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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Vashisht, Parth, Lodha, Abhilasha, Maddipatla, Mukta, Yao, Zonghai, Mitra, Avijit, Yang, Zhichao, Wang, Junda, Kwon, Sunjae, Yu, Hong
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914788899028992
author Vashisht, Parth
Lodha, Abhilasha
Maddipatla, Mukta
Yao, Zonghai
Mitra, Avijit
Yang, Zhichao
Wang, Junda
Kwon, Sunjae
Yu, Hong
author_facet Vashisht, Parth
Lodha, Abhilasha
Maddipatla, Mukta
Yao, Zonghai
Mitra, Avijit
Yang, Zhichao
Wang, Junda
Kwon, Sunjae
Yu, Hong
contents This paper presents our team's participation in the MEDIQA-ClinicalNLP2024 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 its 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_17749
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle UMass-BioNLP at MEDIQA-M3G 2024: DermPrompt -- A Systematic Exploration of Prompt Engineering with GPT-4V for Dermatological Diagnosis
Vashisht, Parth
Lodha, Abhilasha
Maddipatla, Mukta
Yao, Zonghai
Mitra, Avijit
Yang, Zhichao
Wang, Junda
Kwon, Sunjae
Yu, Hong
Artificial Intelligence
Computation and Language
This paper presents our team's participation in the MEDIQA-ClinicalNLP2024 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 its 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.
title UMass-BioNLP at MEDIQA-M3G 2024: DermPrompt -- A Systematic Exploration of Prompt Engineering with GPT-4V for Dermatological Diagnosis
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2404.17749