Explainable Machine Learning Models for Healthcare Diagnosis and Prediction

Abstract

The adoption of machine learning in healthcare has improved diagnostic accuracy but raised concerns regarding interpretability. This study presents an explainable ML framework integrating decision trees and SHAP (SHapley Additive exPlanations) values to provide transparent predictions. The proposed system enhances trust among medical professionals by clearly explaining feature contributions. Evaluation on benchmark healthcare datasets shows improved prediction performance while maintaining interpretability, making it suitable for clinical decision support systems.