Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Minerva Anestesiologica

Comparative analysis of large language models and clinician responses in patient blood management knowledge

View Full Paper
Ask AI
Bookmark
Share

Authors

FTFelix TranPMPatrick MeybohmLBLea Blum

Discussion

Loading...

Member takes

Overview

Observational analysis shows LLMs outperform clinicians in patient blood management knowledge, suggesting potential utility.

Key Points

  • ChatGPT-4o achieved 96.4% accuracy in PBM questions, outperforming clinicians who scored 76.5%.
  • In frequently asked patient questions, ChatGPT-4o provided perfect answers, while clinicians only managed 62.0%.
  • The evaluation involved 40 questions and compared responses from LLMs and clinicians at two university hospitals.
  • While LLMs showed strong responses, clinician verification is essential in critical situations for patient safety.

Cite This Study

Tran et al. (2025) studied this question.

synapsesocial.com/papers/68c1b34d54b1d3bfb60e9a7bhttps://doi.org/10.23736/s0375-9393.25.19014-7
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Performance of several large language models when answering common patient questions about type 1 diabetes in children: accuracy, comprehensibility and practicality2025 · 7 citations
  2. 2Comparative Quality Assessment of Artificial Intelligence in Patient Education on Platelet-Rich Plasma (PRP) Therapy2026
  3. 3Comparing Performance of Large Language Model-Based Tools on Patient-Driven Glaucoma Inquiries2025
  4. 4Can Large Language Models Reliably Educate Patients After Kyphoplasty? A Clinician-Rated Comparative Study of ChatGPT and Gemini2026
  5. 5Assessing the Responses of Large Language Models (ChatGPT-4, Gemini, and Microsoft Copilot) to Frequently Asked Questions in Breast Imaging: A Study on Readability and Accuracy2024 · 44 citations