Key result
Echocardiography-based ResNet deep learning models achieved AUROCs of 82%, 82%, and 78% for predicting 1-, 3-, and 5-year mortality in external validation, outperforming CatBoost models.
Why the study?
Echocardiography-based machine learning models may be useful to identify patients at high risk of all-cause mortality.
Do echocardiography-based machine-learning models accurately predict 1-year, 3-year, and 5-year mortality in patients with or at risk of heart failure?
Cohort (n=4,221)
Yes
Do echocardiography-based machine-learning models accurately predict 1-year, 3-year, and 5-year mortality in patients with or at risk of heart failure?
Echocardiography-based machine learning models, particularly deep learning using echo videos, provide accurate and generalizable predictions of 1- to 5-year mortality that are comparable to established clinical risk scores.
BACKGROUND: Echocardiography (echo) based machine learning (ML) models may be useful in identifying patients at high-risk of all-cause mortality. METHODS: We developed ML models (ResNet deep learning using echo videos and CatBoost gradient boosting using echo measurements) to predict 1-year, 3-year, and 5-year mortality. Models were trained on the Mackay dataset, Taiwan (6083 echos, 3626 patients) and validated in the Alberta HEART dataset, Canada (997 echos, 595 patients). We examined the performance of the models overall, and in subgroups (healthy controls, at risk of heart failure (HF), HF with reduced ejection fraction (HFrEF) and HF with preserved ejection fraction (HFpEF)). We compared the models' performance to the MAGGIC risk score, and examined the correlation between the models' predicted probability of death and baseline quality of life as measured by the Kansas City Cardiomyopathy Questionnaire (KCCQ). FINDINGS: Mortality rates at 1-, 3- and 5-years were 14.9%, 28.6%, and 42.5% in the Mackay cohort, and 3.0%, 10.3%, and 18.7%, in the Alberta HEART cohort. The ResNet and CatBoost models achieved area under the receiver-operating curve (AUROC) between 85% and 92% in internal validation. In external validation, the AUROCs for the ResNet (82%, 82%, and 78%) were significantly better than CatBoost (78%, 73%, and 75%), for 1-, 3- and 5-year mortality prediction respectively, with better or comparable performance to the MAGGIC score. ResNet models predicted higher probability of death in the HFpEF and HFrEF (30%-50%) subgroups than in controls and at risk patients (5%-20%). The predicted probabilities of death correlated with KCCQ scores (all p < 0.05). INTERPRETATION: Echo-based ML models to predict mortality had good internal and external validity, were generalizable, correlated with patients' quality of life, and are comparable to an established HF risk score. These models can be leveraged for automated risk stratification at point-of-care. FUNDING: Funding for Alberta HEART was provided by an Alberta Innovates - Health Solutions Interdisciplinary Team Grant no. AHFMRITG 200801018. P.K. holds a Canadian Institutes of Health Research (CIHR) Sex and Gender Science Chair and a Heart & Stroke Foundation Chair in Cardiovascular Research. A.V. and V.S. received funding from the Mitacs Globalink Research Internship.
No takes yet. Share an insight, caveat, or question.
Valsaraj et al. (2023) conducted a cohort in Heart failure and healthy controls (n=4,221). Echocardiography-based machine-learning models (ResNet) vs. CatBoost models and MAGGIC risk score was evaluated on 1-year, 3-year, and 5-year mortality prediction. Echocardiography-based ResNet deep learning models achieved AUROCs of 82%, 82%, and 78% for predicting 1-, 3-, and 5-year mortality in external validation, outperforming CatBoost models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: