Search

Background: While universal screening for Lipoprotein(a) [Lp(a)] is increasingly recommended, <0.5% of patients undergo Lp(a) testing. Here, we assessed the feasibility of deploying Algorithmic Risk Inspection for Screening Elevated Lp(a) (ARISE), a validated machine learning tool, to health system electronic health records to increase the yield of Lp(a) testing., Methods: We randomly sampled 100 000 patients from the Yale-New Haven Health System to evaluate the feasibility of ARISE deployment. We also evaluated Lp(a)-tested populations in the Yale-New Haven Health System (n=7981) and the Vanderbilt University Medical Center (n=10 635) to assess the association of ARISE score with elevated Lp(a). To compare the representativeness of the Lp(a)-tested population, we included 456 815 participants from the UK Biobank and 23 280 from 3 US-based cohorts of Atherosclerosis Risk in Communities, Coronary Artery Risk Development in Young Adults, and Multi-Ethnic Study of Atherosclerosis., Results: Among 100 000 randomly selected Yale-New Haven Health System patients, 413 (0.4%) had undergone Lp(a) measurement. ARISE score could be computed for 31 586 patients based on existing data, identifying 2376 (7.5%) patients with a high probability of elevated Lp(a). A positive ARISE score was associated with significantly higher odds of elevated Lp(a) in the Yale-New Haven Health System (odds ratio, 1.87 [95% CI, 1.65-2.12]) and the Vanderbilt University Medical Center (odds ratio, 1.41 [95% CI, 1.24-1.60]). The Lp(a)-tested population significantly differed from other study cohorts in terms of ARISE features., Conclusions: We demonstrate the feasibility of deployment of ARISE in US health systems to define the risk of elevated Lp(a), enabling a high-yield testing strategy. We also confirm the markedly low adoption of Lp(a) testing, which is also being restricted to a highly selected population., Competing Interests: Dr Khera is an Associate Editor at JAMA and receives research grant support, through Yale, from Bristol-Myers Squibb, Novo Nordisk, and BridgeBio. He is a coinventor of US Pending Patent Applications WO2023230345A1, US20220336048A1, 63/346,610, 63/484,426, 63/508,315, 63/580,137, 63/606,203, 63/619,241, 63/562,335 and 18/813,882, unrelated to the current work. He also receives support from the Blavatnik Foundation through the Blavatnik Fund for Innovation at Yale. Dr Khera is a cofounder of Ensight-AI, and both Dr Khera and Dr Oikonomou are cofounders of Evidence2Health, which are precision health platforms to improve evidence-based cardiovascular care. Dr Oikonomou is a coinventor of US Patent Applications 18/813882, 17/720068, 63/619241, 63/177117, 63/580137, 63/606203, 63/562335, US11948230B2, and US20210374951A1, and has served as a consultant to Caristo Diagnostics, Ltd (Oxford, UK), unrelated to the current work. The other authors report no conflicts. more...

Importance: Serial functional status assessments are critical to heart failure (HF) management but are often described narratively in documentation, limiting their use in quality improvement or patient selection for clinical trials., Objective: To develop and validate a deep learning natural language processing (NLP) strategy for extracting functional status assessments from unstructured clinical documentation., Design, Setting, and Participants: This diagnostic study used electronic health record data collected from January 1, 2013, through June 30, 2022, from patients diagnosed with HF seeking outpatient care within 3 large practice networks in Connecticut (Yale New Haven Hospital [YNHH], Northeast Medical Group [NMG], and Greenwich Hospital [GH]). Expert-annotated notes were used for NLP model development and validation. Data were analyzed from February to April 2024., Exposures: Development and validation of NLP models to detect explicit New York Heart Association (NYHA) classification, HF symptoms during activity or rest, and frequency of functional status assessments., Main Outcomes and Measures: Outcomes of interest were model performance metrics, including area under the receiver operating characteristic curve (AUROC), and frequency of NYHA class documentation and HF symptom descriptions in unannotated notes., Results: This study included 34 070 patients with HF (mean [SD] age 76.1 [12.6] years; 17 728 [52.0]% female). Among 3000 expert-annotated notes (2000 from YNHH and 500 each from NMG and GH), 374 notes (12.4%) mentioned NYHA class and 1190 notes (39.7%) described HF symptoms. The NYHA class detection model achieved a class-weighted AUROC of 0.99 (95% CI, 0.98-1.00) at YNHH, the development site. At the 2 validation sites, NMG and GH, the model achieved class-weighted AUROCs of 0.98 (95% CI, 0.96-1.00) and 0.98 (95% CI, 0.92-1.00), respectively. The model for detecting activity- or rest-related symptoms achieved an AUROC of 0.94 (95% CI, 0.89-0.98) at YNHH, 0.94 (95% CI, 0.91-0.97) at NMG, and 0.95 (95% CI, 0.92-0.99) at GH. Deploying the NYHA model among 182 308 unannotated notes from the 3 sites identified 23 830 (13.1%) notes with NYHA mentions, specifically 10 913 notes (6.0%) with class I, 12 034 notes (6.6%) with classes II or III, and 883 notes (0.5%) with class IV. An additional 19 730 encounters (10.8%) could be classified into functional status groups based on activity- or rest-related symptoms, resulting in a total of 43 560 medical notes (23.9%) categorized by NYHA, an 83% increase compared with explicit mentions alone., Conclusions and Relevance: In this diagnostic study of 34 070 patients with HF, the NLP approach accurately extracted a patient's NYHA symptom class and activity- or rest-related HF symptoms from clinical notes, enhancing the ability to track optimal care delivery and identify patients eligible for clinical trial participation from unstructured documentation. more...

