Evaluating ChatGPT Responses to Frequently Asked Questions on Total Knee Arthroplasty

Evaluating ChatGPT Responses to Frequently Asked Questions on Total Knee Arthroplasty | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Evaluating ChatGPT Responses to Frequently Asked Questions on Total Knee Arthroplasty Yilun Jiang, Jiesheng Zhu, Yuanyuan Lin, Zheng Su, Libing Zhang, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7122725/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 08 Dec, 2025 Read the published version in Journal of Orthopaedic Surgery and Research → Version 1 posted 17 You are reading this latest preprint version Abstract Background ChatGPT has proven its value in medical information acquisition and perioperative education. This study aimed to evaluate correlated factors to explore the value of ChatGPT in patient communication. Methods 220 questions were collected from patients undergoing TKA. The selected questions were answered by ChatGPT-3.5. Questionnaires were created and sent to surgeons and patients. Some features of respondents were collected and investigated for analysis. Readability scores were assessed via the Flesch-Kincaid Grade Level (FKGL). Results The most common question from patients was about operation costs. Satisfaction scores from patients and surgeons were both high. Correlation analysis revealed that surgeon’s score was influenced by hospital level and surgery experience. The readability scores for FKGL were high. Conclusions Collecting questionnaires reveals patients' real clinical needs. The results of the study showed that ChatGPT has potential to be a tool for communicating with patients. ChatGPT responses require a high level of education although this level of education can be reduced. Total Knee Arthroplasty Artificial Intelligence ChatGPT Patient communication Patient Satisfaction Figures Figure 1 Figure 2 1. Introduction Total knee arthroplasty (TKA) is a common surgery with a growing demand in countries such as China and the U.S. [ 1 , 2 ]. Many patients have numerous questions and concerns about the surgery and recovery process[ 3 , 4 ]. Effective communication reduces anxiety and improves surgical outcomes. While healthcare professionals offer expert advice, time constraints can hinder the provision of comprehensive guidance. Therefore, patients need other ways to acquire surgical information. Patients usually use the internet to seek health information, with most U.S. adults researching medical conditions online [ 5 , 6 ]. Google data confirm this trend, showing that patients frequently search for queries related to their health[ 7 ]. However, there is much inaccurate and misinformed medical information on the internet[ 8 , 9 ], and specialized medical content often requires high reading proficiency[ 10 , 11 ]. In addition to traditional websites, social media and video platforms are becoming channels for accessing medical information, but most of the content comes from nonmedical professionals. [ 12 – 14 ]. The diverse sources result in variable content quality, which makes it difficult for patients to distinguish between accurate and expert information[ 15 ]. In addition, the average American reads score is at the 6th-9th-grade level, whereas most patient education materials are written at the 9th-11th grade level[ 16 ]. Many patients have low health literacy skills and face difficulties with reading, writing, arithmetic, communication, and increasingly electronic technology, which impedes their access to and comprehension of healthcare information. Therefore, it is important to introduce new tools to facilitate patient communication. Recently, artificial intelligence (AI) has become a key resource for medical information. Search engines integrate AI such as ChatGPT and other large language models (LLMs) into browsers, focusing on AI-generated summaries[ 17 , 18 ]. With its rapid development and increasing capabilities, AI is on the verge of becoming an indispensable medical resource in modern healthcare. In the medical field, ChatGPT serves multiple functions, including patient education, medical consultation, and diagnosis. For example, in patient education, ChatGPT has the potential to be used as an adjunct tool to help patients access health information and provide medical suggestions[ 19 , 20 ]. As a self-diagnostic tool, ChatGPT has demonstrated its ability to accurately diagnose a wide variety of common orthopedic diseases[ 21 – 23 ]. However, most ChatGPT-related studies have been conducted by a small number of surgeons to evaluate the responses generated by ChatGPT. Studies testing the awareness of ChatGPT in orthopedics do not focus primarily on the actual utilization of ChatGPT by patients[ 24 – 28 ]. Nonetheless, we consider it highly important to concentrate on the practical aspects of ChatGPT usage and its acceptance among surgeons and patients. Previous studies have not investigated the accuracy, professionalism, and readability of ChatGPT or surgeons' willingness to let ChatGPT answer patient questions, and the readability of ChatGPT responses has rarely been mentioned. In addition, patients’ satisfaction with ChatGPT’s answers is still unknown as to whether these answers are suitable for their reading. Therefore, the aims of this study were 1) to assess the satisfaction, accuracy, and professionalism of ChatGPT responses to patients’ real questions and to evaluate surgeons’ acceptance of ChatGPT and identify the factors that influence it; and 2) to explore patient satisfaction and the readability of ChatGPT responses. 2. Materials and Methods Patient question collection : Perioperative questions from 44 patients undergoing TKA surgery were collected in our department. Each patient was asked to give five questions they were most concerned about before and after TKA surgery, encompassing topics such as preoperative preparation, surgical risks, postoperative, and rehabilitation. A total of 220 questions were collected for further analysis. Ask ChatGPT questions and collect answers : In this study, we utilized the OpenAI ChatGPT-3.5 version for the top 10 (Table 1 ) questions. ChatGPT was accessed via a web browser on April 7, 2024 ( https://chat.openai.com/chat ). We initiated the queries with the prompt, "You are now an arthroplasty surgeon, and the patient is preparing for knee arthroplasty surgery. Please answer the following patients’ questions." To evaluate readability, each question was rephrased to request an easy-to-understand answer based on the Flesch-Kincaid Grade Level (FKGL) assessment. The consistency of the responses was ensured by asking the questions in a controlled, single-session format. Table 1 The top 10 asked questions by TKA patients Number Question Frequency 1. What is the cost of the operation and when do I have to pay for it？ 27 2. Will there be any pain after the operation？ 25 3. What is the procedure like and what implants are used to put it in？ 19 4. How long will I be discharged from the hospital after the operation and when will I be fully recovered？ 16 5. When will I be able to walk on the floor after the operation？ 15 6. Will other illnesses such as high blood pressure, diabetes, uremia, or heart disease affect the operation？ 15 7. What should I eat and drink after the operation, and should I take any supplements or other medication？ 12 8. What does the surgical consent form contain and when should I sign it？ 11 9. What should I do to prepare for the operation？ 10 10. How will I be able to have a bowel movement after the operation？ 10 Surgeons’ questionnaire collection : To further investigate orthopedic surgeons’ satisfaction with ChatGPT-generated responses, we designed questionnaires comprising patient questions and corresponding AI-generated answers on the website ( https://www.wjx.cn/ ). These questionnaires were sent to surgeons at different levels of hospitals in China (hospitals in China are ranked by size, technology, service, and research into three levels: I, II, and III, with subgrades A, B, and C, respectively). The questionnaire assessed the satisfaction of orthopedic surgeons at different hospitals with each response to the ChatGPT using a 5-point scale, while considering professional titles that included medical students to chief surgeons and were stratified by the quantity of surgeries performed annually. Additionally, the survey assessed overall response accuracy and professionalism via a similar 5-point scale for further analysis. The patient questionnaire also assessed satisfaction via a 5-point scale. We simultaneously rated the readability of the two ChatGPT responses on the readability website ( https://datayze.com/readability-analyzer ) and ultimately used the FKGL to represent the readability of the ChatGPT responses. FKGL was chosen because it is an effective method for evaluating the readability of content and is widely used in readability studies. Patient questionnaire collection : To further investigate patient satisfaction with the answers generated by the ChatGPT, a questionnaire with a satisfaction score of 5 was produced and sent to 53 patients undergoing TKA surgery in our orthopedic department at that time. Data analyses We utilized Statistical Package for the Social Sciences 26 (SPSS 26) for data processing and analysis. Descriptive statistics, including the mean, standard deviation, and frequency distribution, were employed to summarize the dataset's basic characteristics. Correlation analysis was conducted to investigate the factors that affect surgeons’ satisfaction accuracy, and professionalism such as professional title, hospital level, and annual surgical quantity. We assessed readability via an independent samples t-test. 3. Results 3.1 Top 10 questions from patients awaiting TKA and their answers from the ChatGPT To choose typical questions from patients before TKA, 220 questions from 44 patients were collected and categorized into 52 distinct questions (Supplement Table 1 ). After analyzing the frequency of these questions, we identified the 10 questions most frequently asked (Table 1 ). In addition to the high-frequency questions, patients raised various concerns related to health insurance reimbursement, surgery timing, surgeon selection, postoperative mobility, care after surgery, medication use, anesthesia methods, preoperative fasting, postoperative diet, hospital stay duration, and risk of deep vein thrombosis. These issues encompass the spectrum of patient concerns regarding perioperative surgery, addressing aspects such as the procedure's safety, recovery, quality of life, and financial implications. We then utilized OpenAI's ChatGPT-3.5 to answer a series of questions from patients. Each question and its corresponding answer are detailed in Supplementary Table 2. 