Article

Structured Clinical Reasoning Prompt Enhances LLM’s Diagnostic Capabilities in Diagnosis Please Quiz Cases

2024-09-03

Abstract excerpt

<h4>Background</h4> Large Language Models (LLMs) show promise in medical diagnosis, but their performance varies with prompting. Recent studies suggest that modifying prompts may enhance diagnostic capabilities. <h4>Objective</h4> This study aimed to test whether a prompting approach that aligns with general clinical reasoning methodology—specifically, separating processes of summarizing clinical information and...

Topics

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

Identifiers and source

Literature Corpus work: 0f840ede-da16-563d-93ee-a0e170faf15b
DOI: 10.1101/2024.09.01.24312894

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Structured Clinical Reasoning Prompt Enhances LLM’s Diagnostic Capabilities in Diagnosis Please Quiz CasesDOI 10.1101/2024.09.01.24312894Read

The effect of medical explanations from large language models on diagnostic accuracy in radiologySemantic proximity Read

The effect of medical explanations from large language models on diagnostic decisions in radiologySemantic proximity Read

“This is a quiz” Premise Input: A Key to Unlocking Higher Diagnostic Accuracy in Large Language ModelsSemantic proximity Read

RAD-CaseBookLLM-08: An open-access dataset of structured large language model–generated radiology differential diagnosis teachingsSemantic proximity Read

RAD-CaseBookLLM-08: An open-access dataset of structured large language model–generated radiology differential diagnosis teachingsSemantic proximity Read

Diagnostic Performances of GPT-4o, Claude 3 Opus, and Gemini 1.5 Pro in “Diagnosis Please” CasesSemantic proximity Read

Large Language Models for Classifying Usual Interstitial Pneumonia from Radiology Reports: Native Reasoning Versus Structured PromptingSemantic proximity Read

Prompting is All You Need: How to Make LLMs More Helpful for Clinical Decision SupportSemantic proximity Read

Comparative Analysis of Multimodal Large Language Models GPT-4o and o1 vs Clinicians in Clinical Case Challenge QuestionsSemantic proximity Read

SHIELD: An AI Framework for Skeletal Health Intelligence and Early Lesion Detection to Improve Orthopedic ReferralsSemantic proximity Read

On the limitations of large language models in clinical diagnosisSemantic proximity Read

MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questionsSemantic proximity Read