Aims: Despite notable population differences in high-income and low- and middle-income countries (LMICs), national guidelines in LMICs often recommend using US-based cardiovascular disease (CVD) risk scores for treatment decisions. We examined the performance of widely used international CVD risk scores within the largest Brazilian community-based cohort study (Brazilian Longitudinal Study of Adult Health, ELSA-Brasil)., Methods: All adults 40-75 years from ELSA-Brasil (2008-2013) without prior CVD who were followed for incident, adjudicated CVD events (fatal and non-fatal MI, stroke, or coronary heart disease death). We evaluated 5 scores-Framingham General Risk (FGR), Pooled Cohort Equations (PCEs), WHO CVD score, Globorisk-LAC and the Systematic Coronary Risk Evaluation 2 score (SCORE-2). We assessed their discrimination using the area under the receiver operating characteristic curve (AUC) and calibration with predicted-to-observed risk (P/O) ratios-overall and by sex/race groups., Results: There were 12 155 individuals (53.0±8.2 years, 55.3% female) who suffered 149 incident CVD events. All scores had a model AUC>0.7 overall and for most age/sex groups, except for white women, where AUC was <0.6 for all scores, with higher overestimation in this subgroup. All risk scores overestimated CVD risk with 32%-170% overestimation across scores. PCE and FGR had the highest overestimation (P/O ratio: 2.74 (95% CI 2.42 to 3.06)) and 2.61 (95% CI 1.79 to 3.43)) and the recalibrated WHO score had the best calibration (P/O ratio: 1.32 (95% CI 1.12 to 1.48))., Conclusion: In a large prospective cohort from Brazil, we found that widely accepted CVD risk scores overestimate risk by over twofold, and have poor risk discrimination particularly among Brazilian women. Our work highlights the value of risk stratification strategies tailored to the unique populations and risks of LMICs., Competing Interests: Competing interests: RK is an Associate Editor at JAMA. In addition to the funding listed above, he also receives research support, through Yale, from Bristol-Myers Squibb, Novo Nordisk and BridgeBio. He is a coinventor of Pending Patent Applications WO2023230345A1, US20220336048A1, 63/346 610, 63/484 426, 63/508 315, 63/580 137, 63/606 203, 63/619 241 and 63/562 335, unrelated to current work. He is also a co-founder of Evidence2Health and Ensight-AI, both representing precision health platforms to improve evidence-based cardiovascular care. The other authors declare no conflicts of interest., (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.) more...