3.2 Satisfaction with the surgeon, accuracy, and professionalism of the ChatGPT were high To evaluate the satisfaction of surgeons, accuracy, and professionalism of the ChatGPT, the questions from patients and answers from the ChatGPT were used in a survey and sent to surgeons in different hospitals to rate the accuracy and professionalism of the answers from the ChatGPT. A total of 81 questionnaires were collected from orthopedic surgeons to assess their satisfaction with the responses of the ChatGPT in communicating with TKA patients. The mean satisfaction score for each answered question is illustrated in Fig. 1 , revealing no significant disparity in satisfaction across different queries. Surgeons rated ChatGPT with an average satisfaction score of 4.72 out of 5, where 75% were satisfied (score of 5), 23% were relatively satisfied (score of 4), and 2% were generally satisfied (score of 3). Interestingly, no surgeons rated their satisfaction as "unsatisfied" (score of 1), underscoring the significant value of the ChatGPT in medical communication. In addition, orthopedic surgeons evaluated ChatGPT responses in TKA patient communication and assigned an average professionalism score of 4.41 and an accuracy score of 4.36 out of 5, suggesting generally reliable medical knowledge and professional advice. Moreover, we also collected information from surgeons about their willingness to substitute ChatGPT responses for their own responses. We found that most surgeons (55.6%) were willing to provide ChatGPT responses to answer almost all (80%-100%) of their patients' questions. A total of 29.6% were willing to provide a majority (60%-80%) of such responses to their patients. A total of 13.6% were willing to provide a moderate number (40%-60%) of ChatGPT responses. Interestingly, only one surgeon was willing to provide a small percentage (20%) of ChatGPT responses to patients. 3.3 Correlation analysis To further investigate the factors that affect surgeon satisfaction, accuracy, and professionalism, the hospital level, professional title, and surgical experience were used for analysis. In this survey, 81 completed questionnaires were collected: 50 from third-level Grade A hospitals, 8 from second-level Grade A hospitals, and 23 from third-level Grade B hospitals. Our questionnaire collected 2 questionnaires from medical students, 15 from resident surgeons, 31 from attending surgeons, 26 from associate surgeons, and 7 from chief surgeons. A total of 27 questionnaires came from surgeons with 0–50 surgeries per year, 5 questionnaires from surgeons with 50–100 surgeries per year, 2 questionnaires were obtained from surgeons with 100–200 surgeries per year, 4 questionnaires from surgeons with 200–500 surgeries per year, and 41 questionnaires from surgeons who were only assistants during TKA surgery. The results revealed that as the hospital level increased, the satisfaction rate (r=-0.236, P < 0.001), accuracy (r=-0.317, P < 0.001), and professionalism (r=-0.429, P < 0.001) gradually decreased (Fig. 2 a-c). Upon further analysis across surgeon titles, no significant correlation was observed between satisfaction and professionalism (Table 2 ). Interestingly, the professionalism ratings increased with increasing surgical experience (r = 0.093, P < 0.01) (Fig. 2 d). Finally, a significant correlation was noted between the degree of non-chief surgical participation and the surgeons' satisfaction (r = 0.119, P < 0.01) and accuracy (r=-0.092, P < 0.01) ratings of the ChatGPT responses. As surgical participation increased, satisfaction ratings increased, whereas accuracy ratings decreased (Fig. 2 e), suggesting that experienced surgeons might evaluate ChatGPT responses from a user experience perspective in addition to professional standards. However, the accuracy ratings of the ChatGPT responses improved with increasing surgeon title (r = 0.12, P < 0.01) (Fig. 2 f). For surgeons with different levels of surgical experience, no significant correlation was found between their satisfaction and accuracy ratings and ChatGPT responses (Table 2 ). No significant correlation was found between the degree of non-chief surgical participation and professionalism scores (Table 2 ). Table 2 The correlation analysis refers to satisfaction, accuracy, expertise Rank Correlation Analysis Satisfaction Accuracy Expertise Hospital level Rs=-0.236*** Rs=-0.317*** Rs=-0.429*** Medical positions Rs=-0.035 Rs = 0.12** Rs = 0.026 Surgical Quantity Rs=-0.013 Rs = 0.023 Rs = 0.093** Surgical Participation Quantity Rs = 0.119** Rs=-0.092** Rs=-0.033 Rs are rank correlation coefficients, with * representing P ≤ 0.05, ** representing P ≤ 0.01, and *** representing P ≤ 0.001. 3.4 Patient satisfaction with ChatGPT answers To explore the patients’ satisfaction rate with ChatGPT’s answers, 53 patients, including 34 women and 19 men, were investigated, and the patients’ satisfaction score was 4.99/5. The mean satisfaction score for each answered question is illustrated in Fig. 1 . Their average education level was equivalent to 4.8th grade. This demonstrated that almost all the patients were satisfied with the answers from ChatGPT, although their education level was low. 3.5 Readability analysis To assess the readability of the ChatGPT responses, we analyzed the FKGL scores. The average FKGL for all the responses was 9.45 (95% CI, SD 0.76), suggesting a reading level of 9th grade or higher. After the ChatGPT was instructed to provide answers in an easy-to-understand manner, the mean FKGL decreased to 8.75(95% CI, SD 0.62). Table 3 shows the FKGL scores for the responses to the 10 questions. An independent samples t-test revealed a significant improvement in readability post-instruction (p < 0.05). The second ChatGPT response is shown in Supplement Table 3 . Therefore, the answers from ChatGPT were fit for a reading level of 8th grade or above. Table 3 The readability analysis score FKGL FKGL Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4 Q1 Q2 V1 9.95 8.3 9.03 10.3 8.98 9.74 8.94 10.77 9.64 8.83 V2 8.27 7.97 8.92 8.9 7.95 8.42 9.57 9.57 9.58 8.36 FKGL, Flesch-Kincaid Grade Level; Q1-Q10 corresponds to the ten questions in Table 1 ; V1 represents the score for the first answer to each question; V2 represents the score when ChatGPT was instructed to provide an easily understandable answer. 4. Discussion In our study, patients' common concerns about perioperative TKA focused on the cost of surgery, postoperative pain, surgical procedure, recovery time, mobility, dietary advice, presurgical preparation, and postoperative continence problems. These concerns reflected patients' real worries about surgical safety, the recovery process, quality of life, and financial burden. Moreover, the surgeon group gave high ratings to ChatGPT's responses, with an average satisfaction score of 4.72/5.00. Professionalism and accuracy were rated at 4.41/5.00 and 4.36/5.00, respectively. These ratings demonstrated the value of ChatGPT in medical communication. Moreover, most surgeons are willing to use ChatGPT to answer 80%-100% of their patients' questions. These findings suggest that surgeons perceive ChatGPT to be reliable in conveying medical knowledge and providing professional advice, although it may not always meet the highest standards of professional medical communication. This study revealed that patients were highly satisfied with the responses of the ChatGPT (mean score 4.99), indicating its significant potential to improve patients' access to information. In contrast, surgeon satisfaction with ChatGPT responses was rated at 4.72, which was lower than patient satisfaction. This difference may reflect differences in evaluation criteria: patients are more concerned with the comprehensibility of the responses, whereas surgeons are more interested in the medical expertise and precision of the responses. ChatGPT, as a cutting-edge AI technology, has shown great potential in the field of medical communication. In the field of epilepsy, Wu et al. reported that ChatGPT offered "accurate and thorough" responses to more than 50% of inquiries[ 29 ]. Another dentistry study also demonstrated that ChatGPT can significantly enhance the efficiency and quality of dental telemedicine[ 30 ]. Similarly, Bahar et al. reported that ChatGPT accurately and satisfactorily answered more than 90% of endometriosis questions[ 31 ]. In the orthopedic research field, there are numerous studies related to the ChatGPT. Aleksander et al. reported that satisfactory AI responses in THA patients require only minimal clarification[ 24 ]. In the specialized field of arthroplasty, the ChatGPT has been shown to provide precise and detailed responses, which positively impact patients' preoperative anxiety and enhance their understanding of the surgical procedure[ 18 , 25 ]. However, the limitations of these studies include the failure to collect questions and the real needs of TKA patients, the lack of response scores from orthopedic surgeons with different experience levels, and the exploration of surgeons' opinions about the use of the ChatGPT to answer patient questions. Therefore, we conducted this study to investigate the effectiveness of ChatGPT in patient communication. Compared with their study, we gathered many real questions from patients and sent questionnaires to surgeons at various levels in different hospitals to obtain their ratings of ChatGPT responses. We also introduced a readability score to analyze the readability of these responses. At the end of the questionnaire, surgeons' recommendations for ChatGPT responses were analyzed. Most studies reported satisfactory and accurate responses, but some mentioned the need for enhanced detailed information, review of information sources, and personalized medicine. Moreover, some surgeons have mentioned that the answers of the ChatGPT are generic and nonspecific. This feedback indicated that there are still shortcomings in ChatGPT responses and areas for further improvement. We also identified the limitations of ChatGPT in dealing with certain complex medical issues, particularly in providing personalized medical advice and citing the latest medical protocols. This finding emphasized that, although AI shows promise in healthcare, its effectiveness depends on integration with healthcare professionals' knowledge and experience [ 32 ]. Although ChatGPT's information is generally valid, accurate, and professional, it can be affected by a variety of factors. Our study revealed that the level of the hospital and the experience of the surgeon are significant factors affecting judgment. We believe that this is due to differences in expertise, medical experience, background, and the application of medical technology among surgeons. Surgeons at top hospitals often have greater expertise, experience, backgrounds, advanced equipment, extensive case databases, and multidisciplinary support. In Mohammad Hosseini's study, significant differences in acceptance and willingness to use ChatGPT were observed between trainees (e.g., students, residents, and fellows) and faculty (e.g., professors and senior fellows). Varying levels of knowledge about ChatGPT and other LLMs may lead to different levels of acceptance of these technologies. An individual's academic background and professional training also influence their acceptance of ChatGPT[ 33 ]. Given the importance of the hospital and surgeon levels, future research should assess the attitudes of patients and surgeons toward AI tools and explore how these tools can be effectively integrated into existing surgeon-patient communication processes[ 31 ]. We conducted a readability analysis, and the results indicated that the majority of the responses were suitable for individuals with a reading level of 9th grade or higher. After we instructed ChatGPT to provide answers in an easy-to-understand manner, the reading difficulty significantly decreased. We also found that ChatGPT can tailor its responses according to the educational background of patients, providing answers suitable for their comprehension. Additionally, ChatGPT can provide multiple response options for a single question, thereby addressing different aspects of patients' needs. This flexibility in generating diverse responses is a notable feature that has been overlooked by most researchers. This study has several limitations. First, the participating surgeons were all from Grade 2A or higher hospitals, which are the only facilities that are qualified to perform TKA in China. Therefore, the results may not reflect the perspectives of surgeons in lower-tier hospitals. Second, the patient cohort generally had low education levels, as most patients undergoing TKA are older and have grown up in an era with limited access to compulsory education. This may have influenced their understanding and evaluation of the responses of ChatGPT. Finally, only the top 10 most frequently asked questions were analyzed, leaving other patient concerns unaddressed. However, we believe that these questions are representative of the primary concerns of perioperative TKA and rehabilitation. 5. Conclusions Overall, questionnaire collection identifies genuine clinical needs of patients. The application of the ChatGPT in TKA patient communication has yielded positive initial results. Additionally, many surgeons are willing to use ChatGPT to answer most of their patients' questions. Although there are differences in satisfaction and accuracy among different hospital levels and surgeons with different titles, overall, surgeons are highly satisfied with the accuracy of using ChatGPT to answer questions. Patient satisfaction with the responses was greater, likely due to the comprehensive and understandable nature of the information provided by the ChatGPT. It is expected that ChatGPT will become an important tool for medical communication and is expected to improve the quality of patient education and communication. Abbreviations Flesch-Kincaid Grade Level (FKGL) Total knee arthroplasty (TKA) artificial intelligence (AI) large language models (LLMs) Statistical Package for the Social Sciences 26 (SPSS 26) Declarations Ethics approval and consent to participate: The protocol of this retrospective study was approved by the ethics committees of the Second Affiliated Hospital of Wenzhou Medical University. The study was conducted in accordance to the declaration of Helsinki. Informed consent to participate was obtained from all participants included in the study. Consent for publication: Not applicable. Availability of data and materials: The data and materials that support the findings of this study are not openly available due to reasons of sensitivity and are available from the corresponding author upon reasonable request. Competing interests: The authors declare that they have no competing interests. Funding: This research received no external funding. Authors' contributions: Conceptualization: P.F. Data collection: Y.L. Formal analysis: P.F. Methodology: P.F., Z.D., Z.L. Project administration: J.Z. Resources: Y.J., Z.S., L.Z., Z.L., Q.S. Software: P.F. Supervision: P.F. Visualization: J.Z. Data analysis: Y.J., Z.L. Writing-original draft: Y.J. Writing-review & editing: P.F. All authors approved the final version to be published. Acknowledgements: We gratefully acknowledge statistics assistance from Dr. Qun Wang. References Siddiqi A, Levine BR, Springer BD. Highlights of the 2021 American joint replacement registry annual report. Arthroplasty Today. 2022;13:205–207. doi: 10.1016/j.artd.2022.01.020. Singh JA, Yu S, Chen L, Cleveland JD. Rates of total joint replacement in the united states: Future projections to 2020-2040 using the national inpatient sample. J Rheumatol. 2019;46:1134–1140. doi: 10.3899/jrheum.170990. Trousdale RT, McGrory BJ, Berry DJ, Becker MW, Harmsen WS. Patients’ concerns prior to undergoing total hip and total knee arthroplasty. Mayo Clin Proc. 1999;74:978–982. doi: 10.4065/74.10.978. Macario A, Schilling P, Rubio R, Bhalla A, Goodman S. What questions do patients undergoing lower extremity joint replacement surgery have? BMC health services research. 2003;3:11. doi: 10.1186/1472-6963-3-11. Calixte R, Rivera A, Oridota O, Beauchamp W, Camacho-Rivera M. Social and demographic patterns of health-related internet use among adults in the united states: A secondary data analysis of the health information national trends survey. Int J Environ Res Public Health. 2020;17:6856. doi: 10.3390/ijerph17186856. The most recent time you looked for information about health or medical topics, where did you go first? | HINTS [Internet]. [cited 2024 Apr 21]. Available from: https://hints.cancer.gov/view-questions/question-detail.aspx?PK_Cycle=11&qid=688. Sa C, Le C, Jd T, G B, R L, M S, Nd H. Google trends as a tool for evaluating public interest in total knee arthroplasty and total hip arthroplasty. Journal of clinical and translational research [Internet]. 2021 [cited 2024 Jan 31];7. Cited: in: : PMID: 34667892. Assessing, controlling, and assuring the quality of medical information on the internet: Caveant lector et viewor--let the reader and viewer beware - PubMed [Internet]. [cited 2024 Apr 21]. Available from: https://pubmed.ncbi.nlm.nih.gov/9103351/. Internet use by orthopaedic outpatients - current trends and practices - PubMed [Internet]. [cited 2024 Apr 21]. Available from: https://pubmed.ncbi.nlm.nih.gov/23382767/. Readability of patient education materials from the American academy of orthopaedic surgeons and pediatric orthopaedic society of north america web sites - PubMed [Internet]. [cited 2024 Apr 20]. Available from: https://pubmed.ncbi.nlm.nih.gov/18171975/. Most American academy of orthopaedic surgeons’ online patient education material exceeds average patient reading level - PubMed [Internet]. [cited 2024 Apr 21]. Available from: https://pubmed.ncbi.nlm.nih.gov/25475715/. Davaris MT, Dowsey MM, Bunzli S, Choong PF. Arthroplasty information on the internet: Quality or quantity? Bone & Joint Open. 2020;1:64–73. doi: 10.1302/2633-1462.14.BJO-2020-0006. Ng MK, Emara AK, Molloy RM, Krebs VE, Mont M, Piuzzi NS. YouTube as a source of patient information for total knee/hip arthroplasty: Quantitative analysis of video reliability, quality, and content. J Am Acad Orthop Surg. 2021;29:e1034–e1044. doi: 10.5435/JAAOS-D-20-00910. Latif MZ, Hussain I, Saeed R, Qureshi MA, Maqsood U. Use of smart phones and social media in medical education: Trends, advantages, challenges and barriers. Acta informatica medica: AIM: journal of the Society for Medical Informatics of Bosnia & Herzegovina: casopis Drustva za medicinsku informatiku BiH. 2019;27:133–138. doi: 10.5455/aim.2019.27.133-138. Cited: in: : PMID: 31452573. Shen TS, Driscoll DA, Islam W, Bovonratwet P, Haas SB, Su EP. Modern Internet Search Analytics and Total Joint Arthroplasty: What Are Patients Asking and Reading Online? J Arthroplasty. 2021;36:1224–1231. doi: 10.1016/j.arth.2020.10.024. Spandorfer JM, Karras DJ, Hughes LA, Caputo C. Comprehension of discharge instructions by patients in an urban emergency department. Ann Emerg Med. 1995;25:71–74. doi: 10.1016/s0196-0644(95)70358-6. Lopez CD, Ding J, Trofa DP, Cooper HJ, Geller JA, Hickernell TR. Machine Learning Model Developed to Aid in Patient Selection for Outpatient Total Joint Arthroplasty. Arthroplasty Today. 2022;13:13–23. doi: 10.1016/j.artd.2021.11.001. Lopez CD, Gazgalis A, Boddapati V, Shah RP, Cooper HJ, Geller JA. Artificial Learning and Machine Learning Decision Guidance Applications in Total Hip and Knee Arthroplasty: A Systematic Review. Arthroplasty Today. 2021;11:103–112. doi: 10.1016/j.artd.2021.07.012. Honda S, Noguchi T. Promise and pitfalls of ChatGPT for patient education on coronary angiogram. Annals of the Academy of Medicine, Singapore. 2023;52:338–339. doi: 10.47102/annals-acadmedsg.2023225. Cited: in: : PMID: 38904498. Patient education and health literacy - PubMed [Internet]. [cited 2024 Apr 20]. Available from: https://pubmed.ncbi.nlm.nih.gov/30017902/. Kuroiwa T, Sarcon A, Ibara T, Yamada E, Yamamoto A, Tsukamoto K, Fujita K. The Potential of ChatGPT as a Self-Diagnostic Tool in Common Orthopedic Diseases: Exploratory Study. J Med Internet Res. 2023;25:e47621. doi: 10.2196/47621. Leveraging large language models (LLM) for the plastic surgery resident training: Do they have a role? - PubMed [Internet]. [cited 2024 Apr 21]. Available from: https://pubmed.ncbi.nlm.nih.gov/38026769/. Rao A, Pang M, Kim J, Kamineni M, Lie W, Prasad AK, Landman A, Dreyer KJ, Succi MD. Assessing the utility of ChatGPT throughout the entire clinical workflow. medRxiv: The Preprint Server for Health Sciences. 2023;2023.02.21.23285886. doi: 10.1101/2023.02.21.23285886. Cited: in: : PMID: 36865204. Mika AP, Martin JR, Engstrom SM, Polkowski GG, Wilson JM. Assessing ChatGPT Responses to Common Patient Questions Regarding Total Hip Arthroplasty. J Bone Joint Surg. 2023;105:1519–1526. doi: 10.2106/JBJS.23.00209. Kienzle A, Niemann M, Meller S, Gwinner C. ChatGPT May Offer an Adequate Substitute for Informed Consent to Patients Prior to Total Knee Arthroplasty-Yet Caution Is Needed. Journal of Personalized Medicine. 2024;14:69. doi: 10.3390/jpm14010069. Wright BM, Bodnar MS, Moore AD, Maseda MC, Kucharik MP, Diaz CC, Schmidt CM, Mir HR. Is ChatGPT a trusted source of information for total hip and knee arthroplasty patients? Bone & Joint Open. 2024;5:139–146. doi: 10.1302/2633-1462.52.BJO-2023-0113.R1. Smith AM, Jacquez EA, Argintar EH. Assessing the efficacy of an AI-powered chatbot (ChatGPT) in providing information on orthopedic surgeries: A comparative study with expert opinion. Cureus. 2024;16:e63287. doi: 10.7759/cureus.63287. Jain N, Gottlich C, Fisher J, Campano D, Winston T. Assessing ChatGPT’s orthopedic in-service training exam performance and applicability in the field. Journal of Orthopaedic Surgery and Research. 2024;19:27. doi: 10.1186/s13018-023-04467-0. Wu Y, Zhang Z, Dong X, Hong S, Hu Y, Liang P, Li L, Zou B, Wu X, Wang D, et al. Evaluating the performance of the language model ChatGPT in responding to common questions of people with epilepsy. Epilepsy & Behavior: E&B. 2024;151:109645. doi: 10.1016/j.yebeh.2024.109645. Cited: in: : PMID: 38244419. Eggmann F, Weiger R, Zitzmann NU, Blatz MB. Implications of large language models such as ChatGPT for dental medicine. J Esthet Restor Dent. 2023;35:1098–1102. doi: 10.1111/jerd.13046. Ozgor BY, Simavi MA. Accuracy and reproducibility of ChatGPT’s free version answers about endometriosis. International Journal of Gynaecology and Obstetrics: The Official Organ of the International Federation of Gynaecology and Obstetrics. 2023; doi: 10.1002/ijgo.15309. Cited: in: : PMID: 38108232. Gordijn B, Have H ten. ChatGPT: evolution or revolution? Medicine, Health Care and Philosophy. 2023;26:1–2. doi: 10.1007/s11019-023-10136-0. Hosseini M, Gao CA, Liebovitz D, Carvalho A, Ahmad FS, Luo Y, MacDonald N, Holmes K, Kho A. An exploratory survey about using ChatGPT in education, healthcare, and research. medRxiv: The Preprint Server for Health Sciences. 