BibTex format
@article{Sau:2024:10.1016/s2589-7500(24)00172-9,
author = {Sau, A and Pastika, L and Sieliwonczyk, E and Patlatzoglou, K and Ribeiro, AH and McGurk, KA and Zeidaabadi, B and Zhang, H and Macierzanka, K and Mandic, D and Sabino, E and Giatti, L and Barreto, SM and Camelo, LDV and Tzoulaki, I and O'Regan, DP and Peters, NS and Ware, JS and Ribeiro, ALP and Kramer, DB and Waks, JW and Ng, FS},
doi = {10.1016/s2589-7500(24)00172-9},
journal = {The Lancet Digital Health},
pages = {e791--e802},
title = {Artificial intelligence-enabled electrocardiogram for mortality and cardiovascular risk estimation: a model development and validation study},
url = {http://dx.doi.org/10.1016/s2589-7500(24)00172-9},
volume = {6},
year = {2024}
}
RIS format (EndNote, RefMan)
TY - JOUR
AB - BackgroundArtificial intelligence (AI)-enabled electrocardiography (ECG) can be used to predict risk of future disease and mortality but has not yet been adopted into clinical practice. Existing model predictions do not have actionability at an individual patient level, explainability, or biological plausibi. We sought to address these limitations of previous AI-ECG approaches by developing the AI-ECG risk estimator (AIRE) platform.MethodsThe AIRE platform was developed in a secondary care dataset (Beth Israel Deaconess Medical Center [BIDMC]) of 1163401 ECGs from 189539 patients with deep learning and a discrete-time survival model to create a patient-specific survival curve with a single ECG. Therefore, AIRE predicts not only risk of mortality, but also time-to-mortality. AIRE was validated in five diverse, transnational cohorts from the USA, Brazil, and the UK (UK Biobank [UKB]), including volunteers, primary care patients, and secondary care patients.FindingsAIRE accurately predicts risk of all-cause mortality (BIDMC C-index 0·775, 95% CI 0·773–0·776; C-indices on external validation datasets 0·638–0·773), future ventricular arrhythmia (BIDMC C-index 0·760, 95% CI 0·756–0·763; UKB C-index 0·719, 95% CI 0·635–0·803), future atherosclerotic cardiovascular disease (0·696, 0·694–0·698; 0·643, 0·624–0·662), and future heart failure (0·787, 0·785–0·789; 0·768, 0·733–0·802). Through phenome-wide and genome-wide association studies, we identified candidate biological pathways for the prediction of increased risk, including changes in cardiac structure and function, and genes associated with cardiac structure, biological ageing, and metabolic syndrome.InterpretationAIRE is an actionable, explainable, and biologically plausible AI-ECG risk estimation platform that
AU - Sau,A
AU - Pastika,L
AU - Sieliwonczyk,E
AU - Patlatzoglou,K
AU - Ribeiro,AH
AU - McGurk,KA
AU - Zeidaabadi,B
AU - Zhang,H
AU - Macierzanka,K
AU - Mandic,D
AU - Sabino,E
AU - Giatti,L
AU - Barreto,SM
AU - Camelo,LDV
AU - Tzoulaki,I
AU - O'Regan,DP
AU - Peters,NS
AU - Ware,JS
AU - Ribeiro,ALP
AU - Kramer,DB
AU - Waks,JW
AU - Ng,FS
DO - 10.1016/s2589-7500(24)00172-9
EP - 802
PY - 2024///
SN - 2589-7500
SP - 791
TI - Artificial intelligence-enabled electrocardiogram for mortality and cardiovascular risk estimation: a model development and validation study
T2 - The Lancet Digital Health
UR - http://dx.doi.org/10.1016/s2589-7500(24)00172-9
VL - 6
ER -