A systematic review of clinical health conditions predicted by machine learning diagnostic and prognostic models trained or validated using real-world primary health care data.

With the advances in technology and data science, machine learning (ML) is being rapidly adopted by the health care sector. However, there is a lack of literature addressing the health conditions targeted by the ML prediction models within primary health care (PHC) to date. To fill this gap in knowledge, we conducted a systematic review following the PRISMA guidelines to identify health conditions targeted by ML in PHC. We searched the Cochrane Library, Web of Science, PubMed, Elsevier, BioRxiv, Association of Computing Machinery (ACM), and IEEE Xplore databases for studies published from January 1990 to January 2022. We included primary studies addressing ML diagnostic or prognostic predictive models that were supplied completely or partially by real-world PHC data. Studies selection, data extraction, and risk of bias assessment using the prediction model study risk of bias assessment tool were performed by two investigators. Health conditions were categorized according to international classification of diseases (ICD-10). Extracted data were analyzed quantitatively. We identified 106 studies investigating 42 health conditions. These studies included 207 ML prediction models supplied by the PHC data of 24.2 million participants from 19 countries. We found that 92.4% of the studies were retrospective and 77.3% of the studies reported diagnostic predictive ML models. A majority (76.4%) of all the studies were for models' development without conducting external validation. Risk of bias assessment revealed that 90.8% of the studies were of high or unclear risk of bias. The most frequently reported health conditions were diabetes mellitus (19.8%) and Alzheimer's disease (11.3%). Our study provides a summary on the presently available ML prediction models within PHC. We draw the attention of digital health policy makers, ML models developer, and health care professionals for more future interdisciplinary research collaboration in this regard.

A scoping review of heart failure transitional care quality indicators and outcomes for use in clinical care and research.

AIMS: There are no accepted quality indicators for transitional care following hospitalization for heart failure (HF). Current quality measures focus on 30-day readmissions without accounting for competing risks such as death. In this scoping review of clinical trials, we aimed to develop a set of HF transitional care quality indicators for clinical or research applications following hospitalization for HF. METHODS AND RESULTS: We performed a scoping review using MEDLINE, Embase, CINAHL, HealthSTAR, reference lists and grey literature from January 1990 to November 2022. We included randomized controlled trials (RCTs) of adults hospitalized for HF who received a healthcare service or strategy intervention that aimed to improve patient-reported or clinical outcomes. We independently extracted data and performed a qualitative synthesis of the results. We generated a list of process, structure, patient-reported, and clinical measures that could be used as quality indicators. We highlighted process indicators that were associated with improved clinical outcomes and patient-reported outcomes that had high adherence to COnsensus-based Standards for the selection of health Measurement INstruments (COSMIN) and United States Food and Drug Administration standards. From 42 RCTs included in the study, we identified a set of process, structure, patient-reported, and clinical indicators that could be used as transitional care measures in clinical or research settings. CONCLUSION: In this scoping review, we developed a list of quality indicators that could guide clinical efforts or serve as research endpoints in transitional care in HF. Clinicians, researchers, institutions, and policymakers can use the indicators to guide management, design research, allocate resources, and fund services that improve clinical outcomes.

Patient-Reported Outcome Measures in Cardiovascular Disease: An Evidence Map of the Psychometric Properties of Health Status Instruments.

BACKGROUND: Patient-reported outcomes (PROs) are important measures of treatment effect and can be used to inform the approval of cardiovascular drugs and devices by the U.S. Food and Drug Administration (FDA). PURPOSE: To catalogue the health status patient-reported outcome measures (PROMs) validated in cardiovascular diseases (CVDs), describe their psychometric properties, and assess adherence with both FDA recommendations and the COnsensus-based Standards for the selection of health Measurement INstruments (COSMIN) framework. DATA SOURCES: MEDLINE, EMBASE, CINAHL, and Allied and Complementary Medicine Database from inception to August 2022. STUDY SELECTION: Studies that developed and/or validated health status PROMs in CVD populations. DATA EXTRACTION: Two study authors extracted data on CVD type, PROM psychometric properties, and adherence to FDA recommendations. The risk of bias informing the development or validation of PROMs was assessed using the COSMIN framework. DATA SYNTHESIS: Fifty health status PROMs (described in 83 studies) were identified, of which 45 were disease specific and 5 were generic. Eleven (22%) of the 50 PROMs validated in CVDs had minimally important differences (MIDs) established, and 8 (16%) reported on the validation of all psychometric properties recommended by the FDA. By COSMIN standards, only 2 PROMs (4%) had all of their psychometric properties rated as sufficient in quality, and 32 PROMs (64%) had less than 50% of psychometric properties rated as sufficient. LIMITATION: The quality of reporting varied across included studies. CONCLUSION: Of 50 PROMs validated in CVDs, only a small minority reported on the validation of all FDA-recommended psychometric properties, had psychometric properties rated as sufficient by COSMIN, or had MIDs established. Given the use of PROMs to guide FDA approvals of drugs and devices in CVDs, there is a need for better adherence to quality standards in PROM validation. PRIMARY FUNDING SOURCE: None.

