Appropriateness of Prostate Cancer Prevention and Screening Recommendations Obtained From ChatGPT-4

preprint OA: closed CC-BY-4.0
📄 Open PDF View at publisher

Abstract

Abstract Purpose: To evaluate the appropriateness of prostate cancer (PCa) prevention and screening recommendations provided by ChatGPT-4 Materials and Methods: We presented 32 questions regarding PCa prevention and screening using ChatGPT-4 based on National Comprehensive Cancer Network (NCCN) guidelines and clinical experience. Each question was asked to ChatGPT-4 three times, and the responses were graded by three expert urologists as reviewers. We evaluated sets of three responses generated by ChatGPT-4 in two distinct contexts: a general patient-facing platform and direct patient-to-clinician messages. A board certified/eligible urologist assessed each response set as appropriate, inappropriate, or unreliable. Results: In both contexts, ChatGPT-4 generated appropriate responses for 30 out of 32 (94%) questions, while one (3%) was considered inappropriate and one (3%) was deemed unreliable. Inappropriate response was related to a Gleason score of 5+3, while unreliable answer was linked to a Gleason score of 3+5 on prostate biopsy results. Conclusions: ChatGPT-4 is capable of providing appropriate counseling regarding disease prevention and screening for patients with PCa.

My notes (saved in your browser only)

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. The paper's references may be in our DB but unresolved to ``paper_id`` (resolution happens at ingest when the cited DOI matches a row we already have). Run the cross-source citation reconcile pass to retry.

Source provenance

europepmc
last seen: 2026-05-19T01:45:01.086888+00:00
unpaywall
last seen: 2026-06-02T02:00:03.124865+00:00
License: CC-BY-4.0