2023;2023.03.31.23287979. doi: 10.1101/2023.03.31.23287979. Cited: in: : PMID: 37066228. Additional Declarations No competing interests reported. Supplementary Files Supplementtable1.docx Supplementtable2.docx Supplementtable3.docx Cite Share Download PDF Status: Published Journal Publication published 08 Dec, 2025 Read the published version in Journal of Orthopaedic Surgery and Research → Version 1 posted Editorial decision: Revision requested 03 Aug, 2025 Reviews received at journal 03 Aug, 2025 Reviews received at journal 02 Aug, 2025 Reviewers agreed at journal 27 Jul, 2025 Reviews received at journal 26 Jul, 2025 Reviewers agreed at journal 25 Jul, 2025 Reviewers agreed at journal 25 Jul, 2025 Reviews received at journal 24 Jul, 2025 Reviewers agreed at journal 24 Jul, 2025 Reviewers agreed at journal 24 Jul, 2025 Reviewers agreed at journal 24 Jul, 2025 Reviewers agreed at journal 22 Jul, 2025 Reviewers agreed at journal 16 Jul, 2025 Reviewers invited by journal 16 Jul, 2025 Editor assigned by journal 14 Jul, 2025 Submission checks completed at journal 14 Jul, 2025 First submitted to journal 14 Jul, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7122725","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":486884868,"identity":"bb26945f-8478-428d-bf77-77af45744f3c","order_by":0,"name":"Yilun Jiang","email":"","orcid":"","institution":"Second Affiliated Hospital \u0026 Yuying Children's Hospital of Wenzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yilun","middleName":"","lastName":"Jiang","suffix":""},{"id":486884869,"identity":"f10fd900-82d0-464b-8e31-54446bb9d82d","order_by":1,"name":"Jiesheng Zhu","email":"","orcid":"","institution":"Second Affiliated Hospital \u0026 Yuying Children's Hospital of Wenzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jiesheng","middleName":"","lastName":"Zhu","suffix":""},{"id":486884870,"identity":"af437999-7972-4b2f-9a25-7954e9f945f5","order_by":2,"name":"Yuanyuan Lin","email":"","orcid":"","institution":"Second Affiliated Hospital \u0026 Yuying Children's Hospital of Wenzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yuanyuan","middleName":"","lastName":"Lin","suffix":""},{"id":486884871,"identity":"f1c4c2e3-e0b6-499a-81cc-bd65171b1b45","order_by":3,"name":"Zheng Su","email":"","orcid":"","institution":"Second Affiliated Hospital \u0026 Yuying Children's Hospital of Wenzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Zheng","middleName":"","lastName":"Su","suffix":""},{"id":486884872,"identity":"879874b6-794d-407c-828c-c0258b78caf5","order_by":4,"name":"Libing Zhang","email":"","orcid":"","institution":"Eye Hospital, Wenzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Libing","middleName":"","lastName":"Zhang","suffix":""},{"id":486884873,"identity":"064390a6-250e-482b-bfed-4c763f04462b","order_by":5,"name":"Zhen Dong","email":"","orcid":"","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"Zhen","middleName":"","lastName":"Dong","suffix":""},{"id":486884874,"identity":"cd0f1bcf-219a-4af4-acef-02e6169e8d8d","order_by":6,"name":"Qiong Song","email":"","orcid":"","institution":"Fuding hospital","correspondingAuthor":false,"prefix":"","firstName":"Qiong","middleName":"","lastName":"Song","suffix":""},{"id":486884875,"identity":"14d5aa72-641a-496b-a66a-46fc808b846c","order_by":7,"name":"Pei Fan","email":"","orcid":"","institution":"Second Affiliated Hospital \u0026 Yuying Children's Hospital of Wenzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Pei","middleName":"","lastName":"Fan","suffix":""},{"id":486884876,"identity":"9e2adf84-2fc1-4fa4-b43d-522a90428814","order_by":8,"name":"Zhenxing Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA60lEQVRIiWNgGAWjYBACA2YGNhDNwwChbXj4+RtI05ImIznjAAEtUKUMUPqwjUFDAgEt7OzPHnzccVjGnH9ZmuSPP+d5DBgOMH74mIPXYemGM8+k8VjOeHZMmrftNo85cwOz5MxteLWAVNrwGNw43nabseE2j2XDATZmXrxaGNuk/7ZJgLXc/PHnHI/BgQRCWpjZpBlBtpxvO3aDh+0AMVrY2CR729KAtrCl/+ZtS+aRnHGwGa9f7PuPP5P42XbY3uD8MWPDH3/s7Pn5mw9++IhHCwJIJMBYjA3EqAcC/gNEKhwFo2AUjIIRBwB15k1Wb64g9QAAAABJRU5ErkJggg==","orcid":"","institution":"Second Affiliated Hospital \u0026 Yuying Children's Hospital of Wenzhou Medical University","correspondingAuthor":true,"prefix":"","firstName":"Zhenxing","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-07-14 15:23:40","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7122725/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7122725/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s13018-025-06451-2","type":"published","date":"2025-12-08T15:58:24+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":87364352,"identity":"86842601-96a1-440b-b3b2-e1c3fe6d58cc","added_by":"auto","created_at":"2025-07-23 06:14:51","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":335382,"visible":true,"origin":"","legend":"\u003cp\u003eRatings of surgeons and patients' satisfaction with ChatGPT responses. The top satisfaction score is 5(5-satisfied, 4-relatively satisfied, 3-generally satisfied, 2-relatively unsatisfied, 1- unsatisfied). Questions 1-10 are the same as Table 1.\u003c/p\u003e","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7122725/v1/0a35e1a23b06e826ece09b1c.png"},{"id":87364350,"identity":"3d60f38c-1899-4012-9e26-d2d5eddcea08","added_by":"auto","created_at":"2025-07-23 06:14:51","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":645338,"visible":true,"origin":"","legend":"\u003cp\u003eThe correlation between satisfaction, accuracy, and professionalism ratings with hospital levels, surgeon levels, and surgical experience. \u003cem\u003e\u003cstrong\u003ea\u003c/strong\u003e\u003c/em\u003e. The line graph shows Scores (out of 5) on questions for different hospital levels, as the hospital levels increase, the satisfaction scores (out of 5) of the surgeons' responses to the ChatGPT show a decreasing trend. \u003cem\u003e\u003cstrong\u003eb\u003c/strong\u003e\u003c/em\u003e. the line graph shows Hospital levels and Accuracy Score (out of 5) As hospital levels increased, surgeons showed a decreasing trend in response accuracy score (out of 5) ratings for ChatGPT. \u003cem\u003e\u003cstrong\u003ec\u003c/strong\u003e\u003c/em\u003e. the line graph shows Hospital levels and Professionalism Score (out of 5) As the hospital levels increased, the surgeons' response professionalism score (out of 5) evaluation of ChatGPT showed a decreasing trend. \u003cem\u003e\u003cstrong\u003ed\u003c/strong\u003e\u003c/em\u003e. the line graph shows the Surgical Quantity and Professionalism Score (out of 5) As the number of bone and joint replacement surgeries performed by surgeons under their primary care increased, the surgeons' response professionalism score (out of 5) ratings for the ChatGPT showed a decreasing trend. \u003cem\u003e\u003cstrong\u003ee\u003c/strong\u003e\u003c/em\u003e. the line graph shows Surgical Participation Quantity and Satisfaction As the quantity of surgeon participation in bone and joint replacement surgeries increased, the surgeons' response satisfaction score (out of 5) ratings for the ChatGPT showed a decreasing trend. \u003cem\u003e\u003cstrong\u003ef\u003c/strong\u003e\u003c/em\u003e. the line graph shows the Title and Accuracy Score (out of 5), as the surgeons' position increases, the surgeons' response accuracy score (out of 5) evaluation of ChatGPT shows a decreasing trend.\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7122725/v1/d3b850277604a7fedea96dd1.png"},{"id":98244304,"identity":"f4d1acfb-9303-4523-9772-55358895c145","added_by":"auto","created_at":"2025-12-15 16:14:02","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1711405,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7122725/v1/07dd16f3-3054-4033-aa23-32a1f691de70.pdf"},{"id":87365883,"identity":"d4e1e268-9eaa-4ff7-aedd-d04bb655b1e8","added_by":"auto","created_at":"2025-07-23 06:30:51","extension":"docx","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":21011,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementtable1.docx","url":"https://assets-eu.researchsquare.com/files/rs-7122725/v1/0dd9c7f70b8c55337f46737d.docx"},{"id":87364356,"identity":"bdcc9cfb-2ff1-4587-b7cd-14f18ed182b8","added_by":"auto","created_at":"2025-07-23 06:14:51","extension":"docx","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":28284,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementtable2.docx","url":"https://assets-eu.researchsquare.com/files/rs-7122725/v1/52e223e092085aa4f895898f.docx"},{"id":87364360,"identity":"e9aa5c5b-12eb-4ede-a3a0-c20719c4ca23","added_by":"auto","created_at":"2025-07-23 06:14:51","extension":"docx","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":26895,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementtable3.docx","url":"https://assets-eu.researchsquare.com/files/rs-7122725/v1/b861385e98659287a3930aee.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Evaluating ChatGPT Responses to Frequently Asked Questions on Total Knee Arthroplasty","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eTotal knee arthroplasty (TKA) is a common surgery with a growing demand in countries such as China and the U.S. [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Many patients have numerous questions and concerns about the surgery and recovery process[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Effective communication reduces anxiety and improves surgical outcomes. While healthcare professionals offer expert advice, time constraints can hinder the provision of comprehensive guidance. Therefore, patients need other ways to acquire surgical information.\u003c/p\u003e\u003cp\u003ePatients usually use the internet to seek health information, with most U.S. adults researching medical conditions online [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Google data confirm this trend, showing that patients frequently search for queries related to their health[\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. However, there is much inaccurate and misinformed medical information on the internet[\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e], and specialized medical content often requires high reading proficiency[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. In addition to traditional websites, social media and video platforms are becoming channels for accessing medical information, but most of the content comes from nonmedical professionals. [\u003cspan additionalcitationids=\"CR13\" citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. The diverse sources result in variable content quality, which makes it difficult for patients to distinguish between accurate and expert information[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. In addition, the average American reads score is at the 6th-9th-grade level, whereas most patient education materials are written at the 9th-11th grade level[\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Many patients have low health literacy skills and face difficulties with reading, writing, arithmetic, communication, and increasingly electronic technology, which impedes their access to and comprehension of healthcare information. Therefore, it is important to introduce new tools to facilitate patient communication. Recently, artificial intelligence (AI) has become a key resource for medical information. Search engines integrate AI such as ChatGPT and other large language models (LLMs) into browsers, focusing on AI-generated summaries[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. With its rapid development and increasing capabilities, AI is on the verge of becoming an indispensable medical resource in modern healthcare. In the medical field, ChatGPT serves multiple functions, including patient education, medical consultation, and diagnosis. For example, in patient education, ChatGPT has the potential to be used as an adjunct tool to help patients access health information and provide medical suggestions[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e, \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. As a self-diagnostic tool, ChatGPT has demonstrated its ability to accurately diagnose a wide variety of common orthopedic diseases[\u003cspan additionalcitationids=\"CR22\" citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eHowever, most ChatGPT-related studies have been conducted by a small number of surgeons to evaluate the responses generated by ChatGPT. Studies testing the awareness of ChatGPT in orthopedics do not focus primarily on the actual utilization of ChatGPT by patients[\u003cspan additionalcitationids=\"CR25 CR26 CR27\" citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]. Nonetheless, we consider it highly important to concentrate on the practical aspects of ChatGPT usage and its acceptance among surgeons and patients. Previous studies have not investigated the accuracy, professionalism, and readability of ChatGPT or surgeons' willingness to let ChatGPT answer patient questions, and the readability of ChatGPT responses has rarely been mentioned. In addition, patients\u0026rsquo; satisfaction with ChatGPT\u0026rsquo;s answers is still unknown as to whether these answers are suitable for their reading.