Comparative Analysis of Machine Learning Algorithms for Heart Disease Classification and Integration with a Custom GPT-based Chatbot

This study investigates the integration of traditional machine learning (ML) algorithms with a custom GPT chatbot to enhance heart disease classification. Five ML models—K-Nearest Neighbors (KNN), Logistic Regression, Support Vector Machine (SVM), Random Forest, and XGBoost—are applied to a curated dataset for intent detection. After rigorous preprocessing and model training, performance is evaluated using standard classification metrics. The best-performing model is then used to drive the logic of a fine-tuned Custom GPT model, improving contextual understanding and response generation. The paper also details the GPT customization pipeline and highlights the improvements observed through hybrid ML-GPT integration.