Barriers to Optimal Clinician Guideline Adherence in Management of Markedly Elevated Blood Pressure: A Qualitative Study.

IMPORTANCE: Hypertension poses a substantial public health challenge. Despite clinical practice guidelines for hypertension management, clinician adherence to these guidelines remains suboptimal. OBJECTIVE: To develop a taxonomy of suboptimal adherence scenarios for severe hypertension and identify barriers to guideline adherence. DESIGN, SETTING, and PARTICIPANTS: This qualitative content analysis using electronic health records (EHRs) of Yale New Haven Health System included participants who had at least 2 consecutive visits with markedly elevated blood pressure (BP; defined as at least 2 consecutive readings of systolic BP ≥160 mm Hg and diastolic BP ≥100 mm Hg) between January 1, 2013, and December 31, 2021, and no prescription for antihypertensive medication within a 90 days of the second BP measurement. Data analysis was conducted from January to December 2023. MAIN OUTCOMES AND MEASURES: The primary outcome was scenarios and influencing factors contributing to clinician nonadherence to the guidelines for hypertension management. A thematic analysis of EHR data was conducted to generate a pragmatic taxonomy of scenarios of suboptimal clinician guideline adherence in the management of severe hypertension. RESULTS: Of the 20 654 patients who met criteria, 200 were randomly selected and thematic saturation was reached after analyzing 100 patients (mean [SD] age at index visit, 66.5 [12.8] years; 50 female [50%]; 8 Black [8%]; 5 Hispanic or Latino [5%]; 85 White [85%]). Three content domains emerged: (1) clinician-related scenarios (defined as noninitiation or nonintensification of treatment due to issues relating to clinician intention, capability, or scope), which included 2 subcategories (did not address and diffusion of responsibility); (2) patient-related scenarios (defined as noninitiation or nonintensification of treatment due to patient behavioral considerations), which included 2 subcategories (patient nonadherence and patient preference); and (3) clinical complexity-related scenarios (defined as noninitiation or nonintensification of treatment due to clinical situational complexities), which included 3 subcategories (diagnostic uncertainty, maintenance of current intervention, and competing medical priorities). CONCLUSIONS AND RELEVANCE: In this qualitative study of EHR data, a taxonomy of suboptimal adherence scenarios for severe hypertension was developed and barriers to guideline adherence were identified. This pragmatic taxonomy lays the foundation for developing targeted interventions to improve clinician adherence to guidelines and patient outcomes.

Benchmarking Emergency Physician EHR Time per Encounter Based on Patient and Clinical Factors.

This cross-sectional study assesses the associations between patient and clinical factors and variations in time emergency department physicians spend using electronic health record (EHR) systems.

Modernizing the Data Infrastructure for Clinical Research to Meet Evolving Demands for Evidence.

Importance: The ways in which we access, acquire, and use data in clinical trials have evolved very little over time, resulting in a fragmented and inefficient system that limits the amount and quality of evidence that can be generated. Observations: Clinical trial design has advanced steadily over several decades. Yet the infrastructure for clinical trial data collection remains expensive and labor intensive and limits the amount of evidence that can be collected to inform whether and how interventions work for different patient populations. Meanwhile, there is increasing demand for evidence from randomized clinical trials to inform regulatory decisions, payment decisions, and clinical care. Although substantial public and industry investment in advancing electronic health record interoperability, data standardization, and the technology systems used for data capture have resulted in significant progress on various aspects of data generation, there is now a need to combine the results of these efforts and apply them more directly to the clinical trial data infrastructure. Conclusions and Relevance: We describe a vision for a modernized infrastructure that is centered around 2 related concepts. First, allowing the collection and rigorous evaluation of multiple data sources and types and, second, enabling the possibility to reuse health data for multiple purposes. We address the need for multidisciplinary collaboration and suggest ways to measure progress toward this goal.

Trends in use of intensive care during hospitalizations at the end-of-life among older adults with advanced cancer.