\u003c/p\u003e\u003cp\u003eTherefore, the aims of this study were 1) to assess the satisfaction, accuracy, and professionalism of ChatGPT responses to patients\u0026rsquo; real questions and to evaluate surgeons\u0026rsquo; acceptance of ChatGPT and identify the factors that influence it; and 2) to explore patient satisfaction and the readability of ChatGPT responses.\u003c/p\u003e"},{"header":"2. Materials and Methods","content":"\u003cp\u003e\u003cb\u003ePatient question collection\u003c/b\u003e:\u003c/p\u003e\u003cp\u003ePerioperative questions from 44 patients undergoing TKA surgery were collected in our department. Each patient was asked to give five questions they were most concerned about before and after TKA surgery, encompassing topics such as preoperative preparation, surgical risks, postoperative, and rehabilitation. A total of 220 questions were collected for further analysis.\u003c/p\u003e\u003cp\u003e\u003cb\u003eAsk ChatGPT questions and collect answers\u003c/b\u003e:\u003c/p\u003e\u003cp\u003eIn this study, we utilized the OpenAI ChatGPT-3.5 version for the top 10 (Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e1\u003c/span\u003e) questions. ChatGPT was accessed via a web browser on April 7, 2024 (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://chat.openai.com/chat\u003c/span\u003e\u003cspan address=\"https://chat.openai.com/chat\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e). We initiated the queries with the prompt, \"You are now an arthroplasty surgeon, and the patient is preparing for knee arthroplasty surgery. Please answer the following patients\u0026rsquo; questions.\" To evaluate readability, each question was rephrased to request an easy-to-understand answer based on the Flesch-Kincaid Grade Level (FKGL) assessment. The consistency of the responses was ensured by asking the questions in a controlled, single-session format.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eThe top 10 asked questions by TKA patients\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNumber\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eQuestion\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eFrequency\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWhat is the cost of the operation and when do I have to pay for it？\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e27\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e2.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWill there be any pain after the operation？\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e25\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e3.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWhat is the procedure like and what implants are used to put it in？\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e19\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e4.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eHow long will I be discharged from the hospital after the operation and when will I be fully recovered？\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e16\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e5.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWhen will I be able to walk on the floor after the operation？\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e15\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e6.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWill other illnesses such as high blood pressure, diabetes, uremia, or heart disease affect the operation？\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e15\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e7.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWhat should I eat and drink after the operation, and should I take any supplements or other medication？\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e12\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e8.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWhat does the surgical consent form contain and when should I sign it？\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e11\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e9.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWhat should I do to prepare for the operation？\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e10.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eHow will I be able to have a bowel movement after the operation？\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eSurgeons\u0026rsquo; questionnaire collection\u003c/b\u003e:\u003c/p\u003e\u003cp\u003eTo further investigate orthopedic surgeons\u0026rsquo; satisfaction with ChatGPT-generated responses, we designed questionnaires comprising patient questions and corresponding AI-generated answers on the website (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.wjx.cn/\u003c/span\u003e\u003cspan address=\"https://www.wjx.cn/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e). These questionnaires were sent to surgeons at different levels of hospitals in China (hospitals in China are ranked by size, technology, service, and research into three levels: I, II, and III, with subgrades A, B, and C, respectively).\u003c/p\u003e\u003cp\u003eThe questionnaire assessed the satisfaction of orthopedic surgeons at different hospitals with each response to the ChatGPT using a 5-point scale, while considering professional titles that included medical students to chief surgeons and were stratified by the quantity of surgeries performed annually. Additionally, the survey assessed overall response accuracy and professionalism via a similar 5-point scale for further analysis. The patient questionnaire also assessed satisfaction via a 5-point scale.\u003c/p\u003e\u003cp\u003eWe simultaneously rated the readability of the two ChatGPT responses on the readability website (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://datayze.com/readability-analyzer\u003c/span\u003e\u003cspan address=\"https://datayze.com/readability-analyzer\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e) and ultimately used the FKGL to represent the readability of the ChatGPT responses. FKGL was chosen because it is an effective method for evaluating the readability of content and is widely used in readability studies.\u003c/p\u003e\u003cp\u003e\u003cb\u003ePatient questionnaire collection\u003c/b\u003e:\u003c/p\u003e\u003cp\u003eTo further investigate patient satisfaction with the answers generated by the ChatGPT, a questionnaire with a satisfaction score of 5 was produced and sent to 53 patients undergoing TKA surgery in our orthopedic department at that time.\u003c/p\u003e\u003cp\u003e\u003cb\u003eData analyses\u003c/b\u003e\u003c/p\u003e\u003cp\u003eWe utilized Statistical Package for the Social Sciences 26 (SPSS 26) for data processing and analysis. Descriptive statistics, including the mean, standard deviation, and frequency distribution, were employed to summarize the dataset's basic characteristics. Correlation analysis was conducted to investigate the factors that affect surgeons\u0026rsquo; satisfaction accuracy, and professionalism such as professional title, hospital level, and annual surgical quantity. We assessed readability via an independent samples t-test.\u003c/p\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\u003ch2\u003e3.1 Top 10 questions from patients awaiting TKA and their answers from the ChatGPT\u003c/h2\u003e\u003cp\u003eTo choose typical questions from patients before TKA, 220 questions from 44 patients were collected and categorized into 52 distinct questions (Supplement Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e1\u003c/span\u003e). After analyzing the frequency of these questions, we identified the 10 questions most frequently asked (Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e1\u003c/span\u003e). In addition to the high-frequency questions, patients raised various concerns related to health insurance reimbursement, surgery timing, surgeon selection, postoperative mobility, care after surgery, medication use, anesthesia methods, preoperative fasting, postoperative diet, hospital stay duration, and risk of deep vein thrombosis. These issues encompass the spectrum of patient concerns regarding perioperative surgery, addressing aspects such as the procedure's safety, recovery, quality of life, and financial implications. We then utilized OpenAI's ChatGPT-3.5 to answer a series of questions from patients. Each question and its corresponding answer are detailed in Supplementary Table\u0026nbsp;2.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003e3.2 Satisfaction with the surgeon, accuracy, and professionalism of the ChatGPT were high\u003c/h2\u003e\u003cp\u003eTo evaluate the satisfaction of surgeons, accuracy, and professionalism of the ChatGPT, the questions from patients and answers from the ChatGPT were used in a survey and sent to surgeons in different hospitals to rate the accuracy and professionalism of the answers from the ChatGPT. A total of 81 questionnaires were collected from orthopedic surgeons to assess their satisfaction with the responses of the ChatGPT in communicating with TKA patients. The mean satisfaction score for each answered question is illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, revealing no significant disparity in satisfaction across different queries. Surgeons rated ChatGPT with an average satisfaction score of 4.72 out of 5, where 75% were satisfied (score of 5), 23% were relatively satisfied (score of 4), and 2% were generally satisfied (score of 3). Interestingly, no surgeons rated their satisfaction as \"unsatisfied\" (score of 1), underscoring the significant value of the ChatGPT in medical communication.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eIn addition, orthopedic surgeons evaluated ChatGPT responses in TKA patient communication and assigned an average professionalism score of 4.41 and an accuracy score of 4.36 out of 5, suggesting generally reliable medical knowledge and professional advice.