Key result
Deep learning model predicts all-cause mortality with AUC 0.83, outperforming NT-proBNP in heart failure.
Why the study?
Heart failure is a heterogeneous syndrome with uncertain prognosis, prompting the development and validation of a robust deep learning approach for personalized risk assessment of worsening heart failure and mortality.
Does a novel deep learning approach using echocardiographic data improve prediction of worsening heart failure and mortality compared to established biomarkers in patients with heart failure?
Does a novel deep learning approach using echocardiographic data improve prediction of worsening heart failure and mortality compared to established biomarkers in patients with heart failure?
Answers are grounded in this paper and cite their sources.
A novel deep learning model using echocardiographic videos outperformed established clinical markers like NT-proBNP and E/e' in predicting mortality and worsening heart failure.
Background Heart failure (HF) is a heterogeneous clinical syndrome with uncertain prognosis, particularly in advanced stages. This project aimed to develop and validate a robust deep learning (DL) approach for personalized risk assessment in HF, focusing on the prediction of worsening of HF and mortality. Methods Echocardiography from participants of the MyoVasc study (n=3,289), a prospective study on HF, were preprocessed using EchoCLIP. The processed videos were used for the development and validation of a novel feedforward neural network, with model performance evaluated on a hold-out test set from the same cohort. A neural network was used to predict all-cause mortality, worsening of HF, and the transition from asymptomatic (Stage B) to symptomatic (Stage C/D) HF over a two years follow-up period. HF stages were determined according to the Universal Definition of Heart Failure. Worsening of HF was defined as a composite of HF-related hospitalization or cardiac death in HF C/D or progression from asymptomatic to symptomatic HF. Transition from asymptomatic to symptomatic HF was defined as having HF stage B at baseline and HF stage C/D at the two-year follow-up examination. Mortality and worsening of HF were estimated using multivariable Cox proportional hazards models, adjusted for age and sex with DL model results, NT-proBNP, left ventricular ejection fraction (LVEF), or E to e prime ratio (E/e’) as predictors in separate models. C-indices were compared using a non-parametric statistical test to evaluate whether the DL model results demonstrated superior prognostic performance compared to established clinical markers. Results A total of 7,441 videos from 2,765 participants was analysed. Follow-up time for all-cause mortality (626 events) was 10 years, for worsening of HF (317 events) was 4 years, and for the transition from stage B to C/D (167 events) was 2 years. The DL model demonstrated high performance across all three tasks, with an area under the curve of 0.83 for all-cause mortality, 0.80 for worsening of HF, and 0.76 for the transition from asymptomatic to symptomatic HF. It correctly identified 84.6% of mortality events, 79.2% of worsening of HF events, and 76.5% of transition events. The DL model had equally good performance across all HF phenotypes (HFpEF, HFmrEF, and HFrEF). The DL model outperformed NT-proBNP, LVEF and E/e’ in predicting all-cause mortality (p<0.0001). For the prediction of worsening of HF, the DL model results outperformed NT-proBNP (p=0.04) and E/e’ (p=0.0002), but were equal to LVEF. Conclusion The novel DL model presented in this work was able to identify individuals at risk of worsening of HF and death and outperformed gold-standard HF markers, suggesting an advancement in HF risk assessment by this approach.
No takes yet. Share an insight, caveat, or question.
Martinez et al. (2026) studied this question. The deep learning model predicted all-cause mortality with AUC 0.83 and outperformed established biomarkers like NT-proBNP in heart failure risk assessment.
Synapse has enriched 10 related papers. Consider them for comparative context: