Article

Assessing GPT-4’s Diagnostic Accuracy with Darker Skin Tones: Underperformance and Implications

2024-04-19

Abstract excerpt

<h4>Introduction</h4> Conversational artificial intelligence (AI) language models like ChatGPT have emerged as promising tools for patients seeking medical information and guidance. However, their use raises ethical concerns due to the potential for inaccurate medical advice that could harm patients. Previous studies in dermatological machine-learning have highlighted that the underrepresentation of diverse skin t...

Topics

Open a Topic to create a Post that cites this publication.

Uncategorized literature

Identifiers and source

Literature Corpus work: 550f98de-285b-5443-8690-d012c5c50bcb
DOI: 10.1101/2024.04.17.24305928

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Assessing GPT-4’s Diagnostic Accuracy with Darker Skin Tones: Underperformance and ImplicationsDOI 10.1101/2024.04.17.24305928Read

A Retrospective Analysis of a Dermatology-Trained Multimodal Large Language Model's Diagnostic Accuracy in Pigmented Skin LesionsSemantic proximity Read

A Multimodal Large Reasoning Model For Fair and Interpretable Dermatological Diagnosis Across Skin TonesSemantic proximity Read

Evaluating the Diagnostic and Treatment Recommendation Capabilities of GPT-4 Vision in DermatologySemantic proximity Read

Evaluating General Vision-Language Models for Clinical MedicineSemantic proximity Read

AI Decision Support for Challenging Teledermatology Cases: MedGemma Performance in the Dermatology ECHO ProgramSemantic proximity Read

Case-level artificial intelligence for multi-photo teledermatology submissions: development and internal validation using patient-submitted dermatology imagesSemantic proximity Read

Assessing ChatGPT's Performance in Delineating Uveitis: An analysis of responses to real-world case presentationsSemantic proximity Read

Use of artificial intelligence as a diagnostic support tool for skin lesions in primary care: feasibility study in clinical practiceSemantic proximity Read

Multimodal Machine Learning Approach for Diagnosing Atopic DermatitisSemantic proximity Read

Multimodal Machine Learning Approach for Diagnosing Atopic DermatitisSemantic proximity Read

A Global Atlas of Digital Dermatology to Map Innovation and DisparitiesSemantic proximity Read

Evaluating GPT-4-based ChatGPT’s Clinical Potential on the NEJM QuizSemantic proximity Read