Explainable LightGBM Approach for Predicting Myocardial Infarction Mortality

TL;DR

This paper presents an explainable LightGBM-based model for predicting myocardial infarction mortality, demonstrating high accuracy and interpretability through feature analysis with SHAP, outperforming existing methods.

Contribution

It introduces an explainable LightGBM approach that effectively handles raw patient data and provides insights into feature importance for mortality prediction.

Findings

LightGBM achieved 91.2% F1-score and 91.8% accuracy without data preprocessing.

The approach outperformed other machine learning models in mortality prediction.

SHAP analysis revealed key features influencing predictions.

Abstract

Myocardial Infarction is a main cause of mortality globally, and accurate risk prediction is crucial for improving patient outcomes. Machine Learning techniques have shown promise in identifying high-risk patients and predicting outcomes. However, patient data often contain vast amounts of information and missing values, posing challenges for feature selection and imputation methods. In this article, we investigate the impact of the data preprocessing task and compare three ensembles boosted tree methods to predict the risk of mortality in patients with myocardial infarction. Further, we use the Tree Shapley Additive Explanations method to identify relationships among all the features for the performed predictions, leveraging the entirety of the available data in the analysis. Notably, our approach achieved a superior performance when compared to other existing machine learning approaches, with an F1-score of 91,2% and an accuracy of 91,8% for LightGBM without data preprocessing.