Artificial intelligence enabled electrocardiogram for mortality and cardiovascular risk estimation: An actionable, explainable and biologically plausible platform
Sau, A.; Pastika, L.; Sieliwonczyk, E.; Patlatzoglou, K.; Ribeiro, A. H.; McGurk, K. A.; Zeidaabadi, B.; Zhang, H.; Macierzanka, K.; Mandic, D.; Sabino, E.; Giatti, L.; Barreto, S. M.; Camelo, L. d. V.; Tzoulaki, I.; O'Regan, D. P.; Peters, N. S.; Ware, J. S.; Ribeiro, A. L.; Kramer, D. B.; Waks, J. W.; Ng, F. S.
Show abstract
Background and AimsArtificial intelligence-enhanced electrocardiograms (AI-ECG) can be used to predict risk of future disease and mortality but has not yet been adopted into clinical practice. Existing model predictions lack actionability at an individual patient level, explainability and biological plausibility. We sought to address these limitations of previous AI-ECG approaches by developing the AI-ECG risk estimator (AIRE) platform. Methods and ResultsThe AIRE platform was developed in a secondary care dataset of 1,163,401 ECGs from 189,539 patients, using deep learning with a discrete-time survival model to create a subject-specific survival curve using a single ECG. Therefore, AIRE predicts not only risk of mortality, but time-to-mortality. AIRE was validated in five diverse, transnational cohorts from the USA, Brazil and the UK, including volunteers, primary care and secondary care subjects. AIRE accurately predicts risk of all-cause mortality (C-index 0.775 (0.773-0.776)), cardiovascular (CV) death 0.832 (0.831-0.834), non-CV death (0.749 (0.747-0.751)), future ventricular arrhythmia (0.760 (0.756-0.763)), future atherosclerotic cardiovascular disease (0.696 (0.694-0.698)) and future heart failure (0.787 (0.785-0.889))). Through phenome- 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 aging and metabolic syndrome. ConclusionAIRE 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- and long-term risk estimation. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=170 SRC="FIGDIR/small/24301267v1_ufig1.gif" ALT="Figure 1"> View larger version (38K): org.highwire.dtl.DTLVardef@10fedb6org.highwire.dtl.DTLVardef@bf7254org.highwire.dtl.DTLVardef@eb06edorg.highwire.dtl.DTLVardef@13ea7f_HPS_FORMAT_FIGEXP M_FIG C_FIG
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Development and Multinational Validation of an Ensemble Deep Learning Algorithm for Detecting and Predicting Structural Heart Disease Using Noisy Single-lead Electrocardiograms 97%
- Simple Models Versus Deep Learning in Detecting Low Ejection Fraction From The Electrocardiogram 95%
- Advanced ECG heart age estimation applicable to both sinus and non-sinus rhythm associates with cardiovascular risk, cardiovascular morbidity, and survival 94%
Similar papers in this journal
- A genotype-phenotype taxonomy of hypertrophic cardiomyopathy 94%
- Multi-ethnic genome-wide association study of decomposed cardioelectric phenotypes illustrates strategies to identify and characterize evidence of shared genetic effects for complex traits 94%
- Dynamic Importance of Genomic and Clinical Risk for Coronary Artery Disease Over the Life Course 94%
Similar papers in this journal
- Automated severe aortic stenosis detection on single-view echocardiography: A multi-center deep learning study 94%
- Genome wide association analysis in dilated cardiomyopathy reveals two new key players in systolic heart failure on chromosome 3p25.1 and 22q11.23 93%
- AORTA Gene: Polygenic prediction improves detection of thoracic aortic aneurysm 93%
Similar papers in this journal
- Development and validation of imaging-free myocardial fibrosis prediction models, association with outcomes, and sample size estimation for phase 3 trials 96%
- Epigenomic prediction of cardiovascular disease risk and interactions with traditional risk metrics 94%
- Artificial intelligence of arterial Doppler waveforms to predict major adverse outcomes among patients evaluated for peripheral artery disease 93%
Similar papers in this journal
- Identification of Digital Twins to Guide Interpretable AI for Diagnosis and Prognosis in Heart Failure 96%
- Cohort Design and Natural Language Processing to Reduce Bias in Electronic Health Records Research: The Community Care Cohort Project 96%
- AI Learning for Pediatric Right Ventricular Assessment: Development and Validation Across Multiple Centers 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.