Related Experiment Video
Updated: May 31, 2026
Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
Multicenter development and validation of machine-learning risk models to predict procedural complete
Yumin Lin1, Yufeng Qin1, Kangkang Ou2
1Department of Cardiology, Hezhou People's Hospital, Hezhou, China.
Insights
Machine learning models accurately predict in-hospital heart failure (HF) and procedural complete revascularization (CR) after ST-segment elevation myocardial infarction (STEMI) primary percutaneous coronary intervention (PPCI). These tools aid in risk stratification and decision-making for STEMI patients undergoing PPCI.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning
Background:
- In-hospital heart failure (HF) is a common complication following primary percutaneous coronary intervention (PPCI) for ST-segment elevation myocardial infarction (STEMI).
- Achieving procedural complete revascularization (CR) during PPCI is clinically important but challenging in real-world settings.
- Predicting these outcomes is crucial for optimizing patient care and resource allocation.
Purpose of the Study:
- To develop and externally validate machine learning (ML) models for predicting in-hospital HF.
- To develop and externally validate ML models for predicting the feasibility of achieving procedural CR during index PCI.
- To enhance peri-procedural risk stratification and decision support for STEMI patients.
Main Methods:
- A multicenter cohort study included STEMI patients treated with PPCI.
- Two independent cohorts were used for training (n=734) and external validation (n=352).
- Multiple ML algorithms were benchmarked, with CatBoost selected for its performance in predicting in-hospital HF and procedural CR.
Main Results:
- The CatBoost model for in-hospital HF prediction achieved an AUC of 0.973 and accuracy of 88.6% in the validation cohort.
- The CatBoost model for procedural CR prediction achieved an AUC of 0.970 and accuracy of 92.0% in the validation cohort.
- Key predictors identified included LAD involvement, age, symptom-to-guidewire crossing time, and markers of inflammation, coagulation, renal function, and lipid metabolism.
Conclusions:
- Externally validated ML models demonstrate strong performance in predicting in-hospital HF and procedural CR feasibility post-PPCI for STEMI.
- These models offer good discrimination, calibration, clinical utility, and interpretability.
- The developed models can support risk stratification and catheterization laboratory decision-making in STEMI patients receiving PPCI.
Background:
In-hospital heart failure (HF) remains common after primary percutaneous coronary intervention (PPCI) for ST-segment elevation myocardial infarction (STEMI) and is associated with adverse in-hospital outcomes. In addition, whether procedural complete revascularization (CR) can be achieved during the index PCI is clinically relevant but often constrained in real-world practice. We aimed to develop and externally validate machine-learning (ML) models for these two complementary prediction tasks.
Methods:
We conducted a multicenter cohort study of STEMI patients treated with PPCI from three hospitals. Patients from Hezhou People's Hospital (January 2020 to June 2024) comprised the training cohort (n = 734). Patients from two other centers (July 2024 to December 2025) were combined as an independent testing cohort (n = 352). Multiple ML algorithms were benchmarked to predict (1) in-hospital HF and (2) the real-world feasibility of achieving procedural CR during the index PCI. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), the area under the precision-recall curve (AUPRC), classification metrics, calibration curves, decision curve analysis (DCA), and clinical impact curves. Shapley Additive Explanations (SHAP) were used to enhance interpretability.
Results:
For in-hospital HF prediction, CatBoost showed the best overall performance in the independent testing cohort (AUC: 0.973; 95% CI: 0.957-0.989; accuracy: 88.6%), with good calibration and favorable net benefit on DCA. For procedural CR prediction, CatBoost was also selected as the primary model based on its overall performance profile in the independent testing cohort (AUC: 0.970; 95% CI: 0.954-0.987; accuracy: 92.0%), with acceptable calibration and positive net benefit across a broad range of threshold probabilities. Key predictors included LAD involvement, age, symptom-to-guidewire crossing time, and markers related to inflammation, coagulation, renal function, and lipid metabolism.
Conclusions:
In a three-center cohort, we developed and externally validated two ML models for predicting subsequent in-hospital HF after index PPCI and the feasibility of achieving procedural CR during the index PCI. Both models demonstrated good discrimination, calibration, clinical utility, and interpretability, supporting peri-procedural risk stratification and catheterization-laboratory decision support in STEMI patients treated with PPCI.