\u003c/p\u003e\u003cp\u003eMoreover, we also collected information from surgeons about their willingness to substitute ChatGPT responses for their own responses. We found that most surgeons (55.6%) were willing to provide ChatGPT responses to answer almost all (80%-100%) of their patients' questions. A total of 29.6% were willing to provide a majority (60%-80%) of such responses to their patients. A total of 13.6% were willing to provide a moderate number (40%-60%) of ChatGPT responses. Interestingly, only one surgeon was willing to provide a small percentage (20%) of ChatGPT responses to patients.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\u003ch2\u003e3.3 Correlation analysis\u003c/h2\u003e\u003cp\u003eTo further investigate the factors that affect surgeon satisfaction, accuracy, and professionalism, the hospital level, professional title, and surgical experience were used for analysis. In this survey, 81 completed questionnaires were collected: 50 from third-level Grade A hospitals, 8 from second-level Grade A hospitals, and 23 from third-level Grade B hospitals. Our questionnaire collected 2 questionnaires from medical students, 15 from resident surgeons, 31 from attending surgeons, 26 from associate surgeons, and 7 from chief surgeons. A total of 27 questionnaires came from surgeons with 0\u0026ndash;50 surgeries per year, 5 questionnaires from surgeons with 50\u0026ndash;100 surgeries per year, 2 questionnaires were obtained from surgeons with 100\u0026ndash;200 surgeries per year, 4 questionnaires from surgeons with 200\u0026ndash;500 surgeries per year, and 41 questionnaires from surgeons who were only assistants during TKA surgery.\u003c/p\u003e\u003cp\u003eThe results revealed that as the hospital level increased, the satisfaction rate (r=-0.236, P\u0026thinsp;\u0026lt;\u0026thinsp;0.001), accuracy (r=-0.317, P\u0026thinsp;\u0026lt;\u0026thinsp;0.001), and professionalism (r=-0.429, P\u0026thinsp;\u0026lt;\u0026thinsp;0.001) gradually decreased (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003ea-c). Upon further analysis across surgeon titles, no significant correlation was observed between satisfaction and professionalism (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). Interestingly, the professionalism ratings increased with increasing surgical experience (r\u0026thinsp;=\u0026thinsp;0.093, P\u0026thinsp;\u0026lt;\u0026thinsp;0.01) (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003ed). Finally, a significant correlation was noted between the degree of non-chief surgical participation and the surgeons' satisfaction (r\u0026thinsp;=\u0026thinsp;0.119, P\u0026thinsp;\u0026lt;\u0026thinsp;0.01) and accuracy (r=-0.092, P\u0026thinsp;\u0026lt;\u0026thinsp;0.01) ratings of the ChatGPT responses. As surgical participation increased, satisfaction ratings increased, whereas accuracy ratings decreased (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003ee), suggesting that experienced surgeons might evaluate ChatGPT responses from a user experience perspective in addition to professional standards. However, the accuracy ratings of the ChatGPT responses improved with increasing surgeon title (r\u0026thinsp;=\u0026thinsp;0.12, P\u0026thinsp;\u0026lt;\u0026thinsp;0.01) (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003ef). For surgeons with different levels of surgical experience, no significant correlation was found between their satisfaction and accuracy ratings and ChatGPT responses (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). No significant correlation was found between the degree of non-chief surgical participation and professionalism scores (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eThe correlation analysis refers to satisfaction, accuracy, expertise\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRank Correlation Analysis\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSatisfaction\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eExpertise\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eHospital level\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRs=-0.236***\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eRs=-0.317***\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRs=-0.429***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eMedical positions\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRs=-0.035\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eRs\u0026thinsp;=\u0026thinsp;0.12**\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRs\u0026thinsp;=\u0026thinsp;0.026\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSurgical Quantity\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRs=-0.013\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eRs\u0026thinsp;=\u0026thinsp;0.023\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRs\u0026thinsp;=\u0026thinsp;0.093**\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSurgical Participation Quantity\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRs\u0026thinsp;=\u0026thinsp;0.119**\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eRs=-0.092**\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRs=-0.033\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eRs are rank correlation coefficients, with * representing P\u0026thinsp;\u0026le;\u0026thinsp;0.05, ** representing P\u0026thinsp;\u0026le;\u0026thinsp;0.01, and *** representing P\u0026thinsp;\u0026le;\u0026thinsp;0.001.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\u003ch2\u003e3.4 Patient satisfaction with ChatGPT answers\u003c/h2\u003e\u003cp\u003eTo explore the patients\u0026rsquo; satisfaction rate with ChatGPT\u0026rsquo;s answers, 53 patients, including 34 women and 19 men, were investigated, and the patients\u0026rsquo; satisfaction score was 4.99/5. The mean satisfaction score for each answered question is illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. Their average education level was equivalent to 4.8th grade. This demonstrated that almost all the patients were satisfied with the answers from ChatGPT, although their education level was low.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003e3.5 Readability analysis\u003c/h2\u003e\u003cp\u003eTo assess the readability of the ChatGPT responses, we analyzed the FKGL scores. The average FKGL for all the responses was 9.45 (95% CI, SD 0.76), suggesting a reading level of 9th grade or higher. After the ChatGPT was instructed to provide answers in an easy-to-understand manner, the mean FKGL decreased to 8.75(95% CI, SD 0.62). Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows the FKGL scores for the responses to the 10 questions. An independent samples t-test revealed a significant improvement in readability post-instruction (p\u0026thinsp;\u0026lt;\u0026thinsp;0.05). The second ChatGPT response is shown in Supplement Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. Therefore, the answers from ChatGPT were fit for a reading level of 8th grade or above.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eThe readability analysis score FKGL\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"11\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFKGL\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eQ1\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eQ2\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eQ3\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eQ4\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eQ1\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eQ2\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003eQ3\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003eQ4\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c10\"\u003e\u003cp\u003eQ1\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c11\"\u003e\u003cp\u003eQ2\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eV1\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e9.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e8.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e9.03\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e10.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e8.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e9.74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e8.94\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e10.77\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e9.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e8.83\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eV2\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e8.27\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e7.97\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e8.92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e8.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e7.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e8.42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e9.57\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e9.57\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e9.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e8.36\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eFKGL, Flesch-Kincaid Grade Level; Q1-Q10 corresponds to the ten questions in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e1\u003c/span\u003e; V1 represents the score for the first answer to each question; V2 represents the score when ChatGPT was instructed to provide an easily understandable answer.\u003c/p\u003e\u003c/div\u003e"},{"header":"4. Discussion","content":"\u003cp\u003eIn our study, patients' common concerns about perioperative TKA focused on the cost of surgery, postoperative pain, surgical procedure, recovery time, mobility, dietary advice, presurgical preparation, and postoperative continence problems. These concerns reflected patients' real worries about surgical safety, the recovery process, quality of life, and financial burden.\u003c/p\u003e\u003cp\u003eMoreover, the surgeon group gave high ratings to ChatGPT's responses, with an average satisfaction score of 4.72/5.00. Professionalism and accuracy were rated at 4.41/5.00 and 4.36/5.00, respectively. These ratings demonstrated the value of ChatGPT in medical communication. Moreover, most surgeons are willing to use ChatGPT to answer 80%-100% of their patients' questions. These findings suggest that surgeons perceive ChatGPT to be reliable in conveying medical knowledge and providing professional advice, although it may not always meet the highest standards of professional medical communication.\u003c/p\u003e\u003cp\u003eThis study revealed that patients were highly satisfied with the responses of the ChatGPT (mean score 4.99), indicating its significant potential to improve patients' access to information. In contrast, surgeon satisfaction with ChatGPT responses was rated at 4.72, which was lower than patient satisfaction. This difference may reflect differences in evaluation criteria: patients are more concerned with the comprehensibility of the responses, whereas surgeons are more interested in the medical expertise and precision of the responses.