{"doi":"10.1101/2024.05.27.24307952","title":"Artificial Intelligence Enabled Prediction of Heart Failure Risk from Single-lead Electrocardiograms","abstract":"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. KEY POINTS Question Can single-lead electrocardiograms (ECG) predict heart failure (HF) risk? Findings We evaluated a noise-adapted artificial intelligence (AI) algorithm for single-lead ECGs across multinational cohorts, spanning a diverse US health-system and community-based cohorts in the UK and Brazil. A positive AI-ECG screen was associated with 3- to 7-fold higher HF risk, independent of age, sex, and comorbidities. The AI model achieved incremental discrimination and improved reclassification over two established clinical risk scores for HF prediction. Meaning A noise-adapted AI model for single-lead ECG predicted the risk of new-onset HF, representing a scalable HF risk-stratification strategy for portable and wearable devices.","journal":"medRxiv","year":2024,"id":484885,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":7,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9507,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":75766,"name":"Arya Aminorroaya","orcid":"0000-0003-3197-2657","position":1,"is_corresponding":false},{"id":1326923,"name":"Aline F Pedroso","orcid":"0000-0002-1876-8304","position":2,"is_corresponding":false},{"id":985597,"name":"Akshay Khunte","orcid":"0000-0003-3812-3260","position":3,"is_corresponding":false},{"id":807985,"name":"Veer Sangha","orcid":"0000-0002-8524-1203","position":4,"is_corresponding":false},{"id":1327019,"name":"Daniel McIntyre","orcid":"0000-0003-4854-4050","position":5,"is_corresponding":false},{"id":1021239,"name":"Clara K Chow","orcid":"0000-0003-4693-0038","position":6,"is_corresponding":false},{"id":21948,"name":"Folkert W. Asselbergs","orcid":"0000-0002-1692-8669","position":7,"is_corresponding":false},{"id":61452,"name":"Luísa Campos Caldeira Brant","orcid":"0000-0002-7317-1367","position":8,"is_corresponding":false},{"id":621705,"name":"Sandhi Maria Barreto","orcid":"0000-0001-7383-7811","position":9,"is_corresponding":false},{"id":61511,"name":"Antônio Luiz Pinho Ribeiro","orcid":"0000-0002-2740-0042","position":10,"is_corresponding":false},{"id":1077,"name":"Harlan M. Krumholz","orcid":"0000-0003-2046-127X","position":11,"is_corresponding":false},{"id":89683,"name":"Evangelos K. Oikonomou","orcid":"0000-0003-4362-0720","position":12,"is_corresponding":false},{"id":74880,"name":"Rohan Khera","orcid":"0000-0001-9467-6199","position":13,"is_corresponding":false},{"id":534990,"name":"Lovedeep Singh Dhingra","orcid":"0000-0002-5664-4126","position":0,"is_corresponding":true}],"reference_count":80,"raw_metadata":null,"created_at":"2026-07-19T02:07:42.971417Z","pmid":"38854022","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}