Identifying and addressing conflicting results across multiple discordant systematic reviews on the same question: protocol for a replication study of the Jadad algorithm.

INTRODUCTION: An increasing growth of systematic reviews (SRs) presents notable challenges for decision-makers seeking to answer clinical questions. In 1997, an algorithm was created by Jadad to assess discordance in results across SRs on the same question. Our study aims to (1) replicate assessments done in a sample of studies using the Jadad algorithm to determine if the same SR would have been chosen, (2) evaluate the Jadad algorithm in terms of utility, efficiency and comprehensiveness, and (3) describe how authors address discordance in results across multiple SRs. METHODS AND ANALYSIS: We will use a database of 1218 overviews (2000-2020) created from a bibliometric study as the basis of our search for studies assessing discordance (called discordant reviews). This bibliometric study searched MEDLINE (Ovid), Epistemonikos and Cochrane Database of Systematic Reviews for overviews. We will include any study using Jadad (1997) or another method to assess discordance. The first 30 studies screened at the full-text stage by two independent reviewers will be included. We will replicate the authors' Jadad assessments. We will compare our outcomes qualitatively and evaluate the differences between our Jadad assessment of discordance and the authors' assessment. ETHICS AND DISSEMINATION: No ethics approval was required as no human subjects were involved. In addition to publishing in an open-access journal, we will disseminate evidence summaries through formal and informal conferences, academic websites, and across social media platforms. This is the first study to comprehensively evaluate and replicate Jadad algorithm assessments of discordance across multiple SRs.

Temporal Trends and Clinical Trial Characteristics Associated With the Inclusion of Women in Heart Failure Trial Steering Committees: A Systematic Review.

BACKGROUND: Trial steering committees (TSCs) steer the conduct of randomized controlled trials (RCTs). We examined the gender composition of TSCs in impactful heart failure RCTs and explored whether trial leadership by a woman was independently associated with the inclusion of women in TSCs. METHODS: We systematically searched MEDLINE, EMBASE, and CINAHL for heart failure RCTs published in journals with impact factor ≥10 between January 2000 and May 2019. We used the Jonckheere-Terpstra test to assess temporal trends and multivariable logistic regression to explore trial characteristics associated with TSC inclusion of women. RESULTS: Of 403 RCTs that met inclusion criteria, 127 (31.5%) reported having a TSC but 20 of these (15.7%) did not identify members. Among 107 TSCs that listed members, 56 (52.3%) included women and 6 of these (10.7%) restricted women members to the RCT leaders. Of 1213 TSC members, 11.1% (95% CI, 9.4%-13.0%) were women, with no change in temporal trends (P=0.55). Women had greater odds of TSC inclusion in RCTs led by women (adjusted odds ratio, 2.48 [95% CI, 1.05-8.72], P=0.042); this association was nonsignificant when analysis excluded TSCs that restricted women to the RCT leaders (adjusted odds ratio 1.46 [95% CI, 0.43-4.91], P=0.36). CONCLUSIONS: Women were included in 52.3% of TSCs and represented 11.1% of TSC members in 107 heart failure RCTs, with no change in trends since 2000. RCTs led by women had higher adjusted odds of including women in TSCs, partly due to the self-inclusion of RCT leaders in TSCs.

Barriers and facilitators of the uptake of digital health technology in cardiovascular care: a systematic scoping review.