Aims: An algorithmic strategy for anatomical vs. functional testing in suspected coronary artery disease (CAD) (Anatomical vs. Stress teSting decIsion Support Tool; ASSIST) is associated with better outcomes than random selection. However, in the real world, this decision is rarely random. We explored the agreement between a provider-driven vs. simulated algorithmic approach to cardiac testing and its association with outcomes across multinational cohorts., Methods and Results: In two cohorts of functional vs. anatomical testing in a US hospital health system [Yale; 2013-2023; n = 130 196 (97.0%) vs. n = 4020 (3.0%), respectively], and the UK Biobank [ n = 3320 (85.1%) vs. n = 581 (14.9%), respectively], we examined outcomes stratified by agreement between the real-world and ASSIST-recommended strategies. Younger age, female sex, Black race, and diabetes history were independently associated with lower odds of ASSIST-aligned testing. Over a median of 4.9 (interquartile range [IQR]: 2.4-7.1) and 5.4 (IQR: 2.6-8.8) years, referral to the ASSIST-recommended strategy was associated with a lower risk of acute myocardial infarction or death (hazard ratio adjusted : 0.81, 95% confidence interval [CI] 0.77-0.85, P < 0.001 and 0.74 [95% CI 0.60-0.90], P = 0.003, respectively), an effect that remained significant across years, test types, and risk profiles. In post hoc analyses of anatomical-first testing in the Prospective Multicentre Imaging Study for Evaluation of Chest Pain (PROMISE) trial, alignment with ASSIST was independently associated with a 17% and 30% higher risk of detecting CAD in any vessel or the left main artery/proximal left anterior descending coronary artery, respectively., Conclusion: In cohorts where historical practices largely favour functional testing, alignment with an algorithmic approach to cardiac testing defined by ASSIST was associated with a lower risk of adverse outcomes. This highlights the potential utility of a data-driven approach in the diagnostic management of CAD., Competing Interests: Conflict of interest: E.K.O. is a co-inventor in patent applications (US17/720,068, 63/619,241, 63/177,117, 63/580,137, 63/606,203, 63/562,335, WO2018078395A1, and WO2020058713A1), has been a consultant for Caristo Diagnostics Ltd and Ensight-AI Inc, and received royalty fees for technology licensed through the University of Oxford related to computed tomography phenotyping of cardiometabolic risk. E.K.O. and R.K. are academic cofounders of Evidence2Health, a health data analytics company. R.K. is an associate editor of JAMA. He receives research support through Yale, from Bristol-Myers Squibb, Novo Nordisk, and BridgeBio. He is a co-inventor of US Provisional Patent Applications 63/177,117, 63/428,569, 63/346,610, 63/484,426, 63/508,315, 63/606,203, 63/619,241, 63/562,335 and co-founder of Ensight-AI, Inc. H.M.K. works under contract with the Centers for Medicare & Medicaid Services to support quality measurement programmes, was a recipient of a research grant from Johnson & Johnson, through Yale University, to support clinical trial data sharing; was a recipient of a research agreement, through Yale University, from the Shenzhen Center for Health Information for work to advance intelligent disease prevention and health promotion; collaborates with the National Center for Cardiovascular Diseases in Beijing; receives payment from the Arnold & Porter Law Firm for work related to the Sanofi clopidogrel litigation, from the Martin Baughman Law Firm for work related to the Cook Celect IVC filter litigation, and from the Siegfried and Jensen Law Firm for work related to Vioxx litigation; chairs a Cardiac Scientific Advisory Board for UnitedHealth; was a member of the IBM Watson Health Life Sciences Board; is a member of the Advisory Board for Element Science, the Advisory Board for Facebook, and the Physician Advisory Board for Aetna; and is the co-founder of Hugo Health, a personal health information platform, and co-founder of Refactor Health, a healthcare AI-augmented data management company, and Ensight-AI, Inc. All other authors declare no relevant competing interests., (© The Author(s) 2024. Published by Oxford University Press on behalf of the European Society of Cardiology.) more...

Importance: Despite efforts to improve the quality of care for patients with atherosclerotic cardiovascular disease (ASCVD), it is unclear whether the US has made progress in reducing racial and ethnic differences in utilization of guideline-recommended therapies for secondary prevention., Objective: To evaluate 21-year trends in racial and ethnic differences in utilization of guideline-recommended pharmacological medications and lifestyle modifications among US adults with ASCVD., Design, Setting, and Participants: This cross-sectional study includes data from the National Health and Nutrition Examination Survey between 1999 and 2020. Eligible participants were adults aged 18 years or older with a history of ASCVD. Data were analyzed between March 2022 and May 2023., Exposure: Self-reported race and ethnicity., Main Outcome and Measures: Rates and racial and ethnic differences in the use of guideline-recommended pharmacological medications and lifestyle modifications., Results: The study included 5218 adults with a history of ASCVD (mean [SD] age, 65.5 [13.2] years, 2148 women [weighted average, 44.2%]), among whom 1170 (11.6%) were Black, 930 (7.7%) were Hispanic or Latino, and 3118 (80.7%) were White in the weighted sample. Between 1999 and 2020, there was a significant increase in total cholesterol control and statin use in all racial and ethnic subgroups, and in angiotensin-converting enzyme inhibitor (ACEI) and angiotensin receptor blocker (ARB) utilization in non-Hispanic White individuals and Hispanic and Latino individuals (Hispanic and Latino individuals: 17.12 percentage points; 95% CI, 0.37-37.88 percentage points; P = .046; non-Hispanic White individuals: 12.14 percentage points; 95% CI, 6.08-18.20 percentage points; P < .001), as well as smoking cessation within the Hispanic and Latino population (-27.13 percentage points; 95% CI, -43.14 to -11.12 percentage points; P = .002). During the same period, the difference in smoking cessation between Hispanic and Latino individuals and White individuals was reduced (-24.85 percentage points; 95% CI, -38.19 to -11.51 percentage points; P < .001), but racial and ethnic differences for other metrics did not change significantly. Notably, substantial gaps persisted between current care and optimal care throughout the 2 decades of data analyzed. In the period of 2017 to 2020, optimal regimens were observed in 47.4% (95% CI, 39.3%-55.4%), 48.7% (95% CI, 36.7%-60.6%), and 53.0% (95% CI, 45.6%-60.4%) of Black, Hispanic and Latino, and White individuals, respectively., Conclusions and Relevance: In this cross-sectional study of US adults with ASCVD, significant disparities persisted between current care and optimal care, surpassing any differences observed among demographic groups. These findings highlight the critical need for sustained efforts to bridge these gaps and achieve better outcomes for all patients, regardless of their racial and ethnic backgrounds. more...