\u003c/p\u003e\u003cp\u003eChatGPT, as a cutting-edge AI technology, has shown great potential in the field of medical communication. In the field of epilepsy, Wu et al. reported that ChatGPT offered \"accurate and thorough\" responses to more than 50% of inquiries[\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. Another dentistry study also demonstrated that ChatGPT can significantly enhance the efficiency and quality of dental telemedicine[\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. Similarly, Bahar et al. reported that ChatGPT accurately and satisfactorily answered more than 90% of endometriosis questions[\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. In the orthopedic research field, there are numerous studies related to the ChatGPT. Aleksander et al. reported that satisfactory AI responses in THA patients require only minimal clarification[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. In the specialized field of arthroplasty, the ChatGPT has been shown to provide precise and detailed responses, which positively impact patients' preoperative anxiety and enhance their understanding of the surgical procedure[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e, \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eHowever, the limitations of these studies include the failure to collect questions and the real needs of TKA patients, the lack of response scores from orthopedic surgeons with different experience levels, and the exploration of surgeons' opinions about the use of the ChatGPT to answer patient questions. Therefore, we conducted this study to investigate the effectiveness of ChatGPT in patient communication. Compared with their study, we gathered many real questions from patients and sent questionnaires to surgeons at various levels in different hospitals to obtain their ratings of ChatGPT responses. We also introduced a readability score to analyze the readability of these responses.\u003c/p\u003e\u003cp\u003eAt the end of the questionnaire, surgeons' recommendations for ChatGPT responses were analyzed. Most studies reported satisfactory and accurate responses, but some mentioned the need for enhanced detailed information, review of information sources, and personalized medicine. Moreover, some surgeons have mentioned that the answers of the ChatGPT are generic and nonspecific. This feedback indicated that there are still shortcomings in ChatGPT responses and areas for further improvement. We also identified the limitations of ChatGPT in dealing with certain complex medical issues, particularly in providing personalized medical advice and citing the latest medical protocols. This finding emphasized that, although AI shows promise in healthcare, its effectiveness depends on integration with healthcare professionals' knowledge and experience [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eAlthough ChatGPT's information is generally valid, accurate, and professional, it can be affected by a variety of factors. Our study revealed that the level of the hospital and the experience of the surgeon are significant factors affecting judgment. We believe that this is due to differences in expertise, medical experience, background, and the application of medical technology among surgeons. Surgeons at top hospitals often have greater expertise, experience, backgrounds, advanced equipment, extensive case databases, and multidisciplinary support. In Mohammad Hosseini's study, significant differences in acceptance and willingness to use ChatGPT were observed between trainees (e.g., students, residents, and fellows) and faculty (e.g., professors and senior fellows). Varying levels of knowledge about ChatGPT and other LLMs may lead to different levels of acceptance of these technologies. An individual's academic background and professional training also influence their acceptance of ChatGPT[\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]. Given the importance of the hospital and surgeon levels, future research should assess the attitudes of patients and surgeons toward AI tools and explore how these tools can be effectively integrated into existing surgeon-patient communication processes[\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eWe conducted a readability analysis, and the results indicated that the majority of the responses were suitable for individuals with a reading level of 9th grade or higher. After we instructed ChatGPT to provide answers in an easy-to-understand manner, the reading difficulty significantly decreased. We also found that ChatGPT can tailor its responses according to the educational background of patients, providing answers suitable for their comprehension. Additionally, ChatGPT can provide multiple response options for a single question, thereby addressing different aspects of patients' needs. This flexibility in generating diverse responses is a notable feature that has been overlooked by most researchers.\u003c/p\u003e\u003cp\u003eThis study has several limitations. First, the participating surgeons were all from Grade 2A or higher hospitals, which are the only facilities that are qualified to perform TKA in China. Therefore, the results may not reflect the perspectives of surgeons in lower-tier hospitals. Second, the patient cohort generally had low education levels, as most patients undergoing TKA are older and have grown up in an era with limited access to compulsory education. This may have influenced their understanding and evaluation of the responses of ChatGPT. Finally, only the top 10 most frequently asked questions were analyzed, leaving other patient concerns unaddressed. However, we believe that these questions are representative of the primary concerns of perioperative TKA and rehabilitation.\u003c/p\u003e"},{"header":"5. Conclusions","content":"\u003cp\u003eOverall, questionnaire collection identifies genuine clinical needs of patients. The application of the ChatGPT in TKA patient communication has yielded positive initial results. Additionally, many surgeons are willing to use ChatGPT to answer most of their patients' questions. Although there are differences in satisfaction and accuracy among different hospital levels and surgeons with different titles, overall, surgeons are highly satisfied with the accuracy of using ChatGPT to answer questions. Patient satisfaction with the responses was greater, likely due to the comprehensive and understandable nature of the information provided by the ChatGPT. It is expected that ChatGPT will become an important tool for medical communication and is expected to improve the quality of patient education and communication.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eFlesch-Kincaid Grade Level (FKGL)\u003c/p\u003e\n\u003cp\u003eTotal knee arthroplasty (TKA)\u003c/p\u003e\n\u003cp\u003eartificial intelligence (AI)\u003c/p\u003e\n\u003cp\u003elarge language models (LLMs)\u003c/p\u003e\n\u003cp\u003eStatistical Package for the Social Sciences 26 (SPSS 26)\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003eEthics approval and consent to participate: The protocol of this retrospective study was approved by the ethics committees of the Second Affiliated Hospital of Wenzhou Medical University. The study was conducted in accordance to the declaration of Helsinki. Informed consent to participate was obtained from all participants included in the study.\u003c/p\u003e\n\u003cp\u003eConsent for publication: Not applicable.\u003c/p\u003e\n\u003cp\u003eAvailability of data and materials: The data\u0026nbsp;and materials\u0026nbsp;that support the findings of this study are not openly available due to reasons of sensitivity and are available from the corresponding author upon reasonable request.\u003c/p\u003e\n\u003cp\u003eCompeting interests: The authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003eFunding: This research received no external funding.\u003c/p\u003e\n\u003cp\u003eAuthors\u0026apos; contributions:\u0026nbsp;\u003c/p\u003e\n\u003cul\u003e\n \u003cli\u003eConceptualization: P.F.\u003c/li\u003e\n \u003cli\u003eData collection: Y.L.\u003csup\u003e\u0026nbsp;\u003c/sup\u003e\u003c/li\u003e\n \u003cli\u003eFormal analysis: P.F.\u003c/li\u003e\n \u003cli\u003eMethodology: P.F., Z.D., Z.L.\u003c/li\u003e\n \u003cli\u003eProject administration: J.Z.\u003c/li\u003e\n \u003cli\u003eResources: Y.J., Z.S., L.Z., Z.L., Q.S.\u003c/li\u003e\n \u003cli\u003eSoftware: P.F.\u003c/li\u003e\n \u003cli\u003eSupervision: P.F.\u003c/li\u003e\n \u003cli\u003eVisualization: J.Z.\u003c/li\u003e\n \u003cli\u003eData analysis: Y.J., Z.L.\u003c/li\u003e\n \u003cli\u003eWriting-original draft: Y.J.\u003c/li\u003e\n \u003cli\u003eWriting-review \u0026amp; editing: P.F.\u003c/li\u003e\n \u003cli\u003eAll authors approved the final version to be published.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eAcknowledgements: We gratefully acknowledge statistics assistance from Dr. Qun Wang.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eSiddiqi A, Levine BR, Springer BD. Highlights of the 2021 American joint replacement registry annual report. Arthroplasty Today. 2022;13:205\u0026ndash;207. doi: 10.1016/j.artd.2022.01.020.\u003c/li\u003e\n\u003cli\u003eSingh JA, Yu S, Chen L, Cleveland JD. Rates of total joint replacement in the united states: Future projections to 2020-2040 using the national inpatient sample. J Rheumatol. 2019;46:1134\u0026ndash;1140. doi: 10.3899/jrheum.170990.\u003c/li\u003e\n\u003cli\u003eTrousdale RT, McGrory BJ, Berry DJ, Becker MW, Harmsen WS. Patients\u0026rsquo; concerns prior to undergoing total hip and total knee arthroplasty. Mayo Clin Proc. 1999;74:978\u0026ndash;982. doi: 10.4065/74.10.978.\u003c/li\u003e\n\u003cli\u003eMacario A, Schilling P, Rubio R, Bhalla A, Goodman S. What questions do patients undergoing lower extremity joint replacement surgery have? BMC health services research. 2003;3:11. doi: 10.1186/1472-6963-3-11.\u003c/li\u003e\n\u003cli\u003eCalixte R, Rivera A, Oridota O, Beauchamp W, Camacho-Rivera M. Social and demographic patterns of health-related internet use among adults in the united states: A secondary data analysis of the health information national trends survey. Int J Environ Res Public Health. 2020;17:6856. doi: 10.3390/ijerph17186856.\u003c/li\u003e\n\u003cli\u003eThe most recent time you looked for information about health or medical topics, where did you go first? | HINTS [Internet]. [cited 2024 Apr 21]. Available from: https://hints.cancer.gov/view-questions/question-detail.aspx?PK_Cycle=11\u0026amp;qid=688.\u003c/li\u003e\n\u003cli\u003eSa C, Le C, Jd T, G B, R L, M S, Nd H. Google trends as a tool for evaluating public interest in total knee arthroplasty and total hip arthroplasty. Journal of clinical and translational research [Internet]. 2021 [cited 2024 Jan 31];7. Cited: in: : PMID: 34667892.\u003c/li\u003e\n\u003cli\u003eAssessing, controlling, and assuring the quality of medical information on the internet: Caveant lector et viewor--let the reader and viewer beware - PubMed [Internet]. [cited 2024 Apr 21]. Available from: https://pubmed.ncbi.nlm.nih.gov/9103351/.\u003c/li\u003e\n\u003cli\u003eInternet use by orthopaedic outpatients - current trends and practices - PubMed [Internet]. [cited 2024 Apr 21]. Available from: https://pubmed.ncbi.nlm.nih.gov/23382767/.\u003c/li\u003e\n\u003cli\u003eReadability of patient education materials from the American academy of orthopaedic surgeons and pediatric orthopaedic society of north america web sites - PubMed [Internet]. [cited 2024 Apr 20]. Available from: https://pubmed.ncbi.nlm.nih.gov/18171975/.\u003c/li\u003e\n\u003cli\u003eMost American academy of orthopaedic surgeons\u0026rsquo; online patient education material exceeds average patient reading level - PubMed [Internet]. [cited 2024 Apr 21]. Available from: https://pubmed.ncbi.nlm.nih.gov/25475715/.