PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
February 5, 2026MedicineOpen Access

A comparative study of ChatGPT 4o and DeepSeek in addressing CIED infection-related questions: Accuracy and readability assessment

View Full Paper
Ask AI
Bookmark
Share

Authors

CYChang YuJFJianhua FanYCYu Chen

Discussion

Loading...

Member takes

Overview

Comparative analysis evaluates accuracy and readability of AI responses to CIED infection questions, highlighting differences in output.

Key Points

  • This research aims to assess the accuracy and readability of two AI models, ChatGPT 4o and DeepSeek, regarding CIED infection-related queries.
  • Compared AI model responses to 30 questions based on American Heart Association guidelines.
  • Evaluated accuracy using a 4-level grading scale by cardiovascular experts.
  • Measured readability using Flesch-Kincaid Grade score and word-count metrics.
  • Tested responses under conditions without and with guideline prompts.
  • Both AI models answered 80% of questions accurately without guidelines, with ChatGPT providing more comprehensive answers.
  • With guidelines, ChatGPT's accuracy increased to 93.33% and DeepSeek's to 90%.
  • ChatGPT 4o had a higher word count (859.10) and more complex responses (Flesch-Kincaid Score of 15.40) than DeepSeek (526.27, score of 13.91).

Cite This Study

Yu et al. (2026) studied this question.

synapsesocial.com/papers/69843398f1d9ada3c1fb0da9https://doi.org/10.1097/md.0000000000047493
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. 1Accuracy of ChatGPT and DeepSeek in answering clinical questions from the 2025 Society for Cardiovascular Angiography & Interventions/Heart Rhythm Society left atrial appendage occlusion guidelines2026 · 1 citations
  2. 2Comparative informative capacity of artificial intelligence (AI)-powered chatbots in colorectal cancer: ChatGPT-4 versus DeepSeek2026
  3. 3Comparative evaluation of DeepSeek-V3.1 and ChatGPT-4o on POI assessment and management: An exploratory cross-sectional study with an international consensus guideline.2026
  4. 4Performance of ChatGPT and DeepSeek in the Management of Postprostatectomy Uri-nary Incontinence.2025 · 6 citations
  5. 5Evaluating the quality and readability of AI-generated information on adenomyosis: a comparative analysis of ChatGPT and deepseek regarding query-model consistency2026