Objective: To assess the uptake of second line antihyperglycaemic drugs among patients with type 2 diabetes mellitus who are receiving metformin., Design: Federated pharmacoepidemiological evaluation in LEGEND-T2DM., Setting: 10 US and seven non-US electronic health record and administrative claims databases in the Observational Health Data Sciences and Informatics network in eight countries from 2011 to the end of 2021., Participants: 4.8 million patients (≥18 years) across US and non-US based databases with type 2 diabetes mellitus who had received metformin monotherapy and had initiated second line treatments., Exposure: The exposure used to evaluate each database was calendar year trends, with the years in the study that were specific to each cohort., Main Outcomes Measures: The outcome was the incidence of second line antihyperglycaemic drug use (ie, glucagon-like peptide-1 receptor agonists, sodium-glucose cotransporter-2 inhibitors, dipeptidyl peptidase-4 inhibitors, and sulfonylureas) among individuals who were already receiving treatment with metformin. The relative drug class level uptake across cardiovascular risk groups was also evaluated., Results: 4.6 million patients were identified in US databases, 61 382 from Spain, 32 442 from Germany, 25 173 from the UK, 13 270 from France, 5580 from Scotland, 4614 from Hong Kong, and 2322 from Australia. During 2011-21, the combined proportional initiation of the cardioprotective antihyperglycaemic drugs (glucagon-like peptide-1 receptor agonists and sodium-glucose cotransporter-2 inhibitors) increased across all data sources, with the combined initiation of these drugs as second line drugs in 2021 ranging from 35.2% to 68.2% in the US databases, 15.4% in France, 34.7% in Spain, 50.1% in Germany, and 54.8% in Scotland. From 2016 to 2021, in some US and non-US databases, uptake of glucagon-like peptide-1 receptor agonists and sodium-glucose cotransporter-2 inhibitors increased more significantly among populations with no cardiovascular disease compared with patients with established cardiovascular disease. No data source provided evidence of a greater increase in the uptake of these two drug classes in populations with cardiovascular disease compared with no cardiovascular disease., Conclusions: Despite the increase in overall uptake of cardioprotective antihyperglycaemic drugs as second line treatments for type 2 diabetes mellitus, their uptake was lower in patients with cardiovascular disease than in people with no cardiovascular disease over the past decade. A strategy is needed to ensure that medication use is concordant with guideline recommendations to improve outcomes of patients with type 2 diabetes mellitus., Competing Interests: Competing interests: This study is undertaken within Observational Health Data Sciences and Informatics, an open collaboration. RK received support from the National Heart, Lung, and Blood Institute of the National Institutes of Health (under award K23HL153775) and the Doris Duke Charitable Foundation (under award, 2022060). He is an Associate Editor of JAMA. He also receives research support, through Yale, from Bristol-Myers Squibb. He is a coinventor of US Provisional Patent Applications 63/177,117 and 63/346,610, unrelated to current work. He is also a founder of Evidence2Health, a precision health platform to improve evidence-based cardiovascular care. TD-S acknowledges receiving financial support from the Instituto de Salud Carlos III (ISCIII; Miguel Servet 2021: CP21/00023). KKCM reports grants from C W Maplethorpe Fellowship, grants from National Institute of Health Research, UK, grants from European Commission Framwork Horizon 2020, grants from Hong Kong Research Grant Council, grants from Innovation and Technology Commission of the Hong Kong Special Administration Region Government, and personal fees from IQVIA outside of the submitted work. DRM was supported by a Wellcome Trust Clinical Research Fellowship (214588/Z/18/Z). MJS is an employee and shareholder of Johnson & Johnson. HK received expenses and/or personal fees from UnitedHealth, Element Science, Aetna, Reality Labs, Tesseract/4Catalyst, F-Prime, the Siegfried and Jensen Law Firm, Arnold and Porter Law Firm, and Martin/Baughman Law Firm. He is a co-founder of Refactor Health and HugoHealth, and is associated with contracts, through Yale New Haven Hospital, from the Centers for Medicare and Medicaid Services and through Yale University from Johnson & Johnson. MAS receives contracts and grants from the National Institutes of Health, the US Department of Veterans Affairs, the US Food and Drug Administration and Janssen Research and Development, the latter two of which are outside the scope of this work. Other authors declare no competing interests., (© Author(s) (or their employer(s)) 2023. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.) more...

Background: Smartphone-based health applications are increasingly popular, but their real-world use for cardiovascular risk management remains poorly understood., Objectives: The purpose of this study was to investigate the patterns of tracking health goals using smart devices, including smartphones and/or tablets, in the United States., Methods: Using the nationally representative Health Information National Trends Survey for 2017 to 2020, we examined self-reported tracking of health-related goals (optimizing body weight, increasing physical activity, and/or quitting smoking) using smart devices among those with cardiovascular disease (CVD) or cardiovascular risk factors of hypertension, diabetes, obesity, and/or smoking. Survey analyses were used to obtain national estimates of use patterns and identify features associated with the use of these devices for tracking health goals., Results: Of 16,092 Health Information National Trends Survey participants, 10,660 had CVD or cardiovascular risk factors, representing 154.2 million (95% CI: 149.2-159.3 million) U.S. adults. Among the general U.S. adult population, 46% (95% CI: 44%-47%) tracked their health goals using their smart devices, compared with 42% (95% CI: 40%-43%) of those with or at risk of CVD. Younger age, female, Black race, higher educational attainment, and greater income were independently associated with tracking of health goals using smart devices., Conclusions: Two in 5 U.S. adults with or at risk of CVD use their smart devices to track health goals. While representing a potential avenue to improve care, the lower use of smart devices among older and low-income individuals, who are at higher risk of adverse cardiovascular outcomes, requires that digital health interventions are designed so as not to exacerbate existing disparities. more...

Background: Left ventricular (LV) systolic dysfunction is associated with a >8-fold increased risk of heart failure and a 2-fold risk of premature death. The use of ECG signals in screening for LV systolic dysfunction is limited by their availability to clinicians. We developed a novel deep learning-based approach that can use ECG images for the screening of LV systolic dysfunction., Methods: Using 12-lead ECGs plotted in multiple different formats, and corresponding echocardiographic data recorded within 15 days from the Yale New Haven Hospital between 2015 and 2021, we developed a convolutional neural network algorithm to detect an LV ejection fraction <40%. The model was validated within clinical settings at Yale New Haven Hospital and externally on ECG images from Cedars Sinai Medical Center in Los Angeles, CA; Lake Regional Hospital in Osage Beach, MO; Memorial Hermann Southeast Hospital in Houston, TX; and Methodist Cardiology Clinic of San Antonio, TX. In addition, it was validated in the prospective Brazilian Longitudinal Study of Adult Health. Gradient-weighted class activation mapping was used to localize class-discriminating signals on ECG images., Results: Overall, 385 601 ECGs with paired echocardiograms were used for model development. The model demonstrated high discrimination across various ECG image formats and calibrations in internal validation (area under receiving operation characteristics [AUROCs], 0.91; area under precision-recall curve [AUPRC], 0.55); and external sets of ECG images from Cedars Sinai (AUROC, 0.90 and AUPRC, 0.53), outpatient Yale New Haven Hospital clinics (AUROC, 0.94 and AUPRC, 0.77), Lake Regional Hospital (AUROC, 0.90 and AUPRC, 0.88), Memorial Hermann Southeast Hospital (AUROC, 0.91 and AUPRC 0.88), Methodist Cardiology Clinic (AUROC, 0.90 and AUPRC, 0.74), and Brazilian Longitudinal Study of Adult Health cohort (AUROC, 0.95 and AUPRC, 0.45). An ECG suggestive of LV systolic dysfunction portended >27-fold higher odds of LV systolic dysfunction on transthoracic echocardiogram (odds ratio, 27.5 [95% CI, 22.3-33.9] in the held-out set). Class-discriminative patterns localized to the anterior and anteroseptal leads (V 2 and V 3 ), corresponding to the left ventricle regardless of the ECG layout. A positive ECG screen in individuals with an LV ejection fraction ≥40% at the time of initial assessment was associated with a 3.9-fold increased risk of developing incident LV systolic dysfunction in the future (hazard ratio, 3.9 [95% CI, 3.3-4.7]; median follow-up, 3.2 years)., Conclusions: We developed and externally validated a deep learning model that identifies LV systolic dysfunction from ECG images. This approach represents an automated and accessible screening strategy for LV systolic dysfunction, particularly in low-resource settings., Competing Interests: Disclosures Dr Mortazavi reported receiving grants from the National Institute of Biomedical Imaging and Bioengineering, National Heart, Lung, and Blood Institute, US Food and Drug Administration, and the US Department of Defense Advanced Research Projects Agency outside the submitted work; in addition, Dr Mortazavi has a pending patent on predictive models using electronic health records (US20180315507A1). Dr A.H. Ribeiro is funded by the Kjell och Märta Beijer Foundation. Dr Krumholz works under contract with the Centers for Medicare & Medicaid Services to support quality measurement programs, was a recipient of a research grant from Johnson & Johnson, through Yale University, to support clinical trial data sharing; was a recipient of a research agreement, through Yale University, from the Shenzhen Center for Health Information for work to advance intelligent disease prevention and health promotion; collaborates with the National Center for Cardiovascular Diseases in Beijing; receives payment from the Arnold & Porter Law Firm for work related to the Sanofi clopidogrel litigation, from the Martin Baughman Law Firm for work related to the Cook Celect IVC filter litigation, and from the Siegfried and Jensen Law Firm for work related to Vioxx litigation; chairs a cardiac scientific advisory board for UnitedHealth; was a member of the IBM Watson Health Life Sciences board; is a member of the advisory board for element science, the advisory board for Facebook, and the physician advisory board for Aetna; and is co-founder of Hugo Health, a personal health information platform, and co-founder of Refactor Health, a health care artificial intelligence–augmented data management company. Dr A.L.P. Ribeiro is supported in part by CNPq (465518/2014-1, 310790/2021-2, and 409604/2022-4) and by FAPEMIG (PPM-00428-17, RED-00081-16, and PPE-00030-21). V. Sangha and Dr Khera are the coinventors of US provisional patent application No. 63/346,610, “Articles and methods for format-independent detection of hidden cardiovascular disease from printed electrocardiographic images using deep learning.” Dr Khera receives support from the National Heart, Lung, and Blood Institute of the National Institutes of Health (under award K23HL153775) and the Doris Duke Charitable Foundation (under award 2022060). He receives support from the Blavatnik Foundation through the Blavatnik fund for innovation at Yale. He also receives research support, through Yale, from Bristol-Myers Squibb, and Novo Nordisk. He is an associate editor for JAMA. In addition to 63/346,610, Dr Khera is a coinventor of US provisional patent applications 63/177,117, 63/428,569, and 63/484,426. He is also a founder of Evidence2Health, a precision health platform to improve evidence-based cardiovascular care. more...