BACKGROUND: High-intensity end-of-life (EOL) care, marked by admission to intensive care units (ICUs) or in-hospital death, can be costly and burdensome. Recent trends in use of ICUs, life-sustaining treatments (LSTs), and noninvasive ventilation (NIV) during EOL hospitalizations among older adults with advanced cancer and patterns of in-hospital death are unknown. METHODS: We used SEER-Medicare data (2003-2017) to identify beneficiaries with advanced solid cancer (summary stage 7) who died within 3 years of diagnosis. We identified EOL hospitalizations (within 30 days of death), classifying them by increasing intensity of care into: (1) without ICU; (2) with ICU but without LST (invasive mechanical ventilation, tracheostomy, gastrostomy, acute dialysis) or NIV; (3) with ICU and NIV but without LST; and (4) with ICU and LST use. We constructed a multinomial regression model to evaluate trends in risk-adjusted hospitalization, overall and across hospitalization categories, adjusting for sociodemographics, cancer characteristics, comorbidities, and frailty. We evaluated trends in in-hospital death across categories. RESULTS: Of 226,263 Medicare beneficiaries with advanced cancer, 138,305 (61.1%) were hospitalized at EOL [Age, Mean (SD):77.9(7.1) years; 45.5% female]. Overall, EOL hospitalizations remained high throughout, from 78.1% (95% CI: 77.4, 78.7) in 2004 to 75.5% (95% CI: 74.5, 76.2) in 2017. Hospitalizations without ICU use decreased from 49.3% (95% CI: 48.5, 50.2) to 35.0% (95% CI: 34.2, 35.9) while hospitalizations with more intensive care increased, from 23.7% (95% CI: 23.0, 24.4) to 28.7% (95% CI: 27.9, 29.5) for ICU without LST or NIV, 0.8% (95% CI: 0.6, 0.9) to 3.8% (95% CI: 3.4, 4.1) for ICU with NIV but without LST, and 4.3% (95% CI: 4.0, 4.7) to 8.0% (95% CI: 7.5, 8.5) for ICU with LST use. Among those who experienced in-hospital death, the proportion receiving ICU care increased from 46.5% to 65.0%. CONCLUSIONS: Among older adults with advanced cancer, EOL hospitalization rates remained stable from 2004-2017. However, intensity of care during EOL hospitalizations increased as evidenced by increasing use of ICUs, LSTs, and NIV.

Learning implementation of a guideline based decision support system to improve hypertension treatment in primary care in China: pragmatic cluster randomised controlled trial.

OBJECTIVE: To evaluate the effectiveness of a clinical decision support system (CDSS) in improving the use of guideline accordant antihypertensive treatment in primary care settings in China. DESIGN: Pragmatic, open label, cluster randomised trial. SETTING: 94 primary care practices in four urban regions of China between August 2019 and July 2022: Luoyang (central China), Jining (east China), and Shenzhen (south China, including two regions). PARTICIPANTS: 94 practices were randomised (46 to CDSS, 48 to usual care). 12 137 participants with hypertension who used up to two classes of antihypertensives and had a systolic blood pressure <180 mm Hg and diastolic blood pressure <110 mm Hg were included. INTERVENTIONS: Primary care practices were randomised to use an electronic health record based CDSS, which recommended a specific guideline accordant regimen for initiation, titration, or switching of antihypertensive (the intervention), or to use the same electronic health record without CDSS and provide treatment as usual (control). MAIN OUTCOME MEASURES: The primary outcome was the proportion of hypertension related visits during which an appropriate (guideline accordant) treatment was provided. Secondary outcomes were the average reduction in systolic blood pressure and proportion of participants with controlled blood pressure (<140/90 mm Hg) at the last scheduled follow-up. Safety outcomes were patient reported antihypertensive treatment related events, including syncope, injurious fall, symptomatic hypotension or systolic blood pressure <90 mm Hg, and bradycardia. RESULTS: 5755 participants with 23 113 visits in the intervention group and 6382 participants with 27 868 visits in the control group were included. Mean age was 61 (standard deviation 13) years and 42.5% were women. During a median 11.6 months of follow-up, the proportion of visits at which appropriate treatment was given was higher in the intervention group than in the control group (77.8% (17 975/23 113) v 62.2% (17 328/27 868); absolute difference 15.2 percentage points (95% confidence interval (CI) 10.7 to 19.8); P<0.001; odds ratio 2.17 (95% CI 1.75 to 2.69); P<0.001). Compared with participants in the control group, those in the intervention group had a 1.6 mm Hg (95% CI -2.7 to -0.5) greater reduction in systolic blood pressure (-1.5 mm Hg v 0.3 mm Hg; P=0.006) and a 4.4 percentage point (95% CI -0.7 to 9.5) improvement in blood pressure control rate (69.0% (3415/4952) v 64.6% (3778/5845); P=0.07). Patient reported antihypertensive treatment related adverse effects were rare in both groups. CONCLUSIONS: Use of a CDSS in primary care in China improved the provision of guideline accordant antihypertensive treatment and led to a modest reduction in blood pressure. The CDSS offers a promising approach to delivering better care for hypertension, both safely and efficiently. TRIAL REGISTRATION: ClinicalTrials.gov NCT03636334.

