Artificial intelligence-enabled electrocardiogram for mortality and cardiovascular risk estimation: a model development and validation study

Arunashis Sau; Libor Pastika; Ewa Sieliwonczyk; Konstantinos Patlatzoglou; Antônio H Ribeiro; Kathryn A McGurk; Boroumand Zeidaabadi; Henry Zhang; Krzysztof Macierzanka; Danilo Mandic; Ester Sabino; Luana Giatti; Sandhi M Barreto; Lidyane do Valle Camelo; Ioanna Tzoulaki; Declan P O'Regan; Nicholas S Peters; James S Ware; Antonio Luiz P Ribeiro; Daniel B Kramer; Jonathan W Waks; Fu Siong Ng

doi:10.1016/S2589-7500(24)00172-9

Artificial intelligence-enabled electrocardiogram for mortality and cardiovascular risk estimation: a model development and validation study

Lancet Digit Health. 2024 Nov;6(11):e791-e802. doi: 10.1016/S2589-7500(24)00172-9.

Authors

Arunashis Sau¹, Libor Pastika², Ewa Sieliwonczyk³, Konstantinos Patlatzoglou², Antônio H Ribeiro⁴, Kathryn A McGurk⁵, Boroumand Zeidaabadi², Henry Zhang², Krzysztof Macierzanka², Danilo Mandic⁶, Ester Sabino⁷, Luana Giatti⁷, Sandhi M Barreto⁸, Lidyane do Valle Camelo⁸, Ioanna Tzoulaki⁹, Declan P O'Regan¹⁰, Nicholas S Peters¹, James S Ware⁵, Antonio Luiz P Ribeiro¹¹, Daniel B Kramer¹², Jonathan W Waks¹³, Fu Siong Ng¹⁴

Affiliations

¹ National Heart and Lung Institute, Imperial College London, London, UK; Department of Cardiology, Imperial College Healthcare NHS Trust, London, UK.
² National Heart and Lung Institute, Imperial College London, London, UK.
³ National Heart and Lung Institute, Imperial College London, London, UK; MRC Laboratory of Medical Sciences, Imperial College London, London, UK; University of Antwerp and Antwerp University Hospital, Antwerp, Belgium.
⁴ Department of Information Technology, Uppsala University, Uppsala, Sweden.
⁵ National Heart and Lung Institute, Imperial College London, London, UK; MRC Laboratory of Medical Sciences, Imperial College London, London, UK.
⁶ Department of Electrical and Electronic Engineering, Imperial College London, London, UK.
⁷ Department of Infectious Diseases, School of Medicine and Institute of Tropical Medicine, University of São Paulo, São Paulo, Brazil.
⁸ Department of Preventive Medicine, School of Medicine, and Hospital das Clínicas/EBSERH, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil.
⁹ Systems Biology, Biomedical Research Foundation, Academy of Athens, Athens, Greece; Department of Biostatistics and Epidemiology, School of Public Health, Imperial College London, London, UK.
¹⁰ MRC Laboratory of Medical Sciences, Imperial College London, London, UK.
¹¹ Department of Internal Medicine, Faculdade de Medicina, and Telehealth Center and Cardiology Service, Hospital das Clínicas, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil.
¹² National Heart and Lung Institute, Imperial College London, London, UK; Richard A and Susan F Smith Center for Outcomes Research in Cardiology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA.
¹³ Harvard-Thorndike Electrophysiology Institute, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA.
¹⁴ National Heart and Lung Institute, Imperial College London, London, UK; Department of Cardiology, Imperial College Healthcare NHS Trust, London, UK; Department of Cardiology, Chelsea and Westminster Hospital NHS Foundation Trust, London, UK. Electronic address: [email protected].

PMID: 39455192
DOI: 10.1016/S2589-7500(24)00172-9

Abstract

Background: Artificial 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.

Methods: The AIRE platform was developed in a secondary care dataset (Beth Israel Deaconess Medical Center [BIDMC]) of 1 163 401 ECGs from 189 539 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.

Findings: AIRE 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.

Interpretation: AIRE is an actionable, explainable, and biologically plausible AI-ECG risk estimation platform that has the potential for use worldwide across a wide range of clinical contexts for short-term and long-term risk estimation.

Funding: British Heart Foundation, National Institute for Health and Care Research, and Medical Research Council.

Publication types

Validation Study

MeSH terms

Adult
Aged
Artificial Intelligence*
Brazil / epidemiology
Cardiovascular Diseases* / mortality
Deep Learning
Electrocardiography*
Female
Humans
Male
Middle Aged
Risk Assessment / methods
United Kingdom

Grants and funding

MR/Y000803/1/MRC_/Medical Research Council/United Kingdom