ArticleArchives of orthopaedic and trauma surgery2025
A comparative analysis of ChatGPT and Google in providing quality and clinical relevance of responses to patients' frequently asked questions on robotic-assisted total knee arthroplasty.
Article in Archives of orthopaedic and trauma surgery, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
1 citing paper in PubMed.
- Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
6 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
introductionThe purpose of this study was to identify the most frequent questions a patient might encounter in an internet search about robotic-assisted total knee arthroplasty (RATKA), and to identify and categorize the answers to these questions to assess the suitability of Chat Generative Pre-Trained Transformer (ChatGPT) and Google search engine as an online health information source for patients.
methodsThe 20 most frequently asked questions (FAQs) were identified by entering the search term "Robot-Assisted Total Knee Replacement" into both Google Search and ChatGPT-4. For Google, a clean search was performed, and the 20 FAQs were extracted from the "People also ask" section. For ChatGPT-4, a specific prompt was used to generate the 20 most frequently asked questions. All identified questions, along with the corresponding answers and cited references, were systematically recorded. A modified version of the Rothwell system was used to categorize questions into 10 subtopics. Each reference was categorized into the following groups: commercial, academic, medical practice, single surgeon personal, or social media. The questions and sources obtained from ChatGPT and Google were compared using Fisher's exact test.
resultsThe percentage distribution of questions by category between Google and ChatGPT was as follows: indications/management (15% vs. 25%), technical details (35% vs. 30%), evaluation of surgery (0% vs. 0%), risks/complications (5% vs. 5%), restrictions (10% vs. 0%), specific activities (15% vs. 5%), timeline of recovery (10% vs. 20%), pain (0% vs. 5%), longevity (0% vs. 0%), and cost (10% vs. 10%). Answers to questions were more frequently sourced from academic websites in ChatGPT compared to Google (70% vs. 20%; p-value = 0.0025).
conclusionChatGPT offers a promising alternative to traditional search engines for patient education, particularly in the context of preparing for RATKA. Compared to Google, ChatGPT provided significantly fewer references to commercial content and offered responses that were more aligned with academic sources. LEVEL OF EVIDENCE: Level IV, Survey study Internet sources.
Indexed as
Identifiers
41105265What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.