Key result
Dynamic GRU model predicts 3-year mortality with an AUC of ~0.77.
Why the study?
Prediction models for mortality risk in chronic heart failure patients have traditionally relied on static admission data, limiting the ability to capture disease dynamics.
Does a dynamic prognosis model utilizing longitudinal patient-reported outcomes and Gated Recurrent Units accurately predict 3-year mortality in patients with chronic heart failure?
Cohort (n=1,333)
Yes
Does a dynamic prognosis model utilizing longitudinal patient-reported outcomes and Gated Recurrent Units accurately predict 3-year mortality in patients with chronic heart failure?
Effect estimate: AUC 0.765 (95% CI 0.761-0.768)
A dynamic prediction model utilizing longitudinal patient-reported outcomes and a Gated Recurrent Units algorithm accurately predicts 3-year mortality in patients with chronic heart failure.
May support dynamic HF mortality prediction with longitudinal PROs; leaves open external validation before clinical use.
Background: Prediction models for mortality risk in patients with chronic heart failure (CHF) have traditionally relied on static admission data, which restricts capturing disease dynamics. Longitudinal follow-up data were used to develop a dynamic model to improve accuracy and provide evidence for tailored interventions. Methods: We enrolled 1,333 CHF patients from 3 Shanxi centres. Data included CHF patient-reported outcome (PRO) measures (CHF-PROM), lifestyle, medications, and prognosis. Endpoint: all-cause mortality. Using sequential data, we developed Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), Multi-layer Perceptron (MLP), and Logistic Regression (LR) for 3-year risk. Performance assessed by area under the receiver operating characteristic curve (AUC), accuracy, true negative rate (TNR), true positive rate (TPR), Brier score, and F1-score. Temporal Shapley Additive exPlanations (TimeSHAP) provided interpretability, and a web tool built. Results: Among models tested, the GRU model demonstrated strongest predictive accuracy, with performance steadily increasing as follow-up progressed. By 24 months, the GRU-based model attained its peak predictive performance, yielding an AUC of 0.765 (95% confidence interval [CI]: 0.761-0.768), an F1-score of 0.537 (95% CI: 0.531-0.542), and a Brier score of 0.208 (95% CI: 0.199-0.216). TimeSHAP indicated that physical condition, appetite, sleep, physical independence, and anxiety within the CHF-PROM, together with age and New York Heart Association Functional Classification functional class, were key predictors of 3-year all-cause mortality in patients with CHF. Conclusion: PRO data from multiple follow-ups, combined with a model constructed using GRU, provides promising tool for predicting mortality risk in patients with chronic heart failure (CHF). The self-developed web-based decision support system allows users to calculate risk scores simply by entering patient information. Trial Registration: Study registered with the China Clinical Trial Registry [identifier: ChiCTR2100043337]. Experimental registration date is February 11, 2021.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2026) conducted a cohort in Chronic heart failure (n=1,333). Longitudinal patient-reported outcomes (PROs) and lifestyle data modeled via Gated Recurrent Units (GRU) vs. Other predictive models (LSTM, LR, MLP) or baseline models was evaluated on Predictive accuracy for 3-year all-cause mortality (AUC) (AUC 0.765, 95% CI 0.761-0.768). A Gated Recurrent Unit (GRU) dynamic prediction model incorporating longitudinal patient-reported outcomes and behavioral data achieved a peak AUC of 0.765 for predicting 3-year all-cause mortality.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: