Key result
CardioMonoStack predicts postoperative heart failure after hip arthroplasty with up to ~0.87 AUROC.
Why the study?
Accurate perioperative risk prediction for postoperative heart failure after total hip arthroplasty remains challenging because of class imbalance, cohort heterogeneity, unstable probability estimates, and limited interpretability.
Does the CardioMonoStack ensemble learning model accurately predict in-hospital postoperative heart failure risk in patients aged ≥65 years undergoing total hip arthroplasty?
Cohort (n=1,911)
Yes
Does the CardioMonoStack ensemble learning model accurately predict in-hospital postoperative heart failure risk in patients aged ≥65 years undergoing total hip arthroplasty?
CardioMonoStack demonstrates promising external discrimination for predicting in-hospital heart failure after total hip arthroplasty in older adults, though prospective validation and local recalibration are needed prior to clinical deployment.
Answers are grounded in this paper and cite their sources.
CardioMonoStack shows strong external discrimination for postoperative HF; hypothesis-generating and requires prospective validation before clinical use.
Background Accurate perioperative risk prediction remains challenging because of class imbalance, cohort heterogeneity, unstable probability estimates and limited interpretability. Objective To develop and externally evaluate CardioMonoStack, an ensemble architecture integrating heterogeneous base learners, branch-level monotonicity priors, stacked meta-learning and feature-dependent residual logit correction. Methods We conducted a multicentre retrospective cohort study of 1911 patients aged ≥65 years undergoing total hip arthroplasty across five healthcare databases. CardioMonoStack was developed using MIMIC-III and MIMIC-IV, validated in INSPIRE, and externally tested in eICU and MOVER. Performance was assessed using AUROC, AUPRC, Brier score, threshold-dependent classification measures, calibration plots and decision curve analysis. Interpretability was examined using SHAP, interaction and individual conditional expectation analyses. Results CardioMonoStack achieved the highest AUROC point estimates among evaluated models in eICU (0.790; 95% CI 0.711–0.865) and MOVER (0.866; 95% CI 0.761–0.949), with AUPRC values of 0.569 (95% CI 0.415–0.717) and 0.571 (95% CI 0.328–0.792), respectively. Calibration and net benefit varied across cohorts and comparators. Omission of L3 increased Brier-score and log-loss point estimates in both external cohorts; paired confidence intervals supported these differences in MOVER but were inconclusive in eICU. SHAP analyses prioritised blood urea nitrogen, creatinine, age, and metabolic and demographic factors. Conclusion CardioMonoStack is a candidate framework for estimating in-hospital heart-failure risk after total hip arthroplasty. Despite promising external discrimination, prospective validation, local recalibration, and clinical impact evaluation are required before implementation.
No takes yet. Share an insight, caveat, or question.
Cui et al. (2026) conducted a cohort in Postoperative heart failure after total hip arthroplasty (n=1,911). CardioMonoStack ensemble risk prediction model vs. Evaluated comparator models and ablated model variants (omission of L3) was evaluated on In-hospital postoperative heart failure discrimination (AUROC and AUPRC) (AUROC 0.790 (eICU); AUROC 0.866 (MOVER), 95% CI 0.711-0.865 (eICU); 0.761-0.949 (MOVER)). CardioMonoStack achieved the highest external AUROC for postoperative heart failure after total hip arthroplasty in eICU and MOVER.
Synapse has enriched 10 related papers. Consider them for comparative context: