Key result
Heart failure mortality prediction models show poor rigor, with only ~23% reporting external validation.
Why the study?
Numerous heart failure mortality prediction models have been developed using conventional statistics, machine learning, and deep learning, but variation in study populations, heart failure definitions, prediction horizons, and development practices may limit interpretation of their applicability.
Do machine learning and deep learning models improve all-cause mortality prediction over 1-60 months compared to conventional statistical models in patients with heart failure?
Systematic Review
Do machine learning and deep learning models improve all-cause mortality prediction over 1-60 months compared to conventional statistical models in patients with heart failure?
Answers are grounded in this paper and cite their sources.
Despite a growing shift toward machine learning for heart failure mortality prediction, clinical utility and comparability remain severely limited by inconsistent cohort definitions (64% undefined) and a lack of external validation (only 23% of studies).
Heart failure is a serious medical condition associated with risk of acute deterioration, recurrent hospitalizations and high mortality making accurate mortality prediction potentially valuable for patient care and healthcare planning. Numerous prognostic models have been developed using conventional statistics (CS), machine learning (ML) and deep learning (DL), but variation in study populations, heart failure definitions, prediction horizons and development practices may limit interpretation of applicability. We conducted a systematic review of mortality prediction models published between 2009 to the start of 2026 searching three databases (PubMed, IEEE and Scopus) for studies predicting all-cause mortality over a 1-60 months prediction horizon among patients with heart failure. Data extracted were cohort characteristics, heart failure definitions, model development, cohort size, validation practices, mortality, computational model design and reported performance. The risk of bias and applicability were assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Of 1516 publications identified, 56 met the inclusion criteria. Publication numbers increased over the observation period, alongside increasing use of ML/DL models and decreasing use of CS approaches. Most development cohorts (64%) were classified as Unknown/Undefined heart failure, reflecting inconsistent reporting and terminology that did not correspond with established heart failure guidelines. External validation was reported in 23% of studies. Overall, research in modeling heart failure mortality has grown alongside increasing adoption of ML/DL approaches. Greater standardization of study design and reporting is needed for meaningful comparison, reproducibility and evaluation of models for clinical application.
No takes yet. Share an insight, caveat, or question.
Aerts et al. (2026) conducted a systematic review in Heart failure. Machine learning and deep learning (ML/DL) mortality prediction models vs. Conventional statistics (CS) mortality prediction models was evaluated on All-cause mortality model performance (C-statistic and AUC), cohort definitions, and external validation rates. Among 56 heart failure mortality prediction studies, 64% had undefined heart failure classifications and only 23% reported external validation despite growing adoption of machine learning models.
Synapse has enriched 10 related papers. Consider them for comparative context: