Towards Explainable Conversational AI for Early Diagnosis with Large Language Models

TL;DR

This paper presents a diagnostic chatbot powered by GPT-4o that enhances explainability and interactivity in healthcare diagnostics, achieving high accuracy and transparency compared to traditional models.

Contribution

Introduces an LLM-based diagnostic chatbot utilizing Retrieval-Augmented Generation and explainable AI techniques for improved healthcare diagnostics.

Findings

Achieved 90% accuracy in diagnosis

Top-3 accuracy reached 100%

Enhanced transparency with Chain-of-Thought prompting

Abstract

Healthcare systems around the world are grappling with issues like inefficient diagnostics, rising costs, and limited access to specialists. These problems often lead to delays in treatment and poor health outcomes. Most current AI and deep learning diagnostic systems are not very interactive or transparent, making them less effective in real-world, patient-centered environments. This research introduces a diagnostic chatbot powered by a Large Language Model (LLM), using GPT-4o, Retrieval-Augmented Generation, and explainable AI techniques. The chatbot engages patients in a dynamic conversation, helping to extract and normalize symptoms while prioritizing potential diagnoses through similarity matching and adaptive questioning. With Chain-of-Thought prompting, the system also offers more transparent reasoning behind its diagnoses. When tested against traditional machine learning models like Naive Bayes, Logistic Regression, SVM, Random Forest, and KNN, the LLM-based system delivered impressive results, achieving an accuracy of 90% and Top-3 accuracy of 100%. These findings offer a promising outlook for more transparent, interactive, and clinically relevant AI in healthcare.