UMass-BioNLP at MEDIQA-M3G 2024: DermPrompt - A Systematic Exploration of Prompt Engineering with GPT-4V for Dermatological Diagnosis

Parth Vashisht, Abhilasha Lodha, Mukta Maddipatla, Zonghai Yao, Avijit Mitra, Zhichao Yang, Sunjae Kwon, Junda Wang, Hong Yu


Abstract
This paper presents our team’s participation in the MEDIQA-ClinicalNLP 2024 shared task B. We present a novel approach to diagnosing clinical dermatology cases by integrating large multimodal models, specifically leveraging the capabilities of GPT-4V under a retriever and a re-ranker framework. Our investigation reveals that GPT-4V, when used as a retrieval agent, can accurately retrieve the correct skin condition 85% of the time using dermatological images and brief patient histories. Additionally, we empirically show that Naive Chain-of-Thought (CoT) works well for retrieval while Medical Guidelines Grounded CoT is required for accurate dermatological diagnosis. Further, we introduce a Multi-Agent Conversation (MAC) framework and show it’s superior performance and potential over the best CoT strategy. The experiments suggest that using naive CoT for retrieval and multi-agent conversation for critique-based diagnosis, GPT-4V can lead to an early and accurate diagnosis of dermatological conditions. The implications of this work extend to improving diagnostic workflows, supporting dermatological education, and enhancing patient care by providing a scalable, accessible, and accurate diagnostic tool.
Anthology ID:
2024.clinicalnlp-1.50
Volume:
Proceedings of the 6th Clinical Natural Language Processing Workshop
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Tristan Naumann, Asma Ben Abacha, Steven Bethard, Kirk Roberts, Danielle Bitterman
Venues:
ClinicalNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
502–525
Language:
URL:
https://aclanthology.org/2024.clinicalnlp-1.50
DOI:
10.18653/v1/2024.clinicalnlp-1.50
Bibkey:
Cite (ACL):
Parth Vashisht, Abhilasha Lodha, Mukta Maddipatla, Zonghai Yao, Avijit Mitra, Zhichao Yang, Sunjae Kwon, Junda Wang, and Hong Yu. 2024. UMass-BioNLP at MEDIQA-M3G 2024: DermPrompt - A Systematic Exploration of Prompt Engineering with GPT-4V for Dermatological Diagnosis. In Proceedings of the 6th Clinical Natural Language Processing Workshop, pages 502–525, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
UMass-BioNLP at MEDIQA-M3G 2024: DermPrompt - A Systematic Exploration of Prompt Engineering with GPT-4V for Dermatological Diagnosis (Vashisht et al., ClinicalNLP-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.clinicalnlp-1.50.pdf