Artificial intelligence (AI) can detect left ventricular systolic dysfunction (LVSD) from electrocardiograms (ECGs). Wearable devices could allow for broad AI-based screening but frequently obtain noisy ECGs. We report a novel strategy that automates the detection of hidden cardiovascular diseases, such as LVSD, adapted for noisy single-lead ECGs obtained on wearable and portable devices. We use 385,601 ECGs for development of a standard and noise-adapted model. For the noise-adapted model, ECGs are augmented during training with random gaussian noise within four distinct frequency ranges, each emulating real-world noise sources. Both models perform comparably on standard ECGs with an AUROC of 0.90. The noise-adapted model performs significantly better on the same test set augmented with four distinct real-world noise recordings at multiple signal-to-noise ratios (SNRs), including noise isolated from a portable device ECG. The standard and noise-adapted models have an AUROC of 0.72 and 0.87, respectively, when evaluated on ECGs augmented with portable ECG device noise at an SNR of 0.5. This approach represents a novel strategy for the development of wearable-adapted tools from clinical ECG repositories., (© 2023. The Author(s).) more...

Importance: Wearable devices may be able to improve cardiovascular health, but the current adoption of these devices could be skewed in ways that could exacerbate disparities., Objective: To assess sociodemographic patterns of use of wearable devices among adults with or at risk for cardiovascular disease (CVD) in the US population in 2019 to 2020., Design, Setting, and Participants: This population-based cross-sectional study included a nationally representative sample of the US adults from the Health Information National Trends Survey (HINTS). Data were analyzed from June 1 to November 15, 2022., Exposures: Self-reported CVD (history of heart attack, angina, or congestive heart failure) and CVD risk factors (≥1 risk factor among hypertension, diabetes, obesity, or cigarette smoking)., Main Outcomes and Measures: Self-reported access to wearable devices, frequency of use, and willingness to share health data with clinicians (referred to as health care providers in the survey)., Results: Of the overall 9303 HINTS participants representing 247.3 million US adults (mean [SD] age, 48.8 [17.9] years; 51% [95% CI, 49%-53%] women), 933 (10.0%) representing 20.3 million US adults had CVD (mean [SD] age, 62.2 [17.0] years; 43% [95% CI, 37%-49%] women), and 5185 (55.7%) representing 134.9 million US adults were at risk for CVD (mean [SD] age, 51.4 [16.9] years; 43% [95% CI, 37%-49%] women). In nationally weighted assessments, an estimated 3.6 million US adults with CVD (18% [95% CI, 14%-23%]) and 34.5 million at risk for CVD (26% [95% CI, 24%-28%]) used wearable devices compared with an estimated 29% (95% CI, 27%-30%) of the overall US adult population. After accounting for differences in demographic characteristics, cardiovascular risk factor profile, and socioeconomic features, older age (odds ratio [OR], 0.35 [95% CI, 0.26-0.48]), lower educational attainment (OR, 0.35 [95% CI, 0.24-0.52]), and lower household income (OR, 0.42 [95% CI, 0.29-0.60]) were independently associated with lower use of wearable devices in US adults at risk for CVD. Among wearable device users, a smaller proportion of adults with CVD reported using wearable devices every day (38% [95% CI, 26%-50%]) compared with overall (49% [95% CI, 45%-53%]) and at-risk (48% [95% CI, 43%-53%]) populations. Among wearable device users, an estimated 83% (95% CI, 70%-92%) of US adults with CVD and 81% (95% CI, 76%-85%) at risk for CVD favored sharing wearable device data with their clinicians to improve care., Conclusions and Relevance: Among individuals with or at risk for CVD, fewer than 1 in 4 use wearable devices, with only half of those reporting consistent daily use. As wearable devices emerge as tools that can improve cardiovascular health, the current use patterns could exacerbate disparities unless there are strategies to ensure equitable adoption. more...

