Quality and Dependability of ChatGPT and DingXiangYuan Forums for Remote Orthopedic Consultations: Comparative Analysis (Preprint)

Abstract

The widespread use of artificial intelligence, such as ChatGPT (OpenAI), is transforming sectors, including health care, while separate advancements of the internet have enabled platforms such as China’s DingXiangYuan to offer remote medical services.

This study evaluates ChatGPT-4’s responses against those of professional health care providers in telemedicine, assessing artificial intelligence’s capability to support the surge in remote medical consultations and its impact on health care delivery.

We sourced remote orthopedic consultations from “Doctor DingXiang,” with responses from its certified physicians as the control and ChatGPT’s responses as the experimental group. In all, 3 blindfolded, experienced orthopedic surgeons assessed responses against 7 criteria: “logical reasoning,” “internal information,” “external information,” “guiding function,” “therapeutic effect,” “medical knowledge popularization education,” and “overall satisfaction.” We used Fleiss κ to measure agreement among multiple raters.

Initially, consultation records for a cumulative count of 8 maladies (equivalent to 800 cases) were gathered. We ultimately included 73 consultation records by May 2023, following primary and rescreening, in which no communication records containing private information, images, or voice messages were transmitted. After statistical scoring, we discovered that ChatGPT’s “internal information” score (mean 4.61, SD 0.52 points vs mean 4.66, SD 0.49 points; <i>P</i>=.43) and “therapeutic effect” score (mean 4.43, SD 0.75 points vs mean 4.55, SD 0.62 points; <i>P</i>=.32) were lower than those of the control group, but the differences were not statistically significant. ChatGPT showed better performance with a higher “logical reasoning” score (mean 4.81, SD 0.36 points vs mean 4.75, SD 0.39 points; <i>P</i>=.38), “external information” score (mean 4.06, SD 0.72 points vs mean 3.92, SD 0.77 points; <i>P</i>=.25), and “guiding function” score (mean 4.73, SD 0.51 points vs mean 4.72, SD 0.54 points; <i>P</i>=.96), although the differences were not statistically significant. Meanwhile, the “medical knowledge popularization education” score of ChatGPT was better than that of the control group (mean 4.49, SD 0.67 points vs mean 3.87, SD 1.01 points; <i>P</i>&lt;.001), and the difference was statistically significant. In terms of “overall satisfaction,” the difference was not statistically significant between the groups (mean 8.35, SD 1.38 points vs mean 8.37, SD 1.24 points; <i>P</i>=.92). According to how Fleiss κ values were interpreted, 6 of the control group’s score points were classified as displaying “fair agreement” (<i>P</i>&lt;.001), and 1 was classified as showing “substantial agreement” (<i>P</i>&lt;.001). In the experimental group, 3 points were classified as indicating “fair agreement,” while 4 suggested “moderate agreement” (<i>P</i>&lt;.001).

ChatGPT-4 matches the expertise found in DingXiangYuan forums’ paid consultations, excelling particularly in scientific education. It presents a promising alternative for remote health advice. For health care professionals, it could act as an aid in patient education, while patients may use it as a convenient tool for health inquiries.