Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine
Abstract 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 s...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-01-01
|
Series: | npj Digital Medicine |
Online Access: | https://doi.org/10.1038/s41746-024-01010-1 |
_version_ | 1797276276363362304 |
---|---|
author | Thomas Savage Ashwin Nayak Robert Gallo Ekanath Rangan Jonathan H. Chen |
author_facet | Thomas Savage Ashwin Nayak Robert Gallo Ekanath Rangan Jonathan H. Chen |
author_sort | Thomas Savage |
collection | DOAJ |
description | Abstract 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. |
first_indexed | 2024-03-07T15:25:55Z |
format | Article |
id | doaj.art-949bf0bf6eff4ff1851bbf287b8ad038 |
institution | Directory Open Access Journal |
issn | 2398-6352 |
language | English |
last_indexed | 2024-03-07T15:25:55Z |
publishDate | 2024-01-01 |
publisher | Nature Portfolio |
record_format | Article |
series | npj Digital Medicine |
spelling | doaj.art-949bf0bf6eff4ff1851bbf287b8ad0382024-03-05T17:06:39ZengNature Portfolionpj Digital Medicine2398-63522024-01-01711710.1038/s41746-024-01010-1Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicineThomas Savage0Ashwin Nayak1Robert Gallo2Ekanath Rangan3Jonathan H. Chen4Department of Medicine, Stanford UniversityDepartment of Medicine, Stanford UniversityPalo Alto Veterans Affairs Medical CenterDepartment of Medicine, Stanford UniversityDepartment of Medicine, Stanford UniversityAbstract 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.https://doi.org/10.1038/s41746-024-01010-1 |
spellingShingle | Thomas Savage Ashwin Nayak Robert Gallo Ekanath Rangan Jonathan H. Chen Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine npj Digital Medicine |
title | Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine |
title_full | Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine |
title_fullStr | Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine |
title_full_unstemmed | Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine |
title_short | Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine |
title_sort | diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine |
url | https://doi.org/10.1038/s41746-024-01010-1 |
work_keys_str_mv | AT thomassavage diagnosticreasoningpromptsrevealthepotentialforlargelanguagemodelinterpretabilityinmedicine AT ashwinnayak diagnosticreasoningpromptsrevealthepotentialforlargelanguagemodelinterpretabilityinmedicine AT robertgallo diagnosticreasoningpromptsrevealthepotentialforlargelanguagemodelinterpretabilityinmedicine AT ekanathrangan diagnosticreasoningpromptsrevealthepotentialforlargelanguagemodelinterpretabilityinmedicine AT jonathanhchen diagnosticreasoningpromptsrevealthepotentialforlargelanguagemodelinterpretabilityinmedicine |