ArticleJournal of experimental orthopaedics2024
Enhancing patient information texts in orthopaedics: How OpenAI's 'ChatGPT' can help.
Article in Journal of experimental orthopaedics, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 11 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
11 citing papers in PubMed.
- Understandability and Actionability of Artificial Intelligence-Assisted Lymphedema Education Material in Patients Undergoing Breast Cancer Surgery: Expert Evaluation.Journal of clinical nursing · 2026Observational
- Gemini 1.5 Flash provides the most reliable content while ChatGPT-4o offers the highest readability for patient education on meniscal tears.Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA · 2026Article
- Benchmarking Open-Source Vision Language Models in Orthopedic In-Training Examination: A Comparison with Residents, Domain-Specific Evaluation, and Parameter Scaling.Clinics in orthopedic surgery · 2026Article
- ChatGPT models provide higher-quality but lower-readability responses than Google Gemini regarding anterior shoulder instability, with no added benefit of the orthopaedic expert plugin.Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA · 2026Article
- Revolutionizing patient care: assessing ai-created discharge education for total hip replacement patients.BMC medical education · 2025Article
- Generative artificial intelligence, large language models and ChatGPT in musculoskeletal Oncology: Current applications and future potential.Journal of clinical orthopaedics and trauma · 2025Article
- Artificial intelligence in medical and biological research: promise and perils of ChatGPT and DeepSeek in advancing healthcare.Turkish journal of biology = Turk biyoloji dergisi · 2025Review
- A Study of Orthopedic Patient Leaflets and Readability of AI-Generated Text in Foot and Ankle Surgery (SOLE-AI).Cureus · 2024Article
- Enhancing patient information texts in orthopaedics: How OpenAI's 'ChatGPT' can help.Journal of experimental orthopaedics · 2024Article
- How Successful Is AI in Developing Postsurgical Wound Care Education Material?Wound repair and regeneration : official publication of the Wound Healing Society [and] the European Tissue Repair SocietyArticle
- 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
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Purpose: The internet has become a primary source for patients seeking healthcare information, but the quality of online information, particularly in orthopaedics, often falls short. Orthopaedic surgeons now have the added responsibility of evaluating and guiding patients to credible online resources. This study aimed to assess ChatGPT's ability to identify deficiencies in patient information texts related to total hip arthroplasty websites and to evaluate its potential for enhancing the quality of these texts. Methods: In August 2023, 25 websites related to total hip arthroplasty were assessed using a standardized search on Google. Peer-reviewed scientific articles, empty pages, dictionary definitions, and unrelated content were excluded. The remaining 10 websites were evaluated using the hip information scoring system (HISS). ChatGPT was then used to assess these texts, identify deficiencies and provide recommendations. Results: The mean HISS score of the websites was 9.5, indicating low to moderate quality. However, after implementing ChatGPT's suggested improvements, the score increased to 21.5, signifying excellent quality. ChatGPT's recommendations included using simpler language, adding FAQs, incorporating patient experiences, addressing cost and insurance issues, detailing preoperative and postoperative phases, including references, and emphasizing emotional and psychological support. The study demonstrates that ChatGPT can significantly enhance patient information quality. Conclusion: ChatGPT's role in elevating patient education regarding total hip arthroplasty is promising. This study sheds light on the potential of ChatGPT as an aid to orthopaedic surgeons in producing high-quality patient information materials. Although it cannot replace human expertise, it offers a valuable means of enhancing the quality of healthcare information available online. Level of Evidence: Level IV.
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.