Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Uludağ Üniversitesi Tıp Fakültesi DergisiOpen Access

Performance of Generative AI Models on Cardiology Practice in Emergency Service: A Pilot Evaluation of GPT-4.o and Gemini-1.5-Flash

View Full Paper
Ask AI
Bookmark
Share

Authors

ŞGŞeyda GünayDSDeniz SığırlıVDVahide Aslıhan Durak

Discussion

Loading...

Member takes

Overview

Pilot evaluation assesses GPT-4.o and Gemini-1.5-Flash for cardiac emergencies, revealing GPT-4.o's superiority in accuracy.

Key Points

  • GPT-4.o achieved a higher correct response rate of 65.7% compared to Gemini-1.5-Flash at 58.6%, highlighting a significant performance difference.
  • When analyzing question types, GPT-4.o fell short to Gemini-1.5-Flash in non-case questions, showcasing a nuanced performance profile.
  • The study utilized a set of 70 multiple choice questions to compare the diagnostic capabilities and readability of responses from both AI models.
  • Overall, both AI models performed better on easier questions and had varied success rates when images were included.

Cite This Study

Günay et al. (2025) studied this question.

synapsesocial.com/papers/68c23b08b210217d64782f6chttps://doi.org/10.32708/uutfd.1718121
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. 1Comparative performance of ChatGPT, Gemini, and final-year emergency medicine clerkship students in answering multiple-choice questions: implications for the use of AI in medical education2025 · 11 citations
  2. 2Performance of large language models ChatGPT and Gemini in child and adolescent psychiatry knowledge assessment2025
  3. 3Comparing Performance of Large Language Model-Based Tools on Patient-Driven Glaucoma Inquiries2025 · 2 citations
  4. 4Performance of ChatGPT, Gemini and DeepSeek for non-critical triage support using real-world conversations in emergency department2025
  5. 5A Comparative Analysis of Three Large Language Models in Answering Patient Queries on Otolaryngology Emergencies2025