Digital health technology (DHT) has the potential to revolutionize healthcare delivery but its uptake has been low in clinical and research settings. The factors that contribute to the limited adoption of DHT, particularly in cardiovascular settings, are unclear. The objective of this review was to determine the barriers and facilitators of DHT uptake from the perspective of patients, clinicians, and researchers. We searched MEDLINE, EMBASE, and CINAHL databases for studies published from inception to May 2020 that reported barriers and/or facilitators of DHT adoption in cardiovascular care. We extracted data on study design, setting, cardiovascular condition, and type of DHT. We conducted a thematic analysis to identify barriers and facilitators of DHT uptake. The search identified 3075 unique studies, of which 29 studies met eligibility criteria. Studies employed: qualitative methods (n = 13), which included interviews and focus groups; quantitative methods (n = 5), which included surveys; or a combination of qualitative and quantitative methods (n = 11). Twenty-five studies reported patient-level barriers, most common of which were difficult-to-use technology (n=7) and a poor internet connection (n=7). Six studies reported clinician-level barriers, which included increased workload (n=4) and a lack of integration with electronic medical records (n=3).Twenty-four studies reported patient-level facilitators, which included improved communication with clinicians (n=10) and personalized technology (n=6). Four studies reported clinician-level facilitators, which included approval and organizational support from cardiology departments and/or hospitals (n=3) and technologies that improved efficiency (n=3). No studies reported researcher-level barriers or facilitators. In summary, internet access, user-friendliness, organizational support, workflow efficiency, and data integration were reported as important factors in the uptake of DHT by patients and clinicians. These factors can be considered when selecting and implementing DHTs in cardiovascular clinical settings.

Postural orthostatic tachycardia syndrome (POTS) and other autonomic disorders after COVID-19 infection: a case series of 20 patients.

OBJECTIVE: To describe clinical features, diagnostic findings, treatments, and outcomes in patients with new-onset postural orthostatic tachycardia syndrome (POTS) and other autonomic disorders following SARS-CoV-2 infection (COVID-19). METHODS: We retrospectively reviewed medical records for patients who presented with persistent neurologic and cardiovascular complaints between April and December 2020 following COVID-19 infection. RESULTS: Twenty patients (70% female) were included in this study.Fifteen had POTS, 3 had neurocardiogenic syncope, and 2 had orthostatic hypotension. Six patients had abnormalities on cardiac or pulmonary testing, and 4 had elevated autoimmune or inflammatory markers. All patients were treated with non-pharmacologic therapies, and most required pharmacologic therapies. Six to 8 months after COVID-19, 17 (85%) patients had residual autonomic symptoms, with 12 (60%) unable to return to work. CONCLUSIONS: POTS can follow COVID-19 in previously healthy patients. Appropriate diagnostic investigations and therapies are necessary to identify and treat autonomic dysfunction after COVID-19.

Trial characteristics associated with under-enrolment of females in randomized controlled trials of heart failure with reduced ejection fraction: a systematic review.

AIMS: To evaluate temporal trends in the enrolment of females in randomized controlled trials (RCTs) of heart failure with reduced ejection fraction (HFrEF) published in high-impact journals, and assess RCT characteristics associated with under-enrolment. METHODS AND RESULTS: We searched MEDLINE, EMBASE and CINAHL for studies published from January 2000 to May 2019 in journals with impact factor ≥10. We included RCTs that recruited adults with HFrEF. We used a 20% threshold below the sex distribution of HFrEF to define under-enrolment. We used multivariable logistic regression to assess trial characteristics independently associated with under-enrolment. We included 317 RCTs. Among the 183 097 participants, mean (standard deviation) age was 63.0 (7.0) years and 25.5% were female. Females were under-enrolled in 71.6% [95% confidence interval (CI) 66.6-76.6%] of the RCTs; enrolment did not increase significantly between 2000-2019. Sex-related eligibility criteria [odds ratio (OR) 2.05, 95% CI 1.01-4.16; P = 0.046]; recruitment in ambulatory settings (OR 2.56, 95% CI 1.37-4.81; P = 0.003); trial coordination in North America (OR 4.44, 95% CI 1.09-18.07; P = 0.037), Europe (OR 6.79, 95% CI 1.63-27.39; P = 0.018) and Asia (OR 9.33, 95% CI 1.40-12.40; P = 0.033); drug (OR 1.76, 95% CI 1.96-7.36; P < 0.001) and device/surgical interventions (OR 1.69, 95% CI 1.16-9.43; P = 0.002); and men in first and last authorship position (OR 1.32, 95% CI 1.12-3.54; P = 0.047) were associated with under-enrolment of females. CONCLUSIONS: Females were under-enrolled relative to disease distribution in a majority of high-impact HFrEF RCTs, with no change in temporal trends between 2000 and 2019. Trial characteristics and gender of trial leaders were associated with under-enrolment.

