Evaluating ChatGPT responses to frequently asked patient questions regarding periprosthetic joint infection after total hip and knee arthroplasty

被引:1
|
作者
Hu, Xiaojun [1 ,2 ,3 ,4 ,5 ]
Niemann, Marcel [1 ,2 ,3 ,4 ]
Kienzle, Arne [1 ,2 ,3 ,4 ]
Braun, Karl [6 ]
Back, David Alexander [1 ,2 ,3 ,4 ]
Gwinner, Clemens [1 ,2 ,3 ,4 ]
Renz, Nora [1 ,2 ,3 ,4 ]
Stoeckle, Ulrich [1 ,2 ,3 ,4 ]
Trampuz, Andrej [1 ,2 ,3 ,4 ]
Meller, Sebastian [1 ,2 ,3 ,4 ]
机构
[1] Charite Univ Med Berlin, Ctr Musculoskeletal Surg, Augustenburger Pl 1, D-13353 Berlin, Germany
[2] Free Univ Berlin, Berlin, Germany
[3] Humboldt Univ, Berlin, Germany
[4] Berlin Inst Hlth, Berlin, Germany
[5] Seventh Peoples Hosp Chongqing, Dept Orthoped, Chongqing, Peoples R China
[6] Tech Univ Munich, Univ Hosp Rechts Isar, Dept Trauma Surg, Munich, Germany
来源
DIGITAL HEALTH | 2024年 / 10卷
关键词
Artificial intelligence; Chatbot; ChatGPT; OpenAI; patient education; periprosthetic joint infection; RISK-FACTORS; ANTIBIOTICS; REVISION; SURGERY;
D O I
10.1177/20552076241272620
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Background Patients access relevant information concerning their orthopaedic surgery resources through multiple information channels before presenting for clinical treatment. Recently, artificial intelligence (AI)-powered chatbots have become another source of information for patients. The currently developed AI chat technology ChatGPT (OpenAI LP) is an application for such purposes and it has been rapidly gaining popularity, including for patient education. This study sought to evaluate whether ChatGPT can correctly answer frequently asked questions (FAQ) regarding periprosthetic joint infection (PJI).Methods Twelve FAQs about PJI after hip and knee arthroplasty were identified from the websites of fifteen international clinical expert centres. ChatGPT was confronted with these questions and its responses were analysed for their accuracy using an evidence-based approach by a multidisciplinary team. Responses were categorised in four groups: (1) Excellent response that did not require additional improvement; (2) Satisfactory responses that required a small amount of improvement; (3) Satisfactory responses that required moderate improvement; and (4) Unsatisfactory responses that required a large amount of improvement.Results From the analysis of the responses given by the chatbot, no reply received an 'unsatisfactory' rating; one did not require any correction; and the majority of the responses required low (7 out of 12) or moderate (4 out of 12) clarification. Although a few responses required minimal clarification, the chatbot responses were generally unbiased and evidence-based, even when asked controversial questions.Conclusions The AI-chatbot ChatGPT was able to effectively answer the FAQs of patients seeking information around PJI diagnosis and treatment. The given information was also written in a manner that can be assumed to be understandable by patients. The chatbot could be a valuable clinical tool for patient education and understanding around PJI treatment in the future. Further studies should evaluate its use and acceptance by patients with PJI.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Evaluating the accuracy and relevance of ChatGPT responses to frequently asked questions regarding total knee replacement
    Zhang, Siyuan
    Liau, Zi Qiang Glen
    Tan, Kian Loong Melvin
    Chua, Wei Liang
    KNEE SURGERY & RELATED RESEARCH, 2024, 36 (01)
  • [2] Evaluating the accuracy and relevance of ChatGPT responses to frequently asked questions regarding total knee replacement
    Siyuan Zhang
    Zi Qiang Glen Liau
    Kian Loong Melvin Tan
    Wei Liang Chua
    Knee Surgery & Related Research, 36
  • [3] Frequently asked questions regarding total knee arthroplasty
    Scott, RD
    Erens, GA
    ORTHOPEDICS, 2004, 27 (09) : 977 - 979
  • [4] ChatGPT is capable of providing satisfactory responses to frequently asked questions regarding total shoulder arthroplasty
    Yeramosu, Teja
    Johns, William L.
    Onor, Gabriel
    Menendez, Mariano E.
    Namdari, Surena
    Hammoud, Sommer
    SHOULDER & ELBOW, 2024, 16 (04) : 407 - 412
  • [5] Assessing ChatGPT Responses to Common Patient Questions Regarding Total Hip Arthroplasty
    Mika, Aleksander P.
    Martin, J. Ryan
    Engstrom, Stephen M.
    Polkowski, Gregory G.
    Wilson, Jacob M.
    JOURNAL OF BONE AND JOINT SURGERY-AMERICAN VOLUME, 2023, 105 (19): : 1519 - 1526
  • [6] Appropriateness of Frequently Asked Patient Questions Following Total Hip Arthroplasty From ChatGPT Compared to Arthroplasty-Trained Nurses
    Dubin, Jeremy A.
    Bains, Sandeep S.
    Derogatis, Michael J.
    Moore, Mallory C.
    Hameed, Daniel
    Mont, Michael A.
    Nace, James
    Delanois, Ronald E.
    JOURNAL OF ARTHROPLASTY, 2024, 39 (09): : S306 - S311
  • [7] Periprosthetic Joint Infection Treatment in Total Hip and Knee Arthroplasty
    Becker, Roland
    Clauss, Martin
    Rotigliano, Niccolo
    Hirschmann, Michael Tobias
    OPERATIVE TECHNIQUES IN ORTHOPAEDICS, 2016, 26 (01) : 20 - 33
  • [8] EVALUATING CHATGPT'S RESPONSES TO FREQUENTLY ASKED QUESTIONS REGARDING POLYCYSTIC OVARY SYNDROME.
    Pace, Lauren
    Kummer, Nicholas
    Bril, Fernando
    Hosseinzadeh, Pardis
    Azziz, Ricardo
    FERTILITY AND STERILITY, 2024, 122 (01) : E55 - E55
  • [9] Can ChatGPT Answer Patient Questions Regarding Total Knee Arthroplasty?
    Mika, Aleksander P.
    Mulvey, Hillary E.
    Engstrom, Stephen M.
    Polkowski, Gregory G.
    Martin, J. Ryan
    Wilson, Jacob M.
    JOURNAL OF KNEE SURGERY, 2024, 37 (09) : 664 - 673
  • [10] Risk Factors for Periprosthetic Joint Infection after Total Hip Arthroplasty and Total Knee Arthroplasty in Chinese Patients
    Wu, Chuanlong
    Qu, Xinhua
    Liu, Fengxiang
    Li, Huiwu
    Mao, Yuanqing
    Zhu, Zhenan
    PLOS ONE, 2014, 9 (04):