Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
June 14, 2026Frontiers in Public HealthOpen Access

Evaluating the quality and readability of AI-generated information on adenomyosis: a comparative analysis of ChatGPT and deepseek regarding query-model consistency

View Full Paper
Ask AI
Bookmark
Share

Authors

LTLing TianYWYan WangMYMing-tao Yang

Discussion

Loading...

Member takes

Overview

Randomized trial compares readability and quality of adenomyosis information from ChatGPT and DeepSeek, implying the need for expert review before use.

Key Points

  • This study aims to evaluate and compare the readability, quality, and consistency of content generated about adenomyosis by ChatGPT and DeepSeek.
  • Obtained 25 high-frequency patient queries using Google Trends.
  • Processed each query through both ChatGPT and DeepSeek using two interaction modes: repetitions and independent cycles.
  • Assessed generated texts for readability using ARI, FRES, GFI, and quality using DISCERN and EQIP tools.
  • DeepSeek produced significantly better readability metrics than ChatGPT across both modes.
  • In the repetition mode, DeepSeek showed significant fluctuations, while ChatGPT’s outputs remained stable.
  • Both models yielded texts at a reading level suitable for undergraduates, which is higher than recommended for public health information.

Cite This Study

Tian et al. (2026) studied this question.

synapsesocial.com/papers/6a2e4429b1cc60ccdea8a16fhttps://doi.org/10.3389/fpubh.2026.1785229
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. 1Artificial intelligence‐generated patient information on shoulder instability remains suboptimal: DeepSeek outperforms ChatGPT in completeness of content while ChatGPT is more readable2026
  2. 2Evaluation of validity, reliability, and readability of AI chatbots for gestational diabetes mellitus: a multi-model comparative study2026 · 7 citations
  3. 3Information Quality of Artificial Intelligence Models in Bladder Cancer Patient Counseling: A Comparison of ChatGPT, Gemini, and DeepSeek: Descriptive Cross-Sectional Study2026
  4. 4Dr. Google to Dr. ChatGPT: assessing the content and quality of artificial intelligence-generated medical information on appendicitis2024 · 93 citations
  5. 5Quantifying Readability in Chatbot-Generated Medical Texts Using Classical Linguistic Indices: A Review2026