Can ChatGPT provide personalised responses for frequently asked questions regarding anterior cruciate ligament reconstruction?

IF 2 4区医学 Q3 ORTHOPEDICS

Knee Pub Date : 2025-07-17 DOI:10.1016/j.knee.2025.06.018

Siyuan Zhang, Isaac Jeremiah Chua, Zhen Chang Liang, Khang Chiang Pang

{"title":"Can ChatGPT provide personalised responses for frequently asked questions regarding anterior cruciate ligament reconstruction?","authors":"Siyuan Zhang, Isaac Jeremiah Chua, Zhen Chang Liang, Khang Chiang Pang","doi":"10.1016/j.knee.2025.06.018","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Chat Generative Pre-trained Transformer (ChatGPT) has the potential to enhance healthcare delivery by providing accessible, high-quality medical information. However, no prior studies have evaluated its ability to provide personalised and patient-specific information. Our study aims to evaluate ChatGPT’s ability to provide personalised responses to frequently asked questions (FAQs) regarding anterior cruciate ligament (ACL) reconstruction.</div></div><div><h3>Methods</h3><div>We curated a list of 13 clinically relevant FAQs regarding ACL reconstruction and created four distinct patient profiles with varying demographics, comorbidities and activity demands. Each patient profile was entered separately as prompts into the latest version of ChatGPT (GPT-4o). ChatGPT’s responses to the FAQs were recorded and assessed independently by two orthopaedic consultants who graded the responses on a scale of 0–2 (0, 1, 2) based on their accuracy and degree that it was personalised to each patient profile.</div></div><div><h3>Results</h3><div>ChatGPT performed well in providing accurate and personalised responses, achieving a mean overall accuracy score of 1.85 and mean overall personalisation score of 1.90. It was able to provide personalised and patient-specific responses by customizing its recommendations to cater to the situation of each distinct patient – achieving mean personalisation scores of 1.96, 1.88, 1.92 and 1.81 for the four respective patient profiles.</div></div><div><h3>Conclusions</h3><div>In our study, ChatGPT demonstrated the ability to adapt to distinct patient profiles and provide highly personalised responses regarding ACL reconstruction. Despite potential ethical and regulatory challenges, the ability of AI chatbots to deliver individualized information and counselling is an exciting new frontier in personalised medicine which warrants further research.</div></div>","PeriodicalId":56110,"journal":{"name":"Knee","volume":"56 ","pages":"Pages 495-502"},"PeriodicalIF":2.0000,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Knee","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0968016025001735","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ORTHOPEDICS","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Chat Generative Pre-trained Transformer (ChatGPT) has the potential to enhance healthcare delivery by providing accessible, high-quality medical information. However, no prior studies have evaluated its ability to provide personalised and patient-specific information. Our study aims to evaluate ChatGPT’s ability to provide personalised responses to frequently asked questions (FAQs) regarding anterior cruciate ligament (ACL) reconstruction.

Methods

We curated a list of 13 clinically relevant FAQs regarding ACL reconstruction and created four distinct patient profiles with varying demographics, comorbidities and activity demands. Each patient profile was entered separately as prompts into the latest version of ChatGPT (GPT-4o). ChatGPT’s responses to the FAQs were recorded and assessed independently by two orthopaedic consultants who graded the responses on a scale of 0–2 (0, 1, 2) based on their accuracy and degree that it was personalised to each patient profile.

Results

ChatGPT performed well in providing accurate and personalised responses, achieving a mean overall accuracy score of 1.85 and mean overall personalisation score of 1.90. It was able to provide personalised and patient-specific responses by customizing its recommendations to cater to the situation of each distinct patient – achieving mean personalisation scores of 1.96, 1.88, 1.92 and 1.81 for the four respective patient profiles.

Conclusions

In our study, ChatGPT demonstrated the ability to adapt to distinct patient profiles and provide highly personalised responses regarding ACL reconstruction. Despite potential ethical and regulatory challenges, the ability of AI chatbots to deliver individualized information and counselling is an exciting new frontier in personalised medicine which warrants further research.

查看原文本刊更多论文

ChatGPT能否为前交叉韧带重建的常见问题提供个性化的回答？

聊天生成预训练转换器（ChatGPT）具有通过提供可访问的高质量医疗信息来增强医疗保健服务的潜力。然而，之前没有研究评估其提供个性化和患者特定信息的能力。我们的研究旨在评估ChatGPT对前交叉韧带（ACL）重建的常见问题（FAQs）提供个性化回答的能力。方法：我们整理了关于ACL重建的13个临床相关常见问题，并创建了四种不同的患者资料，这些患者具有不同的人口统计学、合并症和活动需求。根据提示，将每个患者的资料单独输入最新版本的ChatGPT （gpt - 40）。ChatGPT对常见问题的回答由两名骨科顾问进行记录和独立评估，他们根据回答的准确性和个性化程度，将回答分为0 - 2（0,1,2）。结果schatgpt在提供准确和个性化的回答方面表现良好，平均总体准确性得分为1.85，平均总体个性化得分为1.90。它能够通过定制其建议来满足每个不同患者的情况，从而提供个性化和针对患者的响应——四种不同患者的平均个性化得分分别为1.96、1.88、1.92和1.81。在我们的研究中，ChatGPT显示出适应不同患者情况的能力，并为ACL重建提供高度个性化的响应。尽管存在潜在的伦理和监管挑战，但人工智能聊天机器人提供个性化信息和咨询的能力是个性化医疗领域一个令人兴奋的新领域，值得进一步研究。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Knee 医学-外科

CiteScore

3.80

自引率

5.30%

发文量

171

审稿时长

6 months

期刊介绍： The Knee is an international journal publishing studies on the clinical treatment and fundamental biomechanical characteristics of this joint. The aim of the journal is to provide a vehicle relevant to surgeons, biomedical engineers, imaging specialists, materials scientists, rehabilitation personnel and all those with an interest in the knee. The topics covered include, but are not limited to: • Anatomy, physiology, morphology and biochemistry; • Biomechanical studies; • Advances in the development of prosthetic, orthotic and augmentation devices; • Imaging and diagnostic techniques; • Pathology; • Trauma; • Surgery; • Rehabilitation.