Machine Learning Constructed Based on Patient Plaque and Clinical Features for Predicting Stent Malapposition: A Retrospective Study

Abstract

Background: Stent malapposition (SM) following percutaneous coronary intervention (PCI) for myocardial infarction continues to present significant clinical challenges. In recent years, machine learning (ML) models have demonstrated potential in disease risk stratification and predictive modeling.

Hypothesis: ML models based on optical coherence tomography (OCT) imaging, laboratory tests, and clinical characteristics can predict the occurrence of SM.

Methods: We studied 337 patients from the Affiliated Hospital of Zunyi Medical University, China, who had PCI and coronary OCT from May to October 2023. We employed nested cross-validation to partition patients into training and test sets. We developed five ML models: XGBoost, LR, RF, SVM, and NB based on calcification features. Performance was assessed using ROC curves. Lasso regression selected features from 46 clinical and 21 OCT imaging features, which were optimized with the five ML algorithms.

Results: In the prediction model based on calcification features, the XGBoost model and SVM model exhibited higher AUC values. Lasso regression identified five key features from clinical and imaging data. After incorporating selected features into the model for optimization, the AUC values of all algorithmic models showed significant improvements. The XGBoost model demonstrated the highest calibration accuracy. SHAP values revealed that the top five ranked features influencing the XGBoost model were calcification length, age, coronary dissection, lipid angle, and troponin.

Conclusion: ML models developed using plaque imaging features and clinical characteristics can predict the occurrence of SM. ML models based on clinical and imaging features exhibited better performance.

Keywords: acute myocardial infarction; machine learning; optical coherence tomography; percutaneous coronary intervention; stent malapposition.

Figure 1

Partial OCT images. (A) Normal coronary OCT image; (B) calcified plaque; (C) lipid plaque; (D) microvessels; (E) non‐stent malapposition; (F) stent malapposition.

Figure 2

ROC curves of optimized machine learning prediction models for the training and testing data sets. (A) ROC curves of various algorithms for the training data set; (B) ROC curves of various algorithms for the testing data set.

Figure 3

Feature importance of the XGBoost model assessed by SHAP value. (A) The influence of each feature on the output of the XGBoost model; (B) swarm plot.