ArticleDigital health
Evaluating ChatGPT responses to frequently asked patient questions regarding periprosthetic joint infection after total hip and knee arthroplasty.
Article in Digital health. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 9 papers.
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
9 citing papers in PubMed.
- The potential of large language models to address patients' preoperative questions before anterior cervical discectomy and fusion surgery.Annals of translational medicine · 2026Article
- [Use of artificial intelligence for next-gen anamnesis and communication in orthopedics & trauma surgery : From chatbots to ambient intelligence].Orthopadie (Heidelberg, Germany) · 2026Review
- Evaluation of ChatGPT's responses to frequently asked questions from osteosarcoma patients: A descriptive cross-sectional study.Medicine · 2026Article
- Evaluation of ChatGPT-5.2 responses to frequently asked questions about benign bone tumors.Frontiers in oncology · 2026Article
- A Comparative Analysis of GPT-3.5, GPT-4, GPT-4 Omni, Gemini Advanced, and Gemini 1.5 in Answering Total Knee Replacement-Related Questions.Orthopaedic journal of sports medicine · 2026Article
- To Self-Treat or Not to Self-Treat: Evaluating the Diagnostic, Advisory and Referral Effectiveness of ChatGPT Responses to the Most Common Musculoskeletal Disorders.Diagnostics (Basel, Switzerland) · 2025Article
- The assessment of ChatGPT-4's performance compared to expert's consensus on chronic lateral ankle instability.Journal of experimental orthopaedics · 2025Article
- Evaluation of ChatGPT Responses About Sexual Activity After Total Hip Arthroplasty: A Comparative Study with Observers of Different Experience Levels.Journal of clinical medicine · 2025Article
- Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
10 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Background: Patients access relevant information concerning their orthopaedic surgery resources through multiple information channels before presenting for clinical treatment. Recently, artificial intelligence (AI)-powered chatbots have become another source of information for patients. The currently developed AI chat technology ChatGPT (OpenAI LP) is an application for such purposes and it has been rapidly gaining popularity, including for patient education. This study sought to evaluate whether ChatGPT can correctly answer frequently asked questions (FAQ) regarding periprosthetic joint infection (PJI). Methods: Twelve FAQs about PJI after hip and knee arthroplasty were identified from the websites of fifteen international clinical expert centres. ChatGPT was confronted with these questions and its responses were analysed for their accuracy using an evidence-based approach by a multidisciplinary team. Responses were categorised in four groups: (1) Excellent response that did not require additional improvement; (2) Satisfactory responses that required a small amount of improvement; (3) Satisfactory responses that required moderate improvement; and (4) Unsatisfactory responses that required a large amount of improvement. Results: From the analysis of the responses given by the chatbot, no reply received an 'unsatisfactory' rating; one did not require any correction; and the majority of the responses required low (7 out of 12) or moderate (4 out of 12) clarification. Although a few responses required minimal clarification, the chatbot responses were generally unbiased and evidence-based, even when asked controversial questions. Conclusions: The AI-chatbot ChatGPT was able to effectively answer the FAQs of patients seeking information around PJI diagnosis and treatment. The given information was also written in a manner that can be assumed to be understandable by patients. The chatbot could be a valuable clinical tool for patient education and understanding around PJI treatment in the future. Further studies should evaluate its use and acceptance by patients with PJI.
Indexed as
Identifiers
What 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.