TARGET-AI: a foundational approach for the targeted deployment of artificial intelligence electrocardiography in the electronic health record.

Background: Artificial intelligence (AI) applied to routine electrocardiograms (ECGs) offers promise for screening of structural heart disease (SHD), yet broad clinical integration remains limited by high false positive rates and the lack of tailored deployment strategies.

Methods: We developed TARGET-AI, a multimodal AI-enabled pipeline that integrates longitudinal electronic health record (EHR) data with ECG images to identify optimal intersections of healthcare encounters and patient phenotypes for targeted AI-ECG screening. The approach is built on (1) a foundation model pretrained on 118 million coded EHR events from 159,322 individuals to generate temporal patient embeddings and identify high-risk screening candidates, followed by (2) a contrastive vision-language model trained on 754,533 ECG-echocardiogram pairs to detect SHD with tunable performance characteristics.

Transforming Population Health Screening for Atherosclerotic Cardiovascular Disease with AI-Enhanced ECG Analytics: Opportunities and Challenges.

Purpose Of Review: To define the emerging role of artificial intelligence-enhanced electrocardiography (AI-ECG) in advancing population-level screening for atherosclerotic cardiovascular disease (ASCVD), we provide a comprehensive overview of its role in predicting major adverse cardiovascular events and detecting subclinical coronary artery disease. We also outline the clinical, methodological, and implementation challenges that must be addressed for widespread adoption.

Recent Findings: State-of-the-art AI-ECG models exhibit high accuracy, correctly re-classifying patients deemed 'low risk' by traditional risk models.

Phenotypic Selectivity of Artificial Intelligence-enhanced Electrocardiography in Cardiovascular Diagnosis and Risk Prediction.

Background: Artificial intelligence (AI)-enhanced electrocardiogram (ECG) models are often designed to detect specific anatomical and functional cardiac abnormalities. Understanding the selectivity of their phenotypic associations is essential to inform their clinical use. Here, we sought to assess whether AI-ECG models function as condition-specific classifiers or broader cardiovascular risk markers.

Phenotypic Selectivity of Artificial Intelligence-enhanced Electrocardiography in Cardiovascular Diagnosis and Risk Prediction.

Introduction: Artificial intelligence (AI)-enhanced electrocardiogram (ECG) models are designed to detect specific anatomical and functional cardiac abnormalities. Understanding the selectivity of their phenotypic associations is essential to inform their clinical use. Here, we sought to assess whether AI-ECG models function as condition-specific classifiers or broader cardiovascular risk markers.

National Patterns of Remote Patient Monitoring Service Availability at US Hospitals.

Background: Digital remote patient monitoring (RPM), such as home-based blood pressure, heart rate, or weight monitoring, enables longitudinal care outside traditional health care settings, especially in the vulnerable period after hospitalizations, with broad coverage of the service by payers. We sought to evaluate patterns of RPM service availability at US hospitals and the characteristics of hospitals and the counties they serve that are associated with the availability of these services.

Methods: We used national data from the American Hospital Association Annual Survey from 2018 to 2022 to ascertain US hospitals offering RPM services for postdischarge or chronic care.

Scientific Writing in the Era of Large Language Models: A Computational Analysis of AI Versus Human-Created Content.

Background: Large language models (LLMs) are artificial intelligence (AI) tools that can generate human expert-like content and be used to accelerate the synthesis of scientific literature, but they can spread misinformation by producing misleading content. This study sought to characterize distinguishing linguistic features in differentiating AI-generated from human-authored scientific text and evaluate the performance of AI detection tools for this task.

Methods: We conducted a computational synthesis of 34 essays on cerebrovascular topics (12 generated by large language models [Generative Pre-trained Transformer 4, Generative Pre-trained Transformer 3.

Changes in Cardiovascular Risk Factors and Health Care Expenditures Among Patients Prescribed Semaglutide.

Importance: Semaglutide, a glucagon-like peptide-1 receptor agonist, has demonstrated substantial weight reduction and cardiovascular benefits in clinical trials. However, its association with clinical outcomes and health care expenditures remains underexplored.

