CoChat
Sign Up
Cited by 44Artificial Intelligence in Healthcare and EducationArtificial Intelligence ApplicationsTechnology and Human Factors in Education and Health

Application of ChatGPT for Orthopedic Surgeries and Patient Care

Open access
Morya, Vivek Kumar, Lee, Ho-Won, Shahid, Hamzah, Magar, Anuja Gajanan, Lee, Ju-Hyung, Kim, Jae-Hyung, Jun, Lang, Noh, Kyu-Cheol·2024·Clinics in Orthopedic Surgery
DOI 10.4055/cios23181PMC PMC11130626
Open this paper in CoChat — free accountOpen PDF

Abstract

Artificial intelligence (AI) has rapidly transformed various aspects of life, and the launch of the chatbot "ChatGPT" by OpenAI in November 2022 has garnered significant attention and user appreciation. ChatGPT utilizes natural language processing based on a "generative pre-trained transfer" (GPT) model, specifically the transformer architecture, to generate human-like responses to a wide range of questions and topics. Equipped with approximately 57 billion words and 175 billion parameters from online data, ChatGPT has potential applications in medicine and orthopedics. One of its key strengths is its personalized, easy-to-understand, and adaptive response, which allows it to learn continuously through user interaction. This article discusses how AI, especially ChatGPT, presents numerous opportunities in orthopedics, ranging from preoperative planning and surgical techniques to patient education and medical support. Although ChatGPT's user-friendly responses and adaptive capabilities are laudable, its limitations, including biased responses and ethical concerns, necessitate its cautious and responsible use. Surgeons and healthcare providers should leverage the strengths of the ChatGPT while recognizing its current limitations and verifying critical information through independent research and expert opinions. As AI technology continues to evolve, ChatGPT may become a valuable tool in orthopedic education and patient care, leading to improved outcomes and efficiency in healthcare delivery. The integration of AI into orthopedics offers substantial benefits but requires careful consideration and continuous improvement.

AI snapshot

Written from the paper’s full text.

TL;DR

This review discusses potential applications of ChatGPT in orthopedic surgery and patient care, including preoperative planning, intraoperative guidance, patient communication, education, and rehabilitation. It concludes that ChatGPT is a promising supplementary tool but currently limited by accuracy, transparency, bias, and inability to handle complex patient-specific reasoning.

Key findings

  • ChatGPT is described as a natural language processing model based on transformer architecture, trained with approximately 57 billion words and 175 billion parameters; the original GPT-3 model has 175 billion parameters, whereas GPT-2 has 1.5 billion.
  • Proposed orthopedic uses include preoperative planning, virtual surgical simulation, intraoperative guidance, image recognition, surgical workflow planning, procedural checklists, minimally invasive surgery, error prevention, collaborative surgery, patient education/communication, and postoperative rehabilitation.
  • The paper states ChatGPT may produce biased, inaccurate, or superficial responses; cannot detect sarcasm, irony, or patients’ emotional states; cannot perform physical examinations or interpret diagnostic images; lacks physical presence; has a knowledge cutoff of June 2021; and may generate inaccurate or fabricated references and artificial hallucinations.
  • Cited evidence includes that ChatGPT failed to pass the written part of the Fellowship of the Royal College of Surgeons examinations in Trauma and Orthopedics, and that in one study AI identified the same number of tibial plateau fractures as orthopedic specialists.

Methods

  • Narrative review/commentary synthesizing literature on AI and ChatGPT in orthopedics; no systematic review or primary clinical trial is reported.
  • To evaluate efficacy, the authors prepared hypothetical questions and scrutinized responses for ambiguity, with responses regenerated; details are said to be in Supplementary Material 1.
  • Main analysis is qualitative discussion of potential applications and limitations; no quantitative outcome data or formal statistical analysis is reported.

Limitations

  • Paper-stated limitations include accuracy and reliability concerns, lack of transparency in response generation, limited understanding of language nuances and emotional states, biased training data, inability to capture individual patient subtleties, lack of physical presence, knowledge cutoff of June 2021, lack of citations, artificial hallucinations, superficial or regenerated answers, inaccurate references, and failure on a trauma and orthopedics written examination.
  • Evident from the text: there is no systematic search strategy or inclusion criteria, the evaluation relies on hypothetical questions and authors’ impressions, and many proposed applications are speculative or future-oriented rather than empirically tested in this paper.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.4055/cios23181

Cites

44 of 44 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 108 cited sources checked · 0 supported · 0 flagged

  • Findingcitation

    ChatGPT's response on total hip arthroplasty neglects to address potential risks and complications such as damage to nearby organs or anesthesia-related concerns.

    “For instance, total hip arthroplasty neglects to address potential risks and complications associated with the surgery, such as damage to nearby organs or anesthesia-related concerns.”
    • Also stated in: § LIMITATIONS OF ChatGPT · plain
      “ChatGPT does not address any issues that could arise, such as damage that will occur to nearby organs during surgery, blood loss, or the risk of anesthesia.17)”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [17] Seth, 2023, J Orthop Sports Med source

      Not checked in the free run.

  • Findingown data

    ChatGPT's cost comparison had significantly changed values across regenerated answers.

    “The cost comparison also had significantly changed values, which can create a trust deficit between the patients and healthcare providers.”
    Quote in the paperNot a substantial claim
  • Premisereasoning

    ChatGPT's access to vast Internet information may lead to less detailed or accurate responses compared with those from qualified medical professionals or experts.

    “Its access to vast Internet information may lead to less detailed or accurate responses compared with those from qualified medical professionals/experts.”
    Quote in the paperSubstantial claim0 of 3 sources checked
    • cites [12] Vaishya, 2023, Diabetes Metab Syndr source

      Not checked in the free run.

    • cites [19] Ismail, 2023, J Am Coll Radiol source

      Not checked in the free run.

    • cites [21] 2023, Nat Med source

      Not checked in the free run.

  • Premisecitation

    Biased or inaccurate responses from ChatGPT may arise due to biases and limitations in the training data.

    “Biased or inaccurate responses may arise due to biases and limitations in the training data.13)”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [13] Atik, 2022, Jt Dis Relat Surg source

      Not checked in the free run.

  • Interpretationcitation

    ChatGPT assists surgeons in constructing personalized treatments and preoperative planning with accuracy and safety.

    “Furthermore, ChatGPT assists surgeons in constructing personalized treatments and preoperative planning with accuracy and safety.7)”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [7] Hernigou, 2023, Int Orthop source

      Not checked in the free run.

  • Classified as probably not a substantial claim. 35
  • May combine two claims. 39

  • Probably not a substantial claim: may not pass S4 (based).

    Findingreasoning

    ChatGPT fails when dealing with complex medical conditions.

    “Although ChatGPT can be employed in various orthopedic healthcare and research and development applications to improve the effectiveness and efficiency of information delivery, it fails when dealing with complex medical conditions.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    ChatGPT responses were sometimes very superficial and changed with regenerated answers for the same questions.

    “This shows that sometimes the ChatGPT responses were very superficial and changed with regenerated answers for the same questions.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    ChatGPT can respond to a wide range of domains, including medicine and healthcare.

    “Consequently, it can respond to a wide range of domains, including medicine and healthcare.5)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [5] Sedaghat, 2023, Clin Med (Lond) source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    ChatGPT's personalized and easy-to-understand responses are delivered efficiently within seconds.

    “One of the notable features of ChatGPT is its personalized and easy-to-understand responses, delivered efficiently within seconds.5)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [5] Sedaghat, 2023, Clin Med (Lond) source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    In orthopedics, deep learning has improved musculoskeletal diagnosis and surgical procedures, while natural language processing has simplified communication between physicians and patients.

    “In orthopedics, deep learning has improved musculoskeletal diagnosis and surgical procedures, while natural language processing has simplified communication between physicians and patients.1314)”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [13] Atik, 2022, Jt Dis Relat Surg source

      Not checked in the free run.

    • cites [14] Pruneski, 2023, Knee Surg Sports Traumatol Arthrosc source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    ChatGPT continuously learns from user interactions, becoming increasingly adaptive and responsive over time.

    “It continuously learns from user interactions, becoming increasingly adaptive and responsive over time.24)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [24] Lalevee, 2023, Foot Ankle Clin source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    ChatGPT is based on a transformer architecture that uses introspection mechanisms to capture long-range dependencies between words and sentences and to generate coherent and contextual responses.

