This research introduces an explainable framework that uses large language models to match patients with appropriate medical professionals based on specific health needs.

• Creates a pointwise ranking system that evaluates doctor expertise for specific disease-treatment pairs
• Provides transparent explanations for recommendations, increasing patient trust and satisfaction
• Outperforms traditional recommendation systems by leveraging the contextual understanding of LLMs
• Addresses critical gaps in current medical matchmaking platforms that lack interpretability

This innovation could significantly improve patient experiences in telemedicine platforms by ensuring recommendations are both relevant and explainable, potentially reducing mismatches and improving healthcare outcomes.

Towards Explainable Doctor Recommendation with Large Language Models