ArticleMedicine2026
Artificial intelligence-based patient information in rotator cuff injuries: A cross-sectional comparative study of ChatGPT and DeepSeek models.
Article in Medicine, 2026. 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
3 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
This study aimed to comparatively evaluate the performance of the chat generative pretrained transformer (ChatGPT) and DeepSeek artificial intelligence (AI) models in patient information about rotator cuff injuries. This cross-sectional comparative study was conducted in May 28, 2025 using ChatGPT-4o (OpenAI) and DeepSeek V3 (DeepSeek Inc.) models. Sixteen frequently asked questions related to rotator cuff injuries were posed to both the AI models. The responses were then independently assessed by 2 experienced orthopedic surgeons using the Journal of the American Medical Association (JAMA), response rating system, DISCERN, and 4-point Likert scales. In addition, the readability of the responses was analyzed using the Flesch-Kincaid Readability Score (FRES) and Flesch-Kincaid Grade Level. The primary outcome was overall information quality, secondary outcomes included JAMA benchmark adherence and readability metrics. None of the models met JAMA criteria. In terms of response rating system, there was no statistically significant difference between the 2 models (P >.05). DeepSeek demonstrated higher DISCERN scores compared to ChatGPT (50.12 vs 47.03), with a mean difference of 3.09 (95% CI: 1.58 to 4.61; P = .001). While there was no significant difference in accuracy, clarity, and consistency criteria between the 2 models in the 4-point Likert evaluation (P >.05), DeepSeek scored significantly higher than ChatGPT in the completeness criterion, with a mean difference of 0.75 (95% CI: 0.46 to 1.04; P = .001). In terms of readability, both models showed similar performance (FRES, P >.05; Flesch-Kincaid Grade Level, P >.05). Both AI models deliver satisfactory and clinically relevant information for rotator cuff injury patient education. Although DeepSeek was superior to ChatGPT in terms of completeness of patient information regarding rotator cuff injuries, the results were similar for the other criteria. The responses from both the AI tools were considered promising. However, they require improvements in terms of adherence to scientific standards, transparency, citations, and readability.
Indexed as
Identifiers
What Socratic 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 Socratic graph.