    “The model is based on a transformer architecture that uses introspection mechanisms to capture long-range dependencies between words and sentences and to generate coherent and contextual responses.23)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [23] Flanagin, 2023, JAMA source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    The original GPT-3 model has 175 billion parameters, whereas the smaller GPT-2 model has 1.5 billion parameters.

    “For example, the original GPT-3 model has 175 billion parameters, whereas the smaller GPT-2 model has 1.5 billion parameters.4)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [4] OpenAI. ChatGPT: optimizing language models for dialogue [Internet]. OpenAI. 2022. cited 2024 Feb 1. Available from: https://chatgpt.r4wand.eu.org/

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    ChatGPT shows promise in assisting orthopedic surgeons, patients, and students, providing relevant information about orthopedic topics and acting as an informative tool for students.

    “ChatGPT shows promise in assisting orthopedic surgeons, patients, and students, providing relevant information about orthopedic topics and acting as an informative tool for students.7151617)”
    Quote in the paperSubstantial claim0 of 3 sources checked
    • cites [7] Hernigou, 2023, Int Orthop source

      Not checked in the free run.

    • cites [15] He, 2023, Ann Biomed Eng source

      Not checked in the free run.

    • cites [16] Mika, 2023, J Bone Joint Surg Am source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    ChatGPT can be used to explore various services ranging from patient services and medical support to education and healthcare.

    “Thus, it can be used to explore various services ranging from patient services and medical support to education and healthcare.6)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [6] Kung, 2023, PLOS Digit Health source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Using ChatGPT for tasks like medical diagnosis or legal advice raises ethical concerns regarding accountability and responsibility.

    “Additionally, using ChatGPT for tasks like medical diagnosis or legal advice raises ethical concerns regarding accountability and responsibility.8192021)”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites [8] Vaswani

      Not checked in the free run.

    • cites [19] Ismail, 2023, J Am Coll Radiol source

      Not checked in the free run.

    • cites [20] Dahmen, 2023, Knee Surg Sports Traumatol Arthrosc source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    ChatGPT can be used to support medical education, acting as a virtual assistant for medical students, answering their questions, and providing personalized feedback to enhance their learning experience.

    “Moreover, ChatGPT can be used to support medical education, acting as a virtual assistant for medical students, answering their questions, and providing personalized feedback to enhance their learning experience.12202228)”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites [12] Vaishya, 2023, Diabetes Metab Syndr source

      Not checked in the free run.

    • cites [20] Dahmen, 2023, Knee Surg Sports Traumatol Arthrosc source

      Not checked in the free run.

    • cites [22] Lecler, 2023, Diagn Interv Imaging source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    ChatGPT not only outlines the steps involved in surgery but also delves into expected outcomes, recovery process, and potential risks, thus empowering patients with comprehensive information.

    “It not only outlines the steps involved in the surgery but also delves into the expected outcomes, recovery process, and potential risks, thus empowering patients with comprehensive information.18)”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [18] Cheng, 2023, Int J Surg source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    ChatGPT can monitor patient vital signs, detect anomalies or deviations from the norm, and promptly alert the surgical team to potential complications.

    “Simultaneously, ChatGPT can monitor patient vital signs, detect anomalies or deviations from the norm, and promptly alert the surgical team to potential complications.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [28] Kirchner, 2023, Clin Orthop Relat Res source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationcitation

    ChatGPT extends its reach to the realm of patient education and engagement, offering a more straightforward and patient-centered approach.

    “Furthermore, ChatGPT extends its reach to the realm of patient education and engagement, offering a more straightforward and patient-centered approach.27)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [27] Mbakwe, 2023, PLOS Digit Health source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Interpretationcitation

    When combined with other AI tools, ChatGPT plays a pivotal role in radiology reports by effectively translating intricate medical jargon into simplified versions that improve communication between healthcare providers and patients.

    “When combined with other AI tools, ChatGPT plays a pivotal role in radiology reports by effectively translating intricate medical jargon into simplified versions that improve communication between healthcare providers and patients.”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites [12] Vaishya, 2023, Diabetes Metab Syndr source

      Not checked in the free run.

    • cites [20] Dahmen, 2023, Knee Surg Sports Traumatol Arthrosc source

      Not checked in the free run.

