ArticleIndian journal of orthopaedics2025
Is ChatGPT more Humane than Humans?-Accuracy, Relevance and humanness of the Answers Provided by ChatGPT for Patient Education for Total Knee Replacement.
Article in Indian journal of orthopaedics, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
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
0 citing papers in PubMed.
No citing paper in PubMed yet.
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
Aim: This study aimed to assess the reliability of orthopaedic information provided by ChatGPT in response to common patient inquiries and concerns related to Total Joint Replacement surgery, focusing on preventing the dissemination of potentially harmful medical advice. Method: This qualitative exploratory case study was conducted at a tertiary care centre hospital. Ten common questions patients pose to orthopaedic surgeons when considering knee arthroplasty were formulated and presented independently to an Orthopaedic Consultant, Associate Consultant, a Fellow in Joint Replacement surgery, and ChatGPT. For review, the answers were submitted to a panel of three orthopaedic surgeons specializing in arthroplasty. They were scored based on accuracy, relevance, and usefulness, with a maximum possible score of 100.0 points, allowing for 0.5-point increments. They were also asked to identify which answers were from chat GPT, not humans. Results: ChatGPT exhibited the highest total aggregate score of 232.0 points out of a maximum of 300.0 points, surpassing the scores of the human participants (Participant 1: 197.0 points; Participant 2: 227.5 points; Participant 3: 220.5 points). Furthermore, two out of three panel specialists rated ChatGPT the highest. When comparing the average scores for ChatGPT and the human participants for each question, ChatGPT outperformed the human participants in 8 out of 10 questions. Out of the 120 encounter instances, the evaluator could only point correctly that the response was from ChatGPT response 14 times (11.66%). Conclusion: This study highlights the utility and limitations of ChatGPT in the medical field-ChatGPT exhibits great potential in assisting doctors and surgeons in patient care by providing accurate and relevant information. The study also demonstrated that the answers seemed indistinguishable from humans in most cases. In the current landscape of ChatGPT and other AI technologies, their integration in the medical field should be viewed as complementary to human expertise, which must be leveraged for the greater good.
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.