Objective: To evaluate changes in cardiovascular risk factors and health care expenditures among patients prescribed semaglutide across multicenter cohorts.

Development and multinational validation of an ensemble deep learning algorithm for detecting and predicting structural heart disease using noisy single-lead electrocardiograms.

Aims: Artificial intelligence (AI)-enhanced 12-lead electrocardiogram (ECG) can detect a range of structural heart diseases (SHDs); however, it has a limited role in community-based screening. We developed and externally validated a noise-resilient single-lead AI-ECG algorithm that can detect SHDs and predict the risk of their development using wearable/portable devices.

Methods And Results: Using 266 740 ECGs from 99 205 patients with paired echocardiographic data at Yale New Haven Hospital, we developed AI Deep learning for Adapting Portable Technology in HEART disease detection (ADAPT-HEART), a noise-resilient, deep learning algorithm, to detect SHDs using lead I ECG.

Automated transformation of unstructured cardiovascular diagnostic reports into structured datasets using sequentially deployed large language models.

Aims: Rich data in cardiovascular diagnostic testing are often sequestered in unstructured reports, limiting their use.

Methods And Results: We sequentially deployed generative and interpretative open-source large language models (LLMs; Llama2-70b, Llama2-13b). Using Llama2-70b, we generated varying formats of transthoracic echocardiogram (TTE) reports from 3000 real-world reports with paired structured elements.

Identification of hypertrophic cardiomyopathy on electrocardiographic images with deep learning.

Hypertrophic cardiomyopathy (HCM) is frequently underdiagnosed. Although deep learning (DL) models using raw electrocardiographic (ECG) voltage data can enhance detection, their use at the point of care is limited. Here we report the development and validation of a DL model that detects HCM from images of 12-lead ECGs across layouts.

Artificial intelligence-enabled electrocardiography and echocardiography to track preclinical progression of transthyretin amyloid cardiomyopathy.

Background And Aims: The diagnosis of transthyretin amyloid cardiomyopathy (ATTR-CM) requires advanced imaging, precluding large-scale preclinical testing. Artificial intelligence (AI)-enabled transthoracic echocardiography (TTE) and electrocardiography (ECG) may provide a scalable strategy for preclinical monitoring.

Methods: This was a retrospective analysis of individuals referred for nuclear cardiac amyloid testing at the Yale-New Haven Health System (YNHHS, internal cohort) and Houston Methodist Hospitals (HMH, external cohort).

Cardiac magnetic resonance markers of pre-clinical hypertrophic and dilated cardiomyopathy in genetic variant carriers.

Background: Patients with hypertrophic cardiomyopathy (HCM) and dilated cardiomyopathy (DCM) exhibit structural and functional cardiac abnormalities. We aimed to identify imaging biomarkers for pre-clinical cardiomyopathy in healthy participants carrying cardiomyopathy-associated variants (G +).

Methods: We included 40,169 UK Biobank participants free of cardiac disease at the time of cardiac magnetic resonance imaging (CMR) and with whole exome sequencing.

Leveraging AI-enhanced digital health with consumer devices for scalable cardiovascular screening, prediction, and monitoring.

Traditional cardiovascular care relies on episodic, resource-intensive evaluations. Consumer wearable and portable devices, combined with artificial intelligence (AI), offer a scalable, low-cost alternative. These devices can enhance care with high-fidelity cardiovascular data captured outside traditional care settings, with AI further increasing their value.

Wearable-Echo-FM: An ECG-echo foundation model for single lead electrocardiography.

Artificial intelligence (AI) models can now detect patterns of structural heart diseases (SHDs) from electrocardiograms (ECGs), though scaling them requires the broader use of single-lead ECGs that are now ubiquitous in wearable and portable devices. However, model development for these devices is limited by a lack of diagnostic labels for SHDs for wearable ECGs. Here, we present Wearable-Echo-FM, a foundation model that encodes single-lead ECGs with information from echocardiographic text reports.

Towards a dynamic model to estimate evolving risk of major bleeding after percutaneous coronary intervention.

While static risk models may identify key driving risk factors, the dynamic nature of risk requires up-to-date risk information to guide treatment decision making. Bleeding is a complication of percutaneous coronary intervention (PCI), and existing risk models produce only a single risk estimate anchored at a single point in time, despite the dynamic nature of this risk. Using data available from the National Cardiovascular Data Registry (NCDR) CathPCI, we trained 6 different tree-based machine learning models to estimate the risk of bleeding at key decision points: 1) choice of access site, 2) prescription of medication before PCI, and 3) choice of closure device.

Complete AI-Enabled Echocardiography Interpretation With Multitask Deep Learning.

Importance: Echocardiography is a cornerstone of cardiovascular care, but relies on expert interpretation and manual reporting from a series of videos. An artificial intelligence (AI) system, PanEcho, has been proposed to automate echocardiogram interpretation with multitask deep learning.

Objective: To develop and evaluate the accuracy of an AI system on a comprehensive set of 39 labels and measurements on transthoracic echocardiography (TTE).

A Real-world Evaluation of Longitudinal Healthcare Expenses in a Health System Registry of Type-2 Diabetes Mellitus and Cardiovascular Disease Enabled by the 21st Century Cures Act.

Introduction: Type 2 diabetes (T2D) is associated with substantial healthcare spending, but quantifying these expenses has been limited to cohorts of self-selected patients or assessments of insurance claims for major healthcare events. Leveraging the 21 Century Cures Act, which mandated reporting hospital-level service, we pursued a comprehensive evaluation of healthcare spending in a diverse cohort of individuals with T2D.

Methods: We designed a pragmatic, observational cohort study of patients with T2D seeking regular care (≥ 1 visit/2 years) across 5 hospitals and an outpatient network (2013-2023) in the Yale New Haven Health System.

A Novel Sentence Transformer-based Natural Language Processing Approach for Schema Mapping of Electronic Health Records to the OMOP Common Data Model.

Mapping electronic health records (EHR) data to common data models (CDMs) enables the standardization of clinical records, enhancing interoperability and enabling large-scale, multi-centered clinical investigations. Using 2 large publicly available datasets, we developed transformer-based natural language processing models to map medication-related concepts from the EHR at a large and diverse healthcare system to standard concepts in OMOP CDM. We validated the model outputs against standard concepts manually mapped by clinicians.

Use of Artificial Intelligence Applied to Electrocardiogram for Diagnosis of Left Ventricular Systolic Dysfunction.

Background: Heart failure (HF) is a disease associated with an important type of morbidity and mortality. The electrocardiogram (ECG), one of the tests used to evaluate HF, is low-cost and widely available.

Objective: To evaluate the performance of an artificial intelligence (AI) algorithm applied to ECG to detect HF and compare it with the predictive power of major electrocardiographic alterations (MEA).

Comparative Safety of Second-Line Antihyperglycemic Agents in Older Adults with Type 2 Diabetes: A Multinational Real-World Evidence From LEGEND-T2DM.

Background: As prescribing of newer antihyperglycemic agents expands, there remains limited comparative safety data for older adults-a population particularly vulnerable to adverse drug events and underrepresented in clinical trials. We aimed to evaluate the real-world safety of second-line antihyperglycemic agents among older adults with type 2 diabetes.

Methods: We conducted a multinational cohort study using nine harmonized electronic health record and claims databases from the U.

Effects of Tirzepatide in Type 2 Diabetes: Individual Variation and Relationship to Cardiometabolic Outcomes.

Background: Tirzepatide-a dual GIP/GLP-1 receptor agonist-exerts pleiotropic effects on cardiometabolic health.

Objectives: The authors sought to investigate the efficacy of tirzepatide in improving different cardiometabolic risk factors across individuals and subpopulations.

Methods: Using an independent, global data-sharing and analytics platform, we performed an individual participant data meta-analysis by pooling data from 7 Phase 3 randomized clinical trials that compared tirzepatide with placebo or standard antihyperglycemic agents in individuals with type 2 diabetes.