\u003c/li\u003e\n\u003cli\u003eDavaris MT, Dowsey MM, Bunzli S, Choong PF. Arthroplasty information on the internet: Quality or quantity? Bone \u0026amp; Joint Open. 2020;1:64\u0026ndash;73. doi: 10.1302/2633-1462.14.BJO-2020-0006.\u003c/li\u003e\n\u003cli\u003eNg MK, Emara AK, Molloy RM, Krebs VE, Mont M, Piuzzi NS. YouTube as a source of patient information for total knee/hip arthroplasty: Quantitative analysis of video reliability, quality, and content. J Am Acad Orthop Surg. 2021;29:e1034\u0026ndash;e1044. doi: 10.5435/JAAOS-D-20-00910.\u003c/li\u003e\n\u003cli\u003eLatif MZ, Hussain I, Saeed R, Qureshi MA, Maqsood U. Use of smart phones and social media in medical education: Trends, advantages, challenges and barriers. Acta informatica medica: AIM: journal of the Society for Medical Informatics of Bosnia \u0026amp; Herzegovina: casopis Drustva za medicinsku informatiku BiH. 2019;27:133\u0026ndash;138. doi: 10.5455/aim.2019.27.133-138. Cited: in: : PMID: 31452573.\u003c/li\u003e\n\u003cli\u003eShen TS, Driscoll DA, Islam W, Bovonratwet P, Haas SB, Su EP. Modern Internet Search Analytics and Total Joint Arthroplasty: What Are Patients Asking and Reading Online? J Arthroplasty. 2021;36:1224\u0026ndash;1231. doi: 10.1016/j.arth.2020.10.024.\u003c/li\u003e\n\u003cli\u003eSpandorfer JM, Karras DJ, Hughes LA, Caputo C. Comprehension of discharge instructions by patients in an urban emergency department. Ann Emerg Med. 1995;25:71\u0026ndash;74. doi: 10.1016/s0196-0644(95)70358-6.\u003c/li\u003e\n\u003cli\u003eLopez CD, Ding J, Trofa DP, Cooper HJ, Geller JA, Hickernell TR. Machine Learning Model Developed to Aid in Patient Selection for Outpatient Total Joint Arthroplasty. Arthroplasty Today. 2022;13:13\u0026ndash;23. doi: 10.1016/j.artd.2021.11.001.\u003c/li\u003e\n\u003cli\u003eLopez CD, Gazgalis A, Boddapati V, Shah RP, Cooper HJ, Geller JA. Artificial Learning and Machine Learning Decision Guidance Applications in Total Hip and Knee Arthroplasty: A Systematic Review. Arthroplasty Today. 2021;11:103\u0026ndash;112. doi: 10.1016/j.artd.2021.07.012.\u003c/li\u003e\n\u003cli\u003eHonda S, Noguchi T. Promise and pitfalls of ChatGPT for patient education on coronary angiogram. Annals of the Academy of Medicine, Singapore. 2023;52:338\u0026ndash;339. doi: 10.47102/annals-acadmedsg.2023225. Cited: in: : PMID: 38904498.\u003c/li\u003e\n\u003cli\u003ePatient education and health literacy - PubMed [Internet]. [cited 2024 Apr 20]. Available from: https://pubmed.ncbi.nlm.nih.gov/30017902/.\u003c/li\u003e\n\u003cli\u003eKuroiwa T, Sarcon A, Ibara T, Yamada E, Yamamoto A, Tsukamoto K, Fujita K. The Potential of ChatGPT as a Self-Diagnostic Tool in Common Orthopedic Diseases: Exploratory Study. J Med Internet Res. 2023;25:e47621. doi: 10.2196/47621.\u003c/li\u003e\n\u003cli\u003eLeveraging large language models (LLM) for the plastic surgery resident training: Do they have a role? - PubMed [Internet]. [cited 2024 Apr 21]. Available from: https://pubmed.ncbi.nlm.nih.gov/38026769/.\u003c/li\u003e\n\u003cli\u003eRao A, Pang M, Kim J, Kamineni M, Lie W, Prasad AK, Landman A, Dreyer KJ, Succi MD. Assessing the utility of ChatGPT throughout the entire clinical workflow. medRxiv: The Preprint Server for Health Sciences. 2023;2023.02.21.23285886. doi: 10.1101/2023.02.21.23285886. Cited: in: : PMID: 36865204.\u003c/li\u003e\n\u003cli\u003eMika AP, Martin JR, Engstrom SM, Polkowski GG, Wilson JM. Assessing ChatGPT Responses to Common Patient Questions Regarding Total Hip Arthroplasty. J Bone Joint Surg. 2023;105:1519\u0026ndash;1526. doi: 10.2106/JBJS.23.00209.\u003c/li\u003e\n\u003cli\u003eKienzle A, Niemann M, Meller S, Gwinner C. ChatGPT May Offer an Adequate Substitute for Informed Consent to Patients Prior to Total Knee Arthroplasty-Yet Caution Is Needed. Journal of Personalized Medicine. 2024;14:69. doi: 10.3390/jpm14010069.\u003c/li\u003e\n\u003cli\u003eWright BM, Bodnar MS, Moore AD, Maseda MC, Kucharik MP, Diaz CC, Schmidt CM, Mir HR. Is ChatGPT a trusted source of information for total hip and knee arthroplasty patients? Bone \u0026amp; Joint Open. 2024;5:139\u0026ndash;146. doi: 10.1302/2633-1462.52.BJO-2023-0113.R1.\u003c/li\u003e\n\u003cli\u003eSmith AM, Jacquez EA, Argintar EH. Assessing the efficacy of an AI-powered chatbot (ChatGPT) in providing information on orthopedic surgeries: A comparative study with expert opinion. Cureus. 2024;16:e63287. doi: 10.7759/cureus.63287.\u003c/li\u003e\n\u003cli\u003eJain N, Gottlich C, Fisher J, Campano D, Winston T. Assessing ChatGPT\u0026rsquo;s orthopedic in-service training exam performance and applicability in the field. Journal of Orthopaedic Surgery and Research. 2024;19:27. doi: 10.1186/s13018-023-04467-0.\u003c/li\u003e\n\u003cli\u003eWu Y, Zhang Z, Dong X, Hong S, Hu Y, Liang P, Li L, Zou B, Wu X, Wang D, et al. Evaluating the performance of the language model ChatGPT in responding to common questions of people with epilepsy. Epilepsy \u0026amp; Behavior: E\u0026amp;B. 2024;151:109645. doi: 10.1016/j.yebeh.2024.109645. Cited: in: : PMID: 38244419.\u003c/li\u003e\n\u003cli\u003eEggmann F, Weiger R, Zitzmann NU, Blatz MB. Implications of large language models such as ChatGPT for dental medicine. J Esthet Restor Dent. 2023;35:1098\u0026ndash;1102. doi: 10.1111/jerd.13046.\u003c/li\u003e\n\u003cli\u003eOzgor BY, Simavi MA. Accuracy and reproducibility of ChatGPT\u0026rsquo;s free version answers about endometriosis. International Journal of Gynaecology and Obstetrics: The Official Organ of the International Federation of Gynaecology and Obstetrics. 2023; doi: 10.1002/ijgo.15309. Cited: in: : PMID: 38108232.\u003c/li\u003e\n\u003cli\u003eGordijn B, Have H ten. ChatGPT: evolution or revolution? Medicine, Health Care and Philosophy. 2023;26:1\u0026ndash;2. doi: 10.1007/s11019-023-10136-0.\u003c/li\u003e\n\u003cli\u003eHosseini M, Gao CA, Liebovitz D, Carvalho A, Ahmad FS, Luo Y, MacDonald N, Holmes K, Kho A. An exploratory survey about using ChatGPT in education, healthcare, and research. medRxiv: The Preprint Server for Health Sciences. 2023;2023.03.31.23287979. doi: 10.1101/2023.03.31.23287979. Cited: in: : PMID: 37066228.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-orthopaedic-surgery-and-research","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"josr","sideBox":"Learn more about [Journal of Orthopaedic Surgery and Research](http://josr-online.biomedcentral.com)","snPcode":"13018","submissionUrl":"https://submission.nature.com/new-submission/13018/3","title":"Journal of Orthopaedic Surgery and Research","twitterHandle":"@MSKmedBMC","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Total Knee Arthroplasty, Artificial Intelligence, ChatGPT, Patient communication, Patient Satisfaction","lastPublishedDoi":"10.21203/rs.3.rs-7122725/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7122725/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e\u003cp\u003eChatGPT has proven its value in medical information acquisition and perioperative education. This study aimed to evaluate correlated factors to explore the value of ChatGPT in patient communication.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e\u003cp\u003e220 questions were collected from patients undergoing TKA. The selected questions were answered by ChatGPT-3.5. Questionnaires were created and sent to surgeons and patients. Some features of respondents were collected and investigated for analysis. Readability scores were assessed via the Flesch-Kincaid Grade Level (FKGL).\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eThe most common question from patients was about operation costs. Satisfaction scores from patients and surgeons were both high. Correlation analysis revealed that surgeon\u0026rsquo;s score was influenced by hospital level and surgery experience. The readability scores for FKGL were high.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e\u003cp\u003eCollecting questionnaires reveals patients' real clinical needs. The results of the study showed that ChatGPT has potential to be a tool for communicating with patients. ChatGPT responses require a high level of education although this level of education can be reduced.\u003c/p\u003e","manuscriptTitle":"Evaluating ChatGPT Responses to Frequently Asked Questions on Total Knee Arthroplasty","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-23 06:14:47","doi":"10.21203/rs.3.rs-7122725/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-04T02:28:06+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-04T02:17:43+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-03T02:21:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"82332678002693288835513562169242500335","date":"2025-07-28T03:04:42+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-26T09:19:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"16383884470466559233334829209449112172","date":"2025-07-25T17:34:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"35230839557866895238238700141682222022","date":"2025-07-25T15:47:45+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-24T16:19:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"26706714579055675335900685435196102964","date":"2025-07-24T14:57:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"209158042779300525326038334994020786174","date":"2025-07-24T14:35:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"162784862498212459321455567008242090912","date":"2025-07-24T14:31:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"169810349050577696003402294348240626676","date":"2025-07-22T22:13:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"56438962939701745412276801893498453394","date":"2025-07-16T12:26:09+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-16T12:18:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-15T03:41:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-15T03:06:14+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Orthopaedic Surgery and Research","date":"2025-07-14T15:14:42+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-orthopaedic-surgery-and-research","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"josr","sideBox":"Learn more about [Journal of Orthopaedic Surgery and Research](http://josr-online.biomedcentral.com)","snPcode":"13018","submissionUrl":"https://submission.nature.com/new-submission/13018/3","title":"Journal of Orthopaedic Surgery and Research","twitterHandle":"@MSKmedBMC","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"114049c4-1b0c-4d03-88b3-1d0c670c1137","owner":[],"postedDate":"July 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-15T16:07:40+00:00","versionOfRecord":{"articleIdentity":"rs-7122725","link":"https://doi.org/10.1186/s13018-025-06451-2","journal":{"identity":"journal-of-orthopaedic-surgery-and-research","isVorOnly":false,"title":"Journal of Orthopaedic Surgery and Research"},"publishedOn":"2025-12-08 15:58:24","publishedOnDateReadable":"December 8th, 2025"},"versionCreatedAt":"2025-07-23 06:14:47","video":"","vorDoi":"10.1186/s13018-025-06451-2","vorDoiUrl":"https://doi.org/10.1186/s13018-025-06451-2","workflowStages":[]},"version":"v1","identity":"rs-7122725","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7122725","identity":"rs-7122725","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}