Cardiovascular Disease Prediction Model Based on Machine Learning and LIME Explainability Analysis

Cardiovascular diseases (CVD) are one of the leading causes of death worldwide, and early prediction and intervention are crucial to reducing mortality rates. This study constructs multiple machine learning models based on the cardiovascular disease dataset provided by Kaggle, and evaluates their predictive performance. The research includes data preprocessing, feature selection, and model training steps, and explores the performance of various algorithms, including Linear Regression, Lasso Regression, Random Forest, Gradient Boosting, and SVC. By comprehensively evaluating model performance using metrics such as MAE, MSE, RMSE, R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>, and MAPE, the Gradient Boosting algorithm demonstrates the best performance, with high predictive accuracy and low error. Additionally, the LIME method is used to perform explainability analysis on the best model, revealing the influence of features such as cholesterol levels, blood pressure, blood glucose, and age on cardiovascular disease prediction outcomes. The study shows that machine learning-based cardiovascular disease prediction models have promising application prospects, particularly in early screening and risk assessment.