This research introduces an innovative two-stage architecture for fine-tuning large language models specifically for medical question answering.

• First stage: Classify incoming medical questions using RoBERTa and BERT models
• Second stage: Provide predefined, reliable answers based on classification results
• Improves accuracy and efficiency of medical AI responses
• Models trained on curated medical datasets from Healthline.com

This research advances healthcare AI by creating more reliable information systems for patient queries, helping reduce misinformation and improving access to trustworthy medical guidance.

A Comprehensive Study on Fine-Tuning Large Language Models for Medical Question Answering Using Classification Models and Comparative Analysis