Objective: Nonexercise algorithms are cost-effective methods to estimate cardiorespiratory fitness (CRF), but the existing models have limitations in generalizability and predictive power. This study aims to improve the nonexercise algorithms using machine learning (ML) methods and data from US national population surveys., Materials and Methods: We used the 1999-2004 data from the National Health and Nutrition Examination Survey (NHANES). Maximal oxygen uptake (VO2 max), measured through a submaximal exercise test, served as the gold standard measure for CRF in this study. We applied multiple ML algorithms to build 2 models: a parsimonious model using commonly available interview and examination data, and an extended model additionally incorporating variables from Dual-Energy X-ray Absorptiometry (DEXA) and standard laboratory tests in clinical practice. Key predictors were identified using Shapley additive explanation (SHAP)., Results: Among the 5668 NHANES participants in the study population, 49.9% were women and the mean (SD) age was 32.5 years (10.0). The light gradient boosting machine (LightGBM) had the best performance across multiple types of supervised ML algorithms. Compared with the best existing nonexercise algorithms that could be applied to the NHANES, the parsimonious LightGBM model (RMSE: 8.51 ml/kg/min [95% CI: 7.73-9.33]) and the extended LightGBM model (RMSE: 8.26 ml/kg/min [95% CI: 7.44-9.09]) significantly reduced the error by 15% and 12% (P < .001 for both), respectively., Discussion: The integration of ML and national data source presents a novel approach for estimating cardiovascular fitness. This method provides valuable insights for cardiovascular disease risk classification and clinical decision-making, ultimately leading to improved health outcomes., Conclusion: Our nonexercise models provide improved accuracy in estimating VO2 max within NHANES data as compared to existing nonexercise algorithms., (© The Author(s) 2023. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.) more...

Objectives: Antimicrobial resistance (AMR) is the next big pandemic that threatens humanity. The One Health approach to AMR requires quantification of interactions between health, demographic, socioeconomic, environmental, and geopolitical factors to design interventions. This study is focused on learning health system factors on global AMR., Methods: This study analysed longitudinal data (2004-2017) of AMR having 6 33 820 isolates from 70 middle and high-income countries. We integrated AMR data with the Global Burden of Disease (GBD), Governance (WGI), and Finance data sets to find AMR's unbiased and actionable determinants. We chose a Bayesian decision network (BDN) approach within the causal modelling framework to quantify determinants of AMR. Further, we integrated Bayesian networks' global knowledge discovery approach with discriminative machine learning to predict individual-level antibiotic susceptibility in patients., Results: From MAR (multiple antibiotic resistance) scores, we found a non-uniform spread pattern of AMR. Components-level analysis revealed that governance, finance, and disease burden variables strongly correlate with AMR. From the Bayesian network analysis, we found that access to immunization, obstetric care, and government effectiveness are strong, actionable factors in reducing AMR, confirmed by what-if analysis. Finally, our discriminative machine learning models achieved an individual-level AUROC (Area under receiver operating characteristic curve) of 0.94 (SE = 0.01) and 0.89 (SE = 0.002) to predict Staphylococcus aureus resistance to ceftaroline and oxacillin, respectively., Conclusion: Causal machine learning revealed that immunisation strategies and quality of governance are vital, actionable interventions to reduce AMR., (Copyright © 2022. Published by Elsevier Ltd.) more...

The COVID-19 pandemic has revealed the power of internet disinformation in influencing global health. The deluge of information travels faster than the epidemic itself and is a threat to the health of millions across the globe. Health apps need to leverage machine learning for delivering the right information while constantly learning misinformation trends and deliver these effectively in vernacular languages in order to combat the infodemic at the grassroot levels in the general public. Our application, WashKaro, is a multi-pronged intervention that uses conversational Artificial Intelligence (AI), machine translation, and natural language processing to combat misinformation (NLP). WashKaro uses AI to provide accurate information matched against WHO recommendations and delivered in an understandable format in local languages. The primary aim of this study was to assess the use of neural models for text summarization and machine learning for delivering WHO matched COVID-19 information to mitigate the misinfodemic. The secondary aim of this study was to develop a symptom assessment tool and segmentation insights for improving the delivery of information. A total of 5026 people downloaded the app during the study window; among those, 1545 were actively engaged users. Our study shows that 3.4 times more females engaged with the App in Hindi as compared to males, the relevance of AI-filtered news content doubled within 45 days of continuous machine learning, and the prudence of integrated AI chatbot "Satya" increased thus proving the usefulness of a mHealth platform to mitigate health misinformation. We conclude that a machine learning application delivering bite-sized vernacular audios and conversational AI is a practical approach to mitigate health misinformation., (© 2022. The Author(s).) more...

