Related Experiment Videos
Development and Validation of an Interpretable Machine Learning Model for Predicting 1-Year Cardiac Death After
Hongya Liu1,2, Sutao Hu1, Yukun Zhang1
1Tianjin Key Laboratory of Ionic-Molecular Function of Cardiovascular Disease, Department of Cardiology, Tianjin Institute of Cardiology The Second Hospital of Tianjin Medical University Tianjin China.
Insights
A new machine learning model accurately predicts 1-year cardiac death risk after percutaneous coronary intervention in acute myocardial infarction patients using routine data. This interpretable model shows strong external validation and outperforms existing risk scores.
Area of Science:
- Cardiology
- Machine Learning
- Predictive Analytics
Background:
- Cardiac death prediction post-percutaneous coronary intervention (PCI) in acute myocardial infarction (AMI) is challenging.
- Current risk stratification methods require improvement for optimal patient management.
Purpose of the Study:
- To develop and externally validate an interpretable machine learning (ML) model for predicting 1-year cardiac death.
- To utilize only routine laboratory and demographic variables for model development, excluding imaging data.
Main Methods:
- Retrospective enrollment of 19,284 AMI patients undergoing PCI across 82 hospitals.
- Development of a Light Gradient-Boosting Machine (LightGBM) model using routine data, validated internally and externally.
- Comparison of the ML model's performance against the Global Registry of Acute Coronary Events (GRACE) score.
Main Results:
- The LightGBM model demonstrated strong discrimination in internal validation (AUC 0.921).
- In external validation, the model significantly outperformed the GRACE score (AUC 0.811 vs. 0.728, P=0.001).
- Model interpretability was assessed using Shapley Additive Explanations.
Conclusions:
- An interpretable ML model using routine variables effectively predicts 1-year cardiac death after PCI in AMI patients.
- The model's superior performance and external validity suggest potential for real-world risk stratification and personalized treatment.
Background:
Risk prediction of cardiac death following percutaneous coronary intervention remains suboptimal in acute myocardial infarction. This study aimed to develop and externally validate an interpretable machine learning model using only routine laboratory and demographic variables to predict 1-year cardiac death in this population.
Methods:
We retrospectively enrolled 19 284 patients with acute myocardial infarction who underwent percutaneous coronary intervention across 82 hospitals in Tianjin, China between January 2010 and March 2024. The cohort was randomly split into training (70%, n=13 499) and internal validation (30%, n=5785) sets. An external cohort of 2048 patients from an independent center was used for validation. A Light Gradient-Boosting Machine model based solely on routinely available laboratory and demographic variables, with no imaging inputs, was developed and compared with GRACE (Global Registry of Acute Coronary Events) scores. Shapley Additive Explanations were used to assess model interpretability.
Results:
In the original data set, 1984 patients experienced 1-year cardiac death. The model achieved strong discrimination in internal validation (area under the curve 0.921, precision-recall area under the curve 0.711, sensitivity 79.7%). In the external validation cohort, LightGBM achieved a precision-recall area under the curve of 0.162 and significantly outperformed the GRACE score in discrimination (area under the curve, 0.811 versus 0.728; P=0.001). Complementary assessments of calibration and decision-curve analysis supported the overall findings.
Conclusions:
This interpretable machine learning model based exclusively on routine laboratory and demographic variables outperformed the GRACE score in predicting 1-year cardiac death after percutaneous coronary intervention in patients with acute myocardial infarction. Its strong discrimination and external validity support its potential for real-world risk stratification and individualized management.