    • cites [22] Lecler, 2023, Diagn Interv Imaging source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    ChatGPT can provide patients with information about their medical condition, treatment, rehabilitation strategies, and expected recovery period, benefiting them and bridging the communication gap with surgeons.

    “ChatGPT can also provide patients with information about their medical condition, treatment, rehabilitation strategies, and expected recovery period, thus benefiting them and bridging the communication gap with surgeons.7)”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [7] Hernigou, 2023, Int Orthop source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    ChatGPT's capabilities extend to aid in the diagnosis of patient symptoms and interpretation of complex medical imaging.

    “Its capabilities extend to aid in the diagnosis of patient symptoms and interpretation of complex medical imaging.”
    Quote in the paperSubstantial claim0 of 3 sources checked
    • cites [12] Vaishya, 2023, Diabetes Metab Syndr source

      Not checked in the free run.

    • cites [20] Dahmen, 2023, Knee Surg Sports Traumatol Arthrosc source

      Not checked in the free run.

    • cites [22] Lecler, 2023, Diagn Interv Imaging source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationcitation

    By using ChatGPT, doctors can get an idea of the questions they can ask patients to ensure they fully understand the treatment.

    “By using ChatGPT, doctors can get an idea of the questions they can ask patients to ensure they fully understand the treatment.30)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [30] Liu, 2021, Curr Med Sci source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    During surgery, ChatGPT functions as a virtual assistant, providing real-time surgical navigation information and facilitating data recording for convenient postoperative use.

    “During surgery, ChatGPT functions as a virtual assistant, providing real-time surgical navigation information and facilitating data recording for convenient postoperative use.2125)”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [21] 2023, Nat Med source

      Not checked in the free run.

    • cites [25] Bernstein, 2023, Clin Orthop Relat Res source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Interpretationcitation

    ChatGPT's analysis of a patient's medical history and imaging studies could generate treatment recommendations based on established clinical guidelines and expert opinions, assisting orthopedic surgeons in decision-making.

    “ChatGPT’s analysis of a patient’s medical history and imaging studies could generate treatment recommendations based on established clinical guidelines and expert opinions, assisting orthopedic surgeons in decision-making.122022)”
    Quote in the paperSubstantial claim0 of 3 sources checked
    • cites [12] Vaishya, 2023, Diabetes Metab Syndr source

      Not checked in the free run.

    • cites [20] Dahmen, 2023, Knee Surg Sports Traumatol Arthrosc source

      Not checked in the free run.

    • cites [22] Lecler, 2023, Diagn Interv Imaging source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    For minimally invasive orthopedic procedures, ChatGPT can assist in instrument navigation and placement, optimizing the use of smaller incisions and reducing tissue damage.

    “For minimally invasive orthopedic procedures, ChatGPT can assist in instrument navigation and placement, optimizing the use of smaller incisions and reducing tissue damage.”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [13] Atik, 2022, Jt Dis Relat Surg source

      Not checked in the free run.

    • cites [33] Huang, 2023, Am J Cancer Res

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    Surgeons can interact with these virtual models to plan and practice surgical procedures, improve precision, and reduce the risk of errors during surgery.

    “Surgeons can interact with these virtual models to plan and practice surgical procedures, improve precision, and reduce the risk of errors during surgery.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [20] Dahmen, 2023, Knee Surg Sports Traumatol Arthrosc source

      Not checked in the free run.

  • May combine two claims.

    Interpretationreasoning

    ChatGPT can aid in planning and optimizing surgical procedures and in reducing postoperative risks and complications.

    “As AI algorithms gain insightful knowledge of designed implants and surgical techniques, ChatGPT can aid in planning and optimizing surgical procedures and in reducing postoperative risks and complications.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [7] Hernigou, 2023, Int Orthop source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    ChatGPT can help in personalized preoperative planning and precise implementation.

    “ChatGPT can help in personalized preoperative planning and precise implementation.”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites [21] 2023, Nat Med source

      Not checked in the free run.

    • cites [25] Bernstein, 2023, Clin Orthop Relat Res source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    ChatGPT can generate plain-language explanations of surgical procedures, expected outcomes, and potential risks, helping patients make informed decisions and alleviating anxiety before surgery.

