Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.

Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine

Open access

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41746-024-01010-1

Cites

29 of 29 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 GPT 3.5 CoT and diagnostic reasoning rationale examples. Example GPT-3.5 rationales responding to a traditional CoT prompt as well as diagnostic reasoning prompts. LLM response and rationale results for the entire test set can be found in Supplementary Information 1.
Fig. 1 GPT 3.5 CoT and diagnostic reasoning rationale examples. Example GPT-3.5 rationales responding to a traditional CoT prompt as well as diagnostic reasoning prompts. LLM response and rationale results for the entire test set can be found in Supplementary Information 1.CC BY · PubMed Central
Fig. 2 GPT 4 CoT and diagnostic reasoning rationale examples. Example GPT-4 rationales responding to the question posed in Fig. 1. LLM response and rationale results for the entire test set can be found in Supplementary Information 1.
Fig. 2 GPT 4 CoT and diagnostic reasoning rationale examples. Example GPT-4 rationales responding to the question posed in Fig. 1. LLM response and rationale results for the entire test set can be found in Supplementary Information 1.CC BY · PubMed Central
Fig. 3 Proposed LLM workflow. a Current LLM workflow. b Proposed LLM workflow.
Fig. 3 Proposed LLM workflow. a Current LLM workflow. b Proposed LLM workflow.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

1 more claim about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 22 references

Research works printed but not linked: 2

  1. Case records of the Massachusetts General Hospital articles. 2020-2023. N. Engl. J. Med. Accessed: May 2023. https://www.nejm.org/medical-articles/case-records-of-the-massachusetts-general-hospital.
  2. UpToDate: industry-leading clinical decision support. Wolters Kluwer. Accessed: June 2023. https://www.wolterskluwer.com/en/solutions/uptodate.

Cited by

See all 267

Metadata

Authors
Savage, T., Nayak, A., Gallo, R., Rangan, E., & Chen, J. H.
Affiliations
  • Stanford Medicine (US)
  • Stanford University (US)
Corresponding author
Savage, Thomas
Venue
npj Digital Medicine
Published
2024-01-24
Volume
7
Issue
1
Pages
20-20
ISSN
2398-6352 (ISSN-L)
OpenAlex
W4391170193
Cited by
265
References
22
Citations by year
2026: 90 · 2025: 123 · 2024: 52
FWCI
24.77
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • arXiv (Cornell University) (cc-by)
Funders
  • U.S. Department of Veterans Affairs
  • Gordon and Betty Moore Foundation (#12409)
  • American Heart Association
  • Georgia Clinical and Translational Science Alliance (UL1TR003142)
  • National Institutes of Health (UL1TR003142)
  • National Institute on Drug Abuse (UG1DA015815)
  • National Institute of Allergy and Infectious Diseases (R01AI178121)
  • National Center for Advancing Translational Sciences
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
large language models, interpretability, clinical reasoning, GPT-4, diagnostic accuracy, black box problem, trust in AI, prompting, clinical decision support

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine. https://app.cochat.ai/papers/10.1038/s41746-024-01010-1
The paper
Savage, T., Nayak, A., Gallo, R., Rangan, E., & Chen, J. H. (2024). Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine. npj Digital Medicine. https://doi.org/10.1038/s41746-024-01010-1

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.