Characteristics of Heart Failure Trials Associated With Under-Representation of Women as Lead Authors.

BACKGROUND: Clinical trials change practice in cardiology, and leading them requires research training, mentorship, sponsorship, and networking. Women report challenges in obtaining these opportunities. OBJECTIVES: The purpose of this review was to evaluate temporal trends in representation of women as authors in heart failure (HF) randomized controlled trials (RCTs) published in high-impact medical journals and explore RCT characteristics associated with women as lead authors. METHODS: We searched MEDLINE, EMBASE, and CINAHL for HF RCTs published in journals with an impact factor ≥10 between January 1, 2000, and May 7, 2019. We assessed temporal trends in the gender distribution of authors, and used multivariable logistic regression to determine characteristics associated with women as lead authors. RESULTS: We identified 10,596 unique articles, of which 403 RCTs met inclusion criteria. Women represented 15.6% (95% confidence interval [CI]: 12.2% to 19.6%), 12.9% (95% CI: 9.8% to 16.6%), and 11.4% (95% CI: 8.5% to 14.9%) of lead, senior, and corresponding authors, respectively. The proportion of women authors has not changed over time. Women had lower odds of lead authorship in RCTs that were multicenter (odds ratio [OR]: 0.58; 95% CI: 0.18 to 0.96; p = 0.037), were coordinated in North America (OR: 0.21; 95% CI: 0.08 to 0.70; p = 0.011) or Europe (OR: 0.33; 95% CI: 0.09 to 0.91; p = 0.039), tested drug interventions (OR: 0.42; 95% CI: 0.16 to 0.97; p = 0.043), or had men as the senior author (OR: 0.50; 95% CI: 0.21 to 0.93; p = 0.043). CONCLUSIONS: Women are under-represented as authors of HF RCTs, with no change in temporal trends. Women had lower odds of lead authorship in RCTs that were multicenter, were coordinated in North America or Europe, tested drug interventions, or had men as senior authors.

Applications of digital technology in COVID-19 pandemic planning and response.

With high transmissibility and no effective vaccine or therapy, COVID-19 is now a global pandemic. Government-coordinated efforts across the globe have focused on containment and mitigation, with varying degrees of success. Countries that have maintained low COVID-19 per-capita mortality rates appear to share strategies that include early surveillance, testing, contact tracing, and strict quarantine. The scale of coordination and data management required for effective implementation of these strategies has-in most successful countries-relied on adopting digital technology and integrating it into policy and health care. This Viewpoint provides a framework for the application of digital technologies in pandemic management and response, highlighting ways in which successful countries have adopted these technologies for pandemic planning, surveillance, testing, contact tracing, quarantine, and health care.

Transitional care quality indicators to assess quality of care following hospitalisation for chronic obstructive pulmonary disease and heart failure: a systematic review protocol.

INTRODUCTION: The period following hospitalisation for chronic obstructive pulmonary disease (COPD) or heart failure (HF)-when patients transition between settings and clinicians-is one of high risk. Transitional care services that bridge the gap from hospital to home can improve outcomes, but there are no widely accepted indicators to assess their quality. METHODS AND ANALYSIS: In this systematic review, we will summarise transitional care quality indicators, and describe their associations with clinical, patient-reported and cost outcomes. We will search MEDLINE, Embase, CINAHL and HealthSTAR, as well as grey literature and reference lists of included articles. We will screen all studies published between January 1990 and October 2019 that test an intervention that aims to improve the hospital-to-home transition for patients with COPD and/or HF; and measure at least one process (eg, medication errors), clinical (eg, hospital readmissions) or patient-reported (eg, health-related quality of life) outcome which will serve as a transitional care quality indicator . We will include randomised controlled trials, cohort studies, cross-sectional studies, interrupted time series studies and before-after studies. We will extract data in duplicate and classify transitional care quality indicators as structural, process-related or outcome-related. When possible, we will assess associations between transitional care quality indicators and clinical outcomes. In anticipation of conceptual and statistical heterogeneity, we will provide a qualitative synthesis and narrative review of the results. ETHICS AND DISSEMINATION: This review will provide a list of transitional care quality indicators and their associations with clinical outcomes. These results can be used by hospitals, administrators and clinicians for assessing the quality of transitional care provided to patients with COPD and HF. The findings can also be used by policy-makers to assess and incentivise transitional care quality. We will disseminate results through publications, social media releases and presentations. PROSPERO REGISTRATION NUMBER: This study is registered on PROSPERO.