    “It can generate plain-language explanations of surgical procedures, expected outcomes, and potential risks, helping patients make informed decisions and alleviating anxiety before surgery.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [26] Ollivier, 2023, Knee Surg Sports Traumatol Arthrosc source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    The empathetic and reassuring nature of ChatGPT interactions can help alleviate patient anxiety, foster trust, and strengthen doctor-patient relationships.

    “Furthermore, the empathetic and reassuring nature of ChatGPT interactions can help alleviate patient anxiety, foster trust, and strengthen doctor-patient relationships.28)”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [28] Kirchner, 2023, Clin Orthop Relat Res source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    This finding affirmed the potential of AI as a reliable tool in both diagnosis and treatment.

    “This finding affirmed the potential of AI as a reliable tool in both diagnosis and treatment.2831)”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites [28] Kirchner, 2023, Clin Orthop Relat Res source

      Not checked in the free run.

    • cites [31] O’Connor, 2023, Nurse Educ Pract source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    ChatGPT can assist in identifying anatomical structures, guiding instrument placement, and ensuring accurate alignment during joint replacement surgeries.

    “It can assist in identifying anatomical structures, guiding instrument placement, and ensuring accurate alignment during joint replacement surgeries.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [22] Lecler, 2023, Diagn Interv Imaging source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationcitation

    If the data used to train ChatGPT are biased, they could lead to biased or inaccurate responses.

    “If the data used to train ChatGPT are biased, they could lead to biased or inaccurate responses.2930)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [2930]

      Not checked in the free run.

    • Rests on an assumption: Language used in medicine is often technical and can be influenced by cultural and social factors.

  • May combine two claims.

    Interpretationcitation

    ChatGPT is limited by lack of physical presence in the surgical environment; it cannot physically manipulate or adjust implants or surgical instruments.

    “ChatGPT is limited by the lack of physical presence in the surgical environment as it cannot physically manipulate or adjust implants or surgical instruments.28)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [28] Kirchner, 2023, Clin Orthop Relat Res source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).

    Interpretationnone given

    Currently, ChatGPT is a valuable tool for obtaining surface-level information on various topics.

    “Currently, ChatGPT is a valuable tool for obtaining surface-level information on various topics.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Interpretationnone given

    ChatGPT's inability to detect sarcasm, irony, or patients' emotional states hinders effective communication.

    “Furthermore, the inability of ChatGPT to detect sarcasm, irony, or patients’ emotional states hinders effective communication.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    Intraoperatively, ChatGPT can function as a virtual assistant for surgeons, providing real-time surgical navigation information and facilitating data recording for convenient postoperative use.

    “Intraoperatively, ChatGPT can function as a virtual assistant for surgeons, providing real-time surgical navigation information and facilitating data recording for convenient postoperative use.26)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [26] Ollivier, 2023, Knee Surg Sports Traumatol Arthrosc source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Orthopedic surgeons can use ChatGPT to explain complex medical terms to patients in a concise and simpler manner, promoting better patient understanding.

    “During preoperative planning, orthopedic surgeons can use ChatGPT to explain complex medical terms to patients in a concise and simpler manner, promoting better patient understanding.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [2125]

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.

    Premisecitation

    Arthroscopy is a highly specialized field, and individual patient cases can vary significantly in complexity and surgical approaches.

    “Arthroscopy is a highly specialized field, and individual patient cases can vary significantly in terms of complexity and surgical approaches.39)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [39] Wang, 2023, Nature source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationreasoning

    ChatGPT has limitations that must be addressed for safe and effective use in orthopedic surgery.

    “Despite the potential benefits of improving communication between orthopedic surgeons and patients, ChatGPT has limitations that must be addressed for safe and effective use in orthopedic surgery.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    ChatGPT's provided references were inaccurate and could not be cross-referenced.

    “Perhaps the biggest limitation was that the references provided were inaccurate and could not be cross-referenced.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [41] Seth, 2023, Plast Reconstr Surg Glob Open source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    Lack of transparency in ChatGPT response generation raises concerns about trust between healthcare providers and patients.

    “The lack of transparency in response generation also raises concerns about the trust between healthcare providers and patients.”
    • Also stated in: § LIMITATIONS OF ChatGPT · plain
      “This lack of transparency can lead to mistrust between healthcare providers and patients.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Premisecitation

    ChatGPT provides clear and detailed summaries for certain surgical treatments but may only present the basics for others.

