CoChat

Capacity of ChatGPT to Identify Guideline-Based Treatments for Advanced Solid Tumors

Open access
Schulte, Brian · 2023 · Cureus
Cited by 50

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

Abstract

BACKGROUND: ChatGPT, created by OpenAI, is a large language model which has become the fastest growing consumer application in history, recognized for its expansive knowledge of varied subjects. The field of oncology is highly specialized and requires nuanced understanding of medications and conditions. Herein, we sought to better qualify the ability of ChatGPT to name applicable treatments for patients with advanced solid cancers. METHODS: This observational study was conducted utilizing ChatGPT. The capacity of ChatGPT to tabulate appropriate systemic therapies for new diagnoses of advanced solid malignancies was ascertained through standardized prompts. A ratio of those medications listed by ChatGPT to those suggested in the National Comprehensive Cancer Network (NCCN) guidelines was produced and called the valid therapy quotient (VTQ). Additional descriptive analyses of the VTQ and its association with incidence and type of treatment were performed. RESULTS: Some 51 distinct diagnoses were utilized within this experiment. ChatGPT was able to identify 91 distinct medications in response to prompts related to advanced solid tumors. The overall VTQ is 0.77. In all cases, ChatGPT was able to provide at least one example of systemic therapy suggested by the NCCN. There was a weak association between incidence of each malignancy and the VTQ. CONCLUSION: The capacity of ChatGPT to identify medications used to treat advanced solid tumors indicates a level of concordance with the NCCN guidelines. As it stands, the role of ChatGPT to assist oncologists and patients in treatment decision making remains unknown. Nonetheless, in future iterations, it may be anticipated that accuracy and consistency in this domain will improve, and further studies will be needed to better quantify its capabilities.

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 · 10.7759/cureus.37938

Cites

9 of 9 references verified0 citation errors · 0 not checkable

Statistics

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

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

Cited by

See all 50

Metadata

Authors
Schulte, B.
Venue
Cureus
Published
2023-04-21
Volume
15
Issue
4
Pages
e37938-e37938
ISSN
2168-8184 (ISSN-L)
OpenAlex
W4366683734
Cited by
50
References
9
FWCI
1.73
Type
journal article
Language
en
Open access
diamond

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

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.