Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine
Диагностические подсказки, основанные на рассуждениях, выявляют потенциал интерпретируемости больших языковых моделей в медицине
2024-01-24
SCID: 54.1/ktr5r3n7
Discuss with AI
GPT-4clinical reasoningdiagnostic reasoning promptslarge language model interpretabilitymedical diagnosis
Figures from the paper
Abstract (AI)
One of the major barriers to using large language models (LLMs) in medicine is the perception they use uninterpretable methods to make clinical decisions that are inherently different from the cognitive processes of clinicians. In this manuscript we develop diagnostic reasoning prompts to study whether LLMs can imitate clinical reasoning while accurately forming a diagnosis. We find that GPT-4 can be prompted to mimic the common clinical reasoning processes of clinicians without sacrificing diagnostic accuracy. This is significant because an LLM that can imitate clinical reasoning to provide an interpretable rationale offers physicians a means to evaluate whether an LLMs response is likely correct and can be trusted for patient care. Prompting methods that use diagnostic reasoning have the potential to mitigate the "black box" limitations of LLMs, bringing them one step closer to safe and effective use in medicine.
Key Findings
1
Diagnostic reasoning prompting may mitigate the black-box limitation of LLMs and support safer, more effective medical use.
2
Diagnostic reasoning prompts were developed to assess whether large language models can imitate clinicians’ reasoning while reaching accurate diagnoses.
3
GPT-4 reproduced common clinical reasoning processes when prompted, without sacrificing diagnostic accuracy.
4
Reasoning-based prompts can provide interpretable rationales that help physicians evaluate the likely correctness and trustworthiness of LLM responses.
Research Object
GPT-4 as a large language model applied to medical diagnosis
Research Subject
The ability to imitate clinicians’ diagnostic reasoning while maintaining diagnostic accuracy and providing interpretable rationales
Publication Details
Publication Date
2024-01-24
Journal
Publisher
ISSN
Cited by
276
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai4
Large language models encode clinical knowledge2023
Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models2023
Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum2023
Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine2023