Fine-Tuning DialoGPT on Common Diseases in Rural Nepal for Medical Conversations

TL;DR

This paper demonstrates that fine-tuning a lightweight, offline-capable dialogue model on a domain-specific dataset can produce coherent and medically relevant conversations for rural healthcare support in resource-limited settings.

Contribution

It introduces a method for adapting DialoGPT to rural medical dialogues using a synthetic dataset, enabling offline, domain-specific healthcare conversations.

Findings

Model produces coherent, relevant responses

Effective domain adaptation with limited data

Supports offline deployment in rural healthcare

Abstract

Conversational agents are increasingly being explored to support healthcare delivery, particularly in resource-constrained settings such as rural Nepal. Large-scale conversational models typically rely on internet connectivity and cloud infrastructure, which may not be accessible in rural areas. In this study, we fine-tuned DialoGPT, a lightweight generative dialogue model that can operate offline, on a synthetically constructed dataset of doctor-patient interactions covering ten common diseases prevalent in rural Nepal, including common cold, seasonal fever, diarrhea, typhoid fever, gastritis, food poisoning, malaria, dengue fever, tuberculosis, and pneumonia. Despite being trained on a limited, domain-specific dataset, the fine-tuned model produced coherent, contextually relevant, and medically appropriate responses, demonstrating an understanding of symptoms, disease context, and empathetic communication. These results highlight the adaptability of compact, offline-capable dialogue models and the effectiveness of targeted datasets for domain adaptation in low-resource healthcare environments, offering promising directions for future rural medical conversational AI.