Poor hypertension awareness and underuse of guideline-recommended medications are critical factors contributing to poor hypertension control. Using data from 8095 hypertensive people aged ≥18 years from the National Health and Nutrition Examination Survey (2011-2018), we examined recent trends in racial and ethnic differences in awareness and antihypertensive medication use, and their association with racial and ethnic differences in hypertension control. Between 2011 and 2018, age-adjusted hypertension awareness declined for Black, Hispanic, and White individuals, but the 3 outcomes increased or did not change for Asian individuals. Compared with White individuals, Black individuals had a similar awareness (odds ratio, 1.20 [0.96-1.45]) and overall treatment rates (1.04 [0.84-1.25]), and received more intensive antihypertensive medication if treated (1.41 [1.27-1.56]), but had a lower control rate (0.72 [0.61-0.83]). Asian and Hispanic individuals had significantly lower awareness rates (0.69 [0.52-0.85] and 0.74 [0.59-0.89]), overall treatment rates (0.72 [0.57-0.88] and 0.69 [0.55-0.82]), received less intensive medication if treated (0.60 [0.50-0.72] and 0.86 [0.75-0.96]), and had lower control rates (0.66 [0.54-0.79] and 0.69 [0.57-0.81]). The racial and ethnic differences in awareness, treatment, and control persisted over the study period and were consistent across age, sex, and income strata. Lower awareness and treatment were significantly associated with lower control in Asian and Hispanic individuals ( P <0.01 for all) but not in Black individuals. These findings highlight the need for interventions to improve awareness and treatment among Asian and Hispanic individuals, and more investigation into the downstream factors that may contribute to the poor hypertension control among Black individuals. more...

Background: Teleneurology consultations can be highly advantageous since neurological diseases and disabilities often limit patient's access to health care, particularly in a setting where they need to travel long distances for specialty consults. Patient satisfaction is an important outcome assessing success of a telemedicine program. Materials and Methods: A cross-sectional study was conducted to determine satisfaction and perception of patients toward an audio call based teleneurology follow-up initiated during the coronavirus disease 2019 pandemic. Primary outcomes were satisfaction to tele-consult, and proportion of patients preferring telemedicine for future follow-up. Results: A total of 261 patients who received tele-consult were enrolled. Satisfaction was highest for domain technological quality, followed by patient-physician dialogue (PPD) and least to quality of care (QoC). Median (interquartile range) patient satisfaction on a 5-point Likert scale was 4 (3-5). Eighty-five (32.6%; 95% confidence interval 26.9-38.6%) patients preferred telemedicine for future follow-up. Higher overall satisfaction was associated with health condition being stable/better, change in treatment advised on tele-consult, diagnosis not requiring follow-up examination, higher scores on domains QoC and PPD ( p  < 0.05). Future preference for telemedicine was associated with patient him-/herself consulting with doctor, less duration of follow-up, higher overall satisfaction, and higher scores on domain QoC ( p  < 0.05). On thematic analysis, telemedicine was found convenient, reduced expenditure, and had better physician attention; in-person visits were comprehensive, had better patient-physician relationship, and better communication. Discussion: Patient satisfaction was lower in our study than what has been observed earlier, which may be explained by the primitive nature of our platform. Several variables related to the patients' disease process have an effect on patient satisfaction. Conclusion: Development of robust, structured platforms is necessary to fully utilize the potential of telemedicine in developing countries., Competing Interests: No competing financial interests exist., (© Mudit Agarwal et al., 2021; Published by Mary Ann Liebert, Inc.) more...

Proactive detection of hemodynamic shock can prevent organ failure and save lives. Thermal imaging is a non-invasive, non-contact modality to capture body surface temperature with the potential to reveal underlying perfusion disturbance in shock. In this study, we automate early detection and prediction of shock using machine learning upon thermal images obtained in a pediatric intensive care unit of a tertiary care hospital. 539 images were recorded out of which 253 had concomitant measurement of continuous intra-arterial blood pressure, the gold standard for shock monitoring. Histogram of oriented gradient features were used for machine learning based region-of-interest segmentation that achieved 96% agreement with a human expert. The segmented center-to-periphery difference along with pulse rate was used in longitudinal prediction of shock at 0, 3, 6 and 12 hours using a generalized linear mixed-effects model. The model achieved a mean area under the receiver operating characteristic curve of 75% at 0 hours (classification), 77% at 3 hours (prediction) and 69% at 12 hours (prediction) respectively. Since hemodynamic shock associated with critical illness and infectious epidemics such as Dengue is often fatal, our model demonstrates an affordable, non-invasive, non-contact and tele-diagnostic decision support system for its reliable detection and prediction. more...