Publications by authors named "Gilson Yuuji Shimizu"
Article Synopsis
- - The study focuses on developing and validating machine learning models to predict major adverse cardiovascular events (MACE) by evaluating their reliability and interpretability across different populations, utilizing data from Brazil and the USA.
- - Eight machine learning algorithms were trained using a balanced dataset and assessed for their predictive performance based on accuracy and ROC curve metrics, with emphasis on Random Forest, which outperformed the others in both internal and external validations.
- - Findings indicate that while Random Forest was the most effective model, Shapley values offered more consistent insights for understanding feature importance compared to LIME during exploratory analyses.