Tirzepatide and blood pressure reduction: stratified analyses of the SURMOUNT-1 randomised controlled trial.

BACKGROUND: Treating obesity may be a pathway to prevent and control hypertension. In the SURMOUNT-1 trial in people with obesity or overweight with weight-related complications, 72-week tirzepatide treatment led to clinically meaningful body weight and blood pressure reduction. Post hoc analyses were conducted to further explore the effects of tirzepatide on the pattern of blood pressure reduction and whether the effects were consistent across various subgroups. METHODS: The mixed effect for repeated measure model was used to compare changes in overall blood pressure, across demographic and clinical subgroups, baseline blood pressure subgroups and hypertension categories between SURMOUNT-1 participants randomised to treatment with tirzepatide and placebo. The association between weight changes and blood pressure and adverse events associated with low blood pressure were also evaluated by mediation analysis. RESULTS: Tirzepatide treatment was associated with a rapid decline in systolic and diastolic blood pressure over the first 24 weeks, followed by blood pressure stabilisation until the end of the observation period, resulting in a significant net reduction by 72 weeks of 6.8 mm Hg systolic and 4.2 mm Hg diastolic blood pressure versus placebo. Participants randomly assigned to any tirzepatide group were more likely than those assigned to placebo to have normal blood pressure at week 72 (58.0% vs 35.2%, respectively). The effects were broadly consistent across baseline blood pressure subgroups, shifting the blood pressure distribution curve to lower blood pressure levels. The mediation analysis indicated that weight loss explained 68% of the systolic and 71% of the diastolic blood pressure reduction. Low blood pressure adverse events were infrequent, but the rate was higher in the tirzepatide group. CONCLUSIONS: In these post hoc analyses, in participants with obesity or overweight, tirzepatide was associated with reduced blood pressure consistently across participant groups primarily via weight loss, with relatively few blood pressure-related adverse events. TRIAL REGISTRATION NUMBER: NCT04184622.

Altmetric Attention Scores and Citations of Published Research With or Without Preprints.

This cross-sectional study assesses how frequently research articles published in the clinical journals with high impact factors are preprinted and whether preprinting is associated with changes in media attention and citation counts.

Internal tremors and vibrations in long COVID: a cross-sectional study.

BACKGROUND: Internal tremors and vibrations are symptoms previously described as part of neurologic disorders but not fully described as a part of long COVID. This study compared pre-pandemic comorbidities, new-onset conditions, and long COVID symptoms between people with internal tremors and vibrations as part of their long COVID symptoms and people with long COVID but without these symptoms. METHODS: The Yale Listen to Immune, Symptom and Treatment Experiences Now (LISTEN) Study surveyed 423 adults who had long COVID between May 12, 2022 and June 1, 2023. The exposure variable was long COVID symptoms of internal tremors and vibrations. The outcome variables were demographic characteristics, pre-pandemic comorbidities, new-onset conditions, other symptoms, and quality of life. RESULTS: Among study participants with long COVID, median age was 46 years [IQR, 38-56]), 74% were female, 87% were Non-Hispanic White, and 158 (37%) reported "internal tremors, or buzzing/vibration" as a long COVID symptom. The 2 groups reported similar pre-pandemic comorbidities, but people with internal tremors reported worse health as measured by the Euro-QoL visual analogue scale (median: 40 points [IQR, 30-60] vs. 50 points [IQR, 35-62], P = 0.007) and had higher rates of new-onset mast cell disorders (11% [95% CI, 7.1-18] vs. 2.6% [1.2-5.6], P = 0.008) and neurologic conditions (22% [95% CI, 16-29] vs. 8.3% [5.4-12], P = 0.004). CONCLUSIONS: Among people with long COVID, those with internal tremors and vibrations had different conditions and symptoms and worse health status compared with others who had long COVID without these symptoms.

