation by 27.8% and to mHealth implementation by 66.3% (P<.001). Follow-up scheduling increased from baseline to the guidelines phase by 20.6% and the mHealth phase by 39.8% (P<.001). CONCLUSIONS: Results from this study of an mHealth app in 10 PHC facilities in Lebanon indicate that the app has potential to improve adherence to guidelines and quality of care. Further studies are necessary to determine the effects of patient-controlled health record apps on provider adherence to treatment guidelines, as well as patients' long-term medication and treatment adherence and disease control.

Pilot Testing and Implementation of a mHealth tool for Non-communicable Diseases in a Humanitarian Setting.

INTRODUCTION: Given the protracted nature of the crisis in Syria, national and international assistance agencies face immense challenges in providing for the needs of refugees and the host Lebanese due to the high burden of noncommunicable diseases (NCDs) among both populations. These are complex conditions to manage, and the resources for refugee care limited, having dramatic implications for Lebanon's health system. METHODS: A longitudinal cohort study was implemented from January 2015 through August 2016 to evaluate the effectiveness of treatment guidelines and an mHealth application on quality of care and health outcomes for patients in primary health care facilities in Lebanon serving Syrian refugees and host communities. RESULTS: Overall, reporting in clinic medical records remained low, however, during the mHealth phase recording of BMI and blood pressure were significantly greater in the mHealth application as compared to clinic medical records. Patient exit interviews reported a much more frequent measurement of weight, height, blood pressure, and blood glucose, suggesting these may be assessed more often than they are recorded. Satisfaction with the clinic visit improved significantly during implementation of the mHealth application as compared to both baseline and guidelines implementation in all measures. Despite positive changes, provider uptake of the application was low; patients indicated that the mHealth application was used in a minority (21.7%) of consultations. Provider perspectives on how the application changed patient interactions were mixed. DISCUSSION: Similar to previous evidence, this study further demonstrates the need to incorporate new interventions with existing practices and reporting requirements to minimize duplication of efforts and, consequently, strengthen provider usage. Additional research is needed to identify organizational and provider-side factors associated with uptake of similar applications, particularly in complex settings, to optimize the benefit of such tools.

The hackathon model to spur innovation around global mHealth.

The challenge of providing quality healthcare to underserved populations in low- and middle-income countries (LMICs) has attracted increasing attention from information and communication technology (ICT) professionals interested in providing societal impact through their work. Sana is an organisation hosted at the Institute for Medical Engineering and Science at the Massachusetts Institute of Technology that was established out of this interest. Over the past several years, Sana has developed a model of organising mobile health bootcamp and hackathon events in LMICs with the goal of encouraging increased collaboration between ICT and medical professionals and leveraging the growing prevalence of cellphones to provide health solutions in resource limited settings. Most recently, these events have been based in Colombia, Uganda, Greece and Mexico. The lessons learned from these events can provide a framework for others working to create sustainable health solutions in the developing world.

A "datathon" model to support cross-disciplinary collaboration.

In recent years, there has been a growing focus on the unreliability of published biomedical and clinical research. To introduce effective new scientific contributors to the culture of health care, we propose a "datathon" or "hackathon" model in which participants with disparate, but potentially synergistic and complementary, knowledge and skills effectively combine to address questions faced by clinicians. The continuous peer review intrinsically provided by follow-up datathons, which take up prior uncompleted projects, might produce more reliable research, either by providing a different perspective on the study design and methodology or by replication of prior analyses.