Deep learning for mortality prediction in patients with a de-novo or worsened heart failure

Le résumé fourni par la source

Abstract Background Heart failure (HF) is a heterogenous syndrome with complex pathophysiology. Biomarkers and clinical risk scores often fail to provide optimal patient-level precision in the prognostic stratification. As utilizing single observational timepoint, they do not capture the entire care pathway with variations in individual patient management. Electronic patient records provide an opportunity to develop new artificial intelligence (AI) strategies for comprehensive prognostic re-stratification reflecting diagnostic and therapeutic management. Purpose We sought to use deep artificial intelligence (AI) and develop an unbiased predictive algorithm for all-cause mortality in a cohort of patients hospitalized with a de novo or worsened HF. Methods In a cohort of 2449 HF patients hospitalized between 2011–2017, we utilized 151 451 patient exams from 422 parameters. They included clinical phenotyping, medication, ECG, laboratory, echocardiography, catheterization data or percutaneous and surgical interventions gathered on a routine clinical basis reflecting standard of care as captured in individual electronic records. The AI model development consisted of 101 iterations of repeated random subsampling splits into balanced training and validation sets. Results AI models yielded performance ranging from 0.83 to 0.89 AUC on the outcome-balanced validation set in predicting all-cause mortality at 30-, 90-, 180-, 360- and 720-day time-limits (Figure 1). The primary endpoint, 1-year mortality prediction model, recorded an 0.85 AUC accuracy. We observed stable model performance across all HF phenotypes: HFpEF 0.83 AUC, HFmrEF 0.85 AUC and HFrEF 0.86 AUC, respectively). Conclusion Our findings present a novel, patient-level, AI-based risk prediction of all-cause mortality in heart failure with a robust accuracy across its phenotypes. This suggests the potential of AI based predictive models in a point-of-care approach to guide clinical risk stratification. Funding Acknowledgement Type of funding sources: Foundation. Main funding source(s): VZW Cardiovascular Research Center Aalst

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.