Using Artificial Intelligence to Predict Heart Failure Risk from Single-lead Electrocardiographic Signals: A Multinational Assessment.

Importance: Despite the availability of disease-modifying therapies, scalable strategies for heart failure (HF) risk stratification remain elusive. Portable devices capable of recording single-lead electrocardiograms (ECGs) can enable large-scale community-based risk assessment. Objective: To evaluate an artificial intelligence (AI) algorithm to predict HF risk from noisy single-lead ECGs. Design: Multicohort study. Setting: Retrospective cohort of individuals with outpatient ECGs in the integrated Yale New Haven Health System (YNHHS) and prospective population-based cohorts of UK Biobank (UKB) and Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). Participants: Individuals without HF at baseline. Exposures: AI-ECG-defined risk of left ventricular systolic dysfunction (LVSD). Main Outcomes and Measures: Among individuals with ECGs, we isolated lead I ECGs and deployed a noise-adapted AI-ECG model trained to identify LVSD. We evaluated the association of the model probability with new-onset HF, defined as the first HF hospitalization. We compared the discrimination of AI-ECG against the pooled cohort equations to prevent HF (PCP-HF) score for new-onset HF using Harrel's C-statistic, integrated discrimination improvement (IDI), and net reclassification improvement (NRI). Results: There were 194,340 YNHHS patients (age 56 years [IQR, 41-69], 112,082 women [58%]), 42,741 UKB participants (65 years [59-71], 21,795 women [52%]), and 13,454 ELSA-Brasil participants (56 years [41-69], 7,348 women [55%]) with baseline ECGs. A total of 3,929 developed HF in YNHHS over 4.5 years (2.6-6.6), 46 in UKB over 3.1 years (2.1-4.5), and 31 in ELSA-Brasil over 4.2 years (3.7-4.5). A positive AI-ECG screen was associated with a 3- to 7-fold higher risk for HF, and each 0.1 increment in the model probability portended a 27-65% higher hazard across cohorts, independent of age, sex, comorbidities, and competing risk of death. AI-ECG's discrimination for new-onset HF was 0.725 in YNHHS, 0.792 in UKB, and 0.833 in ELSA-Brasil. Across cohorts, incorporating AI-ECG predictions in addition to PCP-HF resulted in improved Harrel's C-statistic (Δ=0.112-0.114), with an IDI of 0.078-0.238 and an NRI of 20.1%-48.8% for AI-ECG vs. PCP-HF. Conclusions and Relevance: Across multinational cohorts, a noise-adapted AI model with lead I ECGs as the sole input defined HF risk, representing a scalable portable and wearable device-based HF risk-stratification strategy.

Real-world evaluation of an algorithmic machine-learning-guided testing approach in stable chest pain: a multinational, multicohort study.

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 ratioadjusted: 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.

Social Determinants of Health and Delivery of Rehabilitation to Older Adults During ICU Hospitalization.

Importance: Older adults with socioeconomic disadvantage develop a greater burden of disability after critical illness than those without socioeconomic disadvantage. The delivery of in-hospital rehabilitation that can mitigate functional decline may be influenced by social determinants of health (SDOH). Whether rehabilitation delivery differs by SDOH during critical illness hospitalization is not known. Objective: To evaluate whether SDOH are associated with the delivery of skilled rehabilitation during critical illness hospitalization among older adults. Design, Setting, and Participants: This cohort study used data from the National Health and Aging Trends Study linked with Medicare claims (2011-2018). Participants included older adults hospitalized with a stay in the intensive care unit (ICU). Data were analyzed from August 2022 to September 2023. Exposures: Dual eligibility for Medicare and Medicaid, education, income, limited English proficiency (LEP), and rural residence. Main Outcome and Measures: The primary outcome was delivery of physical therapy (PT) and/or occupational therapy (OT) during ICU hospitalization, characterized as any in-hospital PT or OT and rate of in-hospital PT or OT, calculated as total number of units divided by length of stay. Results: In the sample of 1618 ICU hospitalizations (median [IQR] patient age, 81.0 [75.0-86.0] years; 842 [52.0%] female), 371 hospitalizations (22.9%) were among patients with dual Medicare and Medicaid eligibility, 523 hospitalizations (32.6%) were among patients with less than high school education, 320 hospitalizations (19.8%) were for patients with rural residence, and 56 hospitalizations (3.5%) were among patients with LEP. A total of 1076 hospitalized patients (68.5%) received any PT or OT, with a mean rate of 0.94 (95% CI, 0.86-1.02) units/d. After adjustment for age, sex, prehospitalization disability, mechanical ventilation, and organ dysfunction, factors associated with lower odds of receipt of PT or OT included dual Medicare and Medicaid eligibility (adjusted odds ratio, 0.70 [95% CI, 0.50-0.97]) and rural residence (adjusted odds ratio, 0.65 [95% CI, 0.48-0.87]). LEP was associated with a lower rate of PT or OT (adjusted rate ratio, 0.55 [95% CI, 0.32-0.94]). Conclusions and Relevance: These findings highlight the need to consider SDOH in efforts to promote rehabilitation delivery during ICU hospitalization and to investigate factors underlying inequities in this practice.

The PAX LC Trial: A Decentralized, Phase 2, Randomized, Double-Blind Study of Nirmatrelvir/Ritonavir Compared with Placebo/Ritonavir for Long COVID.

BACKGROUND: Individuals with long COVID lack evidence-based treatments and have difficulty participating in traditional site-based trials. Our digital, decentralized trial investigates the efficacy and safety of nirmatrelvir/ritonavir, targeting viral persistence as a potential cause of long COVID. METHODS: The PAX LC trial (NCT05668091) is a Phase 2, 1:1 randomized, double-blind, superiority, placebo-controlled trial in 100 community-dwelling, highly symptomatic adult participants with long COVID residing in the 48 contiguous US states to determine the efficacy, safety, and tolerability of 15 days of nirmatrelvir/ritonavir compared with placebo/ritonavir. Participants are recruited via patient groups, cultural ambassadors, and social media platforms. Medical records are reviewed through a platform facilitating participant-mediated data acquisition from electronic health records nationwide. During the drug treatment, participants complete daily digital diaries using a web-based application. Blood draws for eligibility and safety assessments are conducted at or near participants' homes. The study drug is shipped directly to participants' homes. The primary endpoint is the PROMIS-29 Physical Health Summary Score difference between baseline and Day 28, evaluated by a mixed model repeated measure analysis. Secondary endpoints include PROMIS-29 (Mental Health Summary Score and all items), Modified GSQ-30 with supplemental symptoms questionnaire, COVID Core Outcome Measures for Recovery, EQ-5D-5L (Utility Score and all items), PGIS 1 and 2, PGIC 1 and 2, and healthcare utilization. The trial incorporates immunophenotyping to identify long COVID biomarkers and treatment responders. CONCLUSION: The PAX LC trial uses a novel decentralized design and a participant-centric approach to test a 15-day regimen of nirmatrelvir/ritonavir for long COVID.

Factors Associated with Long COVID Recovery among US Adults.

BACKGROUND: While factors associated with long COVID (LC) continue to be illuminated, little is known about recovery. This study used national survey data to assess factors associated with recovery from LC. METHODS: We used data from the 2022 National Health Interview Survey, a cross-sectional sample of noninstitutionalized US adults. Survey analysis was used to account for oversampling and nonresponse bias and to obtain nationally representative estimates. A multivariable logistic regression model was used to identify potential predictors of LC recovery. RESULTS: Among those reporting ever having COVID-19, 17.7% or an estimated 17.5 million American adults reported ever having LC, and among those with LC, 48.5% or an estimated 8.5 million reported having recovered. Multivariable logistic regression analysis showed that Hispanic adults were significantly more likely than White adults to report recovery from LC. At the same time, those with severe COVID-19 symptoms and those who had more than a high school degree, were aged 40 years or older, or were female were less likely to report recovery. CONCLUSION: Significant variations in LC recovery were noted across age, sex, race and ethnicity, education, and severity of COVID-19 symptoms. Further work is needed to elucidate the causes of these differences and identify strategies to increase recovery rates.

Hypertension Trends and Disparities Over 12 Years in a Large Health System: Leveraging the Electronic Health Records.

BACKGROUND: The digital transformation of medical data enables health systems to leverage real-world data from electronic health records to gain actionable insights for improving hypertension care. METHODS AND RESULTS: We performed a serial cross-sectional analysis of outpatients of a large regional health system from 2010 to 2021. Hypertension was defined by systolic blood pressure ≥140 mm Hg, diastolic blood pressure ≥90 mm Hg, or recorded treatment with antihypertension medications. We evaluated 4 methods of using blood pressure measurements in the electronic health record to define hypertension. The primary outcomes were age-adjusted prevalence rates and age-adjusted control rates. Hypertension prevalence varied depending on the definition used, ranging from 36.5% to 50.9% initially and increasing over time by ≈5%, regardless of the definition used. Control rates ranged from 61.2% to 71.3% initially, increased during 2018 to 2019, and decreased during 2020 to 2021. The proportion of patients with a hypertension diagnosis ranged from 45.5% to 60.2% initially and improved during the study period. Non-Hispanic Black patients represented 25% of our regional population and consistently had higher prevalence rates, higher mean systolic and diastolic blood pressure, and lower control rates compared with other racial and ethnic groups. CONCLUSIONS: In a large regional health system, we leveraged the electronic health record to provide real-world insights. The findings largely reflected national trends but showed distinctive regional demographics and findings, with prevalence increasing, one-quarter of the patients not controlled, and marked disparities. This approach could be emulated by regional health systems seeking to improve hypertension care.

A Multimodal Video-Based AI Biomarker for Aortic Stenosis Development and Progression.

Importance: Aortic stenosis (AS) is a major public health challenge with a growing therapeutic landscape, but current biomarkers do not inform personalized screening and follow-up. A video-based artificial intelligence (AI) biomarker (Digital AS Severity index [DASSi]) can detect severe AS using single-view long-axis echocardiography without Doppler characterization. Objective: To deploy DASSi to patients with no AS or with mild or moderate AS at baseline to identify AS development and progression. Design, Setting, and Participants: This is a cohort study that examined 2 cohorts of patients without severe AS undergoing echocardiography in the Yale New Haven Health System (YNHHS; 2015-2021) and Cedars-Sinai Medical Center (CSMC; 2018-2019). A novel computational pipeline for the cross-modal translation of DASSi into cardiac magnetic resonance (CMR) imaging was further developed in the UK Biobank. Analyses were performed between August 2023 and February 2024. Exposure: DASSi (range, 0-1) derived from AI applied to echocardiography and CMR videos. Main Outcomes and Measures: Annualized change in peak aortic valve velocity (AV-Vmax) and late (>6 months) aortic valve replacement (AVR). Results: A total of 12 599 participants were included in the echocardiographic study (YNHHS: n = 8798; median [IQR] age, 71 [60-80] years; 4250 [48.3%] women; median [IQR] follow-up, 4.1 [2.4-5.4] years; and CSMC: n = 3801; median [IQR] age, 67 [54-78] years; 1685 [44.3%] women; median [IQR] follow-up, 3.4 [2.8-3.9] years). Higher baseline DASSi was associated with faster progression in AV-Vmax (per 0.1 DASSi increment: YNHHS, 0.033 m/s per year [95% CI, 0.028-0.038] among 5483 participants; CSMC, 0.082 m/s per year [95% CI, 0.053-0.111] among 1292 participants), with values of 0.2 or greater associated with a 4- to 5-fold higher AVR risk than values less than 0.2 (YNHHS: 715 events; adjusted hazard ratio [HR], 4.97 [95% CI, 2.71-5.82]; CSMC: 56 events; adjusted HR, 4.04 [95% CI, 0.92-17.70]), independent of age, sex, race, ethnicity, ejection fraction, and AV-Vmax. This was reproduced across 45 474 participants (median [IQR] age, 65 [59-71] years; 23 559 [51.8%] women; median [IQR] follow-up, 2.5 [1.6-3.9] years) undergoing CMR imaging in the UK Biobank (for participants with DASSi ≥0.2 vs those with DASSi <.02, adjusted HR, 11.38 [95% CI, 2.56-50.57]). Saliency maps and phenome-wide association studies supported associations with cardiac structure and function and traditional cardiovascular risk factors. Conclusions and Relevance: In this cohort study of patients without severe AS undergoing echocardiography or CMR imaging, a new AI-based video biomarker was independently associated with AS development and progression, enabling opportunistic risk stratification across cardiovascular imaging modalities as well as potential application on handheld devices.

A Deep Learning Approach for Automated Extraction of Functional Status and New York Heart Association Class for Heart Failure Patients During Clinical Encounters.

Introduction: 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. We developed and validated a deep learning-based natural language processing (NLP) strategy to extract functional status assessments from unstructured clinical notes. Methods: We identified 26,577 HF patients across outpatient services at Yale New Haven Hospital (YNHH), Greenwich Hospital (GH), and Northeast Medical Group (NMG) (mean age 76.1 years; 52.0% women). We used expert annotated notes from YNHH for model development/internal testing and from GH and NMG for external validation. The primary outcomes were NLP models to detect (a) explicit New York Heart Association (NYHA) classification, (b) HF symptoms during activity or rest, and (c) functional status assessment frequency. Results: Among 3,000 expert-annotated notes, 13.6% mentioned NYHA class, and 26.5% described HF symptoms. The model to detect NYHA classes achieved a class-weighted AUROC of 0.99 (95% CI: 0.98-1.00) at YNHH, 0.98 (0.96-1.00) at NMG, and 0.98 (0.92-1.00) at GH. The activity-related HF symptom model achieved an AUROC of 0.94 (0.89-0.98) at YNHH, 0.94 (0.91-0.97) at NMG, and 0.95 (0.92-0.99) at GH. Deploying the NYHA model among 166,655 unannotated notes from YNHH identified 21,528 (12.9%) with NYHA mentions and 17,642 encounters (10.5%) classifiable into functional status groups based on activity-related symptoms. Conclusions: We developed and validated an NLP approach to extract NYHA classification and activity-related HF symptoms from clinical notes, enhancing the ability to track optimal care and identify trial-eligible patients.

Scalable Risk Stratification for Heart Failure Using Artificial Intelligence applied to 12-lead Electrocardiographic Images: A Multinational Study.

Background: Current risk stratification strategies for heart failure (HF) risk require either specific blood-based biomarkers or comprehensive clinical evaluation. In this study, we evaluated the use of artificial intelligence (AI) applied to images of electrocardiograms (ECGs) to predict HF risk. Methods: Across multinational longitudinal cohorts in the integrated Yale New Haven Health System (YNHHS) and in population-based UK Biobank (UKB) and Brazilian Longitudinal Study of Adult Health (ELSA-Brasil), we identified individuals without HF at baseline. Incident HF was defined based on the first occurrence of an HF hospitalization. We evaluated an AI-ECG model that defines the cross-sectional probability of left ventricular dysfunction from a single image of a 12-lead ECG and its association with incident HF. We accounted for the competing risk of death using the Fine-Gray subdistribution model and evaluated the discrimination using Harrel's c-statistic. The pooled cohort equations to prevent HF (PCP-HF) were used as a comparator for estimating incident HF risk. Results: Among 231,285 individuals at YNHHS, 4472 had a primary HF hospitalization over 4.5 years (IQR 2.5-6.6) of follow-up. In UKB and ELSA-Brasil, among 42,741 and 13,454 people, 46 and 31 developed HF over a follow-up of 3.1 (2.1-4.5) and 4.2 (3.7-4.5) years, respectively. A positive AI-ECG screen portended a 4-fold higher risk of incident HF among YNHHS patients (age-, sex-adjusted HR [aHR] 3.88 [95% CI, 3.63-4.14]). In UKB and ELSA-Brasil, a positive-screen ECG portended 13- and 24-fold higher hazard of incident HF, respectively (aHR: UKBB, 12.85 [6.87-24.02]; ELSA-Brasil, 23.50 [11.09-49.81]). The association was consistent after accounting for comorbidities and the competing risk of death. Higher model output probabilities were progressively associated with a higher risk for HF. The model's discrimination for incident HF was 0.718 in YNHHS, 0.769 in UKB, and 0.810 in ELSA-Brasil. Across cohorts, incorporating model probability with PCP-HF yielded a significant improvement in discrimination over PCP-HF alone. Conclusions: An AI model applied to images of 12-lead ECGs can identify those at elevated risk of HF across multinational cohorts. As a digital biomarker of HF risk that requires just an ECG image, this AI-ECG approach can enable scalable and efficient screening for HF risk.

Artificial intelligence-guided detection of under-recognized cardiomyopathies on point-of-care cardiac ultrasound: a multi-center study.

Background: Point-of-care ultrasonography (POCUS) enables cardiac imaging at the bedside and in communities but is limited by abbreviated protocols and variation in quality. We developed and tested artificial intelligence (AI) models to automate the detection of underdiagnosed cardiomyopathies from cardiac POCUS. Methods: In a development set of 290,245 transthoracic echocardiographic videos across the Yale-New Haven Health System (YNHHS), we used augmentation approaches and a customized loss function weighted for view quality to derive a POCUS-adapted, multi-label, video-based convolutional neural network (CNN) that discriminates HCM (hypertrophic cardiomyopathy) and ATTR-CM (transthyretin amyloid cardiomyopathy) from controls without known disease. We evaluated the final model across independent, internal and external, retrospective cohorts of individuals who underwent cardiac POCUS across YNHHS and Mount Sinai Health System (MSHS) emergency departments (EDs) (2011-2024) to prioritize key views and validate the diagnostic and prognostic performance of single-view screening protocols. Findings: We identified 33,127 patients (median age 61 [IQR: 45-75] years, n=17,276 [52·2%] female) at YNHHS and 5,624 (57 [IQR: 39-71] years, n=1,953 [34·7%] female) at MSHS with 78,054 and 13,796 eligible cardiac POCUS videos, respectively. An AI-enabled single-view screening approach successfully discriminated HCM (AUROC of 0·90 [YNHHS] & 0·89 [MSHS]) and ATTR-CM (YNHHS: AUROC of 0·92 [YNHHS] & 0·99 [MSHS]). In YNHHS, 40 (58·0%) HCM and 23 (47·9%) ATTR-CM cases had a positive screen at median of 2·1 [IQR: 0·9-4·5] and 1·9 [IQR: 1·0-3·4] years before clinical diagnosis. Moreover, among 24,448 participants without known cardiomyopathy followed over 2·2 [IQR: 1·1-5·8] years, AI-POCUS probabilities in the highest (vs lowest) quintile for HCM and ATTR-CM conferred a 15% (adj.HR 1·15 [95%CI: 1·02-1·29]) and 39% (adj.HR 1·39 [95%CI: 1·22-1·59]) higher age- and sex-adjusted mortality risk, respectively. Interpretation: We developed and validated an AI framework that enables scalable, opportunistic screening of treatable cardiomyopathies wherever POCUS is used. Funding: National Heart, Lung and Blood Institute, Doris Duke Charitable Foundation, BridgeBio.