Artificial Intelligence Enabled Prediction of Heart Failure Risk from Single-lead Electrocardiograms

Abstract

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 two risk scores for new-onset HF (PCP-HF and PREVENT equations) using Harrel's C-statistic, integrated discrimination improvement (IDI), and net reclassification improvement (NRI).

Results: There were 192,667 YNHHS patients (age 56 years [IQR, 41-69], 112,082 women [58%]), 42,141 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 3,697 developed HF in YNHHS over 4.6 years (2.8-6.6), 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 and PREVENT equations resulted in improved Harrel's C-statistic (Δ_PCP-HF=0.112-0.114; Δ_PREVENT=0.080-0.101). AI-ECG had IDI of 0.094-0.238 and 0.090-0.192, and NRI of 15.8%-48.8% and 12.8%-36.3%, vs. PCP-HF and PREVENT, respectively.

Conclusions and relevance: Across multinational cohorts, a noise-adapted AI model defined HF risk using lead I ECGs, suggesting a potential portable and wearable device-based HF risk-stratification strategy.

Keywords: Deep learning; Electrocardiograms; Heart failure; Predictive Modelling; Risk Stratification; Wearable Devices.

Figure 1.. Study Overview.

Abbreviations: BMI, Body Mass Index; BP; Blood Pressure; CNN, Convolutional Neural Network; ECG, Electrocardiogram; EF, Ejection Fraction; EHR, Electronic Health Record; ELSA-Brasil, Brazilian Longitudinal Study of Adult Health; HDL, High-density Lipoprotein Cholesterol; HF, Heart Failure; LV, Left Ventricle; YNH, Yale New Haven Hospital; YNHHS, Yale New Haven Health System.