ChatGPT-HealthPrompt. Harnessing the Power of XAI in Prompt-Based Healthcare Decision Support using ChatGPT

TL;DR

This paper introduces a novel prompt-based approach using ChatGPT for healthcare decision support, integrating domain knowledge from interpretable models to improve binary classification, especially in data-scarce scenarios.

Contribution

It presents a new method of incorporating domain knowledge into prompt design for LLMs, enhancing clinical decision-making in low-data environments.

Findings

Effective prompt strategies improve classification accuracy.

Domain knowledge integration enhances interpretability.

ChatGPT outperforms traditional models in data-scarce settings.

Abstract

This study presents an innovative approach to the application of large language models (LLMs) in clinical decision-making, focusing on OpenAI's ChatGPT. Our approach introduces the use of contextual prompts-strategically designed to include task description, feature description, and crucially, integration of domain knowledge-for high-quality binary classification tasks even in data-scarce scenarios. The novelty of our work lies in the utilization of domain knowledge, obtained from high-performing interpretable ML models, and its seamless incorporation into prompt design. By viewing these ML models as medical experts, we extract key insights on feature importance to aid in decision-making processes. This interplay of domain knowledge and AI holds significant promise in creating a more insightful diagnostic tool. Additionally, our research explores the dynamics of zero-shot and few-shot prompt learning based on LLMs. By comparing the performance of OpenAI's ChatGPT with traditional supervised ML models in different data conditions, we aim to provide insights into the effectiveness of prompt engineering strategies under varied data availability. In essence, this paper bridges the gap between AI and healthcare, proposing a novel methodology for LLMs application in clinical decision support systems. It highlights the transformative potential of effective prompt design, domain knowledge integration, and flexible learning approaches in enhancing automated decision-making.