Quality of AI-Generated Postoperative Patient Education After Minimally Invasive Gynecologic Surgery: A Comparative Analysis
OA: closed
AI-generated summary
This study compared the quality of AI-generated patient education materials for post-operative care following minimally invasive gynecologic surgery.
One-sentence paraphrase of the abstract; not a substitute for reading it. No clinical advice. How this works
Abstract
STUDY OBJECTIVE: To compare the quality of AI-generated responses to gynecologic postoperative questions with educational materials published by professional societies.
DESIGN: Comparative analysis of published and AI-generated patient education relating to hysterectomy, hysteroscopy, laparoscopy, and management of conditions such as endometriosis and abnormal uterine bleeding.
SETTING: Questions were selected from gynecologic professional society materials and asked to AI platforms: ChatGPT and Google Gemini.
PARTICIPANTS: None.
INTERVENTION: Two expert reviewers scored blinded responses for accuracy (evidence-based and clinically appropriate), comprehensiveness (adequacy of information to address patient questions), and understandability (clarity for a typical patient) using a Likert 1-5 scale. Inclusivity was scored as a binary outcome. Readability and word count were also measured.
MEASUREMENTS AND MAIN RESULTS: A total of 20 questions were chosen for comparison. ChatGPT generated the most comprehensive responses (4.675, p < .05), while Google Gemini generated the most accurate (4.975, p < .05) but least understandable responses (3.2, p < .05). Professional society materials received lower accuracy (4.475, p < .05) and comprehensiveness (2.725, p < .05) relative to AI-generated responses, but had the highest readability (median SMOG 11.275; Flesch-Kincaid score 9.005, p < .05). ChatGPT responses were the longest, while professional society materials were the shortest (245.2 vs. 101 words, p < .05). There were no significant differences in inclusivity across sources (p = .098).
CONCLUSION: AI platforms provide accurate and comprehensive responses to commonly asked gynecologic postoperative questions. While professional society materials remained the most readable, all sources exceeded the recommended sixth to eighth grade reading level. These findings highlight that AI could be a powerful tool in enhancing postoperative education and setting clearer expectations for gynecologic postoperative patients.
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. This is a recent paper (2026) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.
Source provenance
- europepmc
- last seen: 2026-09-05T06:14:40.014199+00:00
- pubmed
- last seen: 2026-09-05T06:09:49.193210+00:00
- unpaywall
- last seen: 2026-09-05T06:29:56.012541+00:00