    “While ChatGPT provides clear and detailed summaries for certain surgical treatments, it may only present the basics for others.5)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [5] Sedaghat, 2023, Clin Med (Lond) source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Interpretationnone given

    ChatGPT's responses were limited by the word limit, which may restrict its use in medical research.

    “However, ChatGPT’s responses were limited by the word limit, which may restrict its use in medical research.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationnone given

    ChatGPT describes scientific data in ordinary language, making it easier for patients to understand medical terms.

    “It describes scientific data in ordinary language, making it easier for patients to understand medical terms.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationcitation

    Specialized orthopedic details and expertise are still necessary, making ChatGPT a supplementary tool rather than a comprehensive solution for orthopedic education.

    “Moreover, specialized orthopedic details and expertise are still necessary, making ChatGPT a supplementary tool rather than a comprehensive solution for orthopedic education.2840)”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [2840]

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    The present iteration of ChatGPT is still in its infancy for the healthcare industry and is unable to resolve complex or multi-logical concerns.

    “ChatGPT has been observed to help experts with their fundamental knowledge or assist them, but the present iteration of ChatGPT is still in its infancy for the healthcare industry; thus, it is unable to resolve complex or multi-logical concerns.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [2940]

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    In that study, most ChatGPT answers consisted of errors and surface-level information.

    “Furthermore, most answers consisted of errors and surface-level information.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [41] Seth, 2023, Plast Reconstr Surg Glob Open source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    ChatGPT may create false reports in the medical field, inadvertently causing more harm than good.

    “Currently, ChatGPT suffers from artificial hallucinations, suggesting it may create false reports in the medical field inadvertently causing more harm than good.43)”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [43] Khan, 2023, Pak J Med Sci

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationreasoning

    ChatGPT's use in healthcare orthopedics remains questionable until it is adequately trained to handle complex cases.

    “Thus, its use in healthcare orthopedics remains questionable until it is adequately trained to handle such cases.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim. May combine two claims.

    Interpretationnone given

    ChatGPT lacks citations for the information it provides, making it difficult for users to verify sources, potentially leading to biased representations that influence responses.

    “Furthermore, the lack of citations for the information provided by the chatbot makes it difficult for users to verify the sources, potentially leading to biased representations that influence the responses.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Premisecitation

    ChatGPT can help experts with their fundamental knowledge or assist them.

    “ChatGPT has been observed to help experts with their fundamental knowledge or assist them, but the present iteration of ChatGPT is still in its infancy for the healthcare industry; thus, it is unable to resolve complex or multi-logical concerns.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [2940]

      Not checked in the free run.

  • Classified as probably not a substantial claim. May combine two claims.

    Interpretationnone given

    ChatGPT provides simple explanations understandable by laypersons, but its limitations lie in complex tasks requiring multi-logical reasoning.

    “While it provides simple explanations that can be understood by laypersons, its limitations lie in complex tasks that require multi-logical reasoning.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.

    Interpretationnone given

    The complex algorithms used by ChatGPT are difficult to understand, making it difficult to assess the quality and accuracy of generated information.

    “The complex algorithms used by ChatGPT are difficult to understand, which makes it difficult to assess the quality and accuracy of the generated information.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Postoperatively, both surgeons and patients can use ChatGPT to design detailed rehabilitation programs tailored to individual patient needs.

    “Postoperatively, both surgeons and patients can use ChatGPT to design detailed rehabilitation programs tailored to individual patient needs.15)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [15] He, 2023, Ann Biomed Eng source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    ChatGPT can create interactive quizzes and educational tools for students, reinforcing learning and providing immediate feedback on their progress.

    “It can create interactive quizzes and educational tools for students, reinforcing learning and providing immediate feedback on their progress.33)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [33] Huang, 2023, Am J Cancer Res

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    ChatGPT was unable to implement higher-order judgments or employ multi-logical reasoning in clinical scenarios involving complex patient-specific factors.

    “ChatGPT was unable to implement higher-order judgments or employ multi-logical reasoning in clinical scenarios involving complex patient-specific factors.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [40] Wagner, 2024, Can Assoc Radiol J source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationnone given

    ChatGPT's inability to perform physical examinations or interpret diagnostic images limits its role in the surgical environment.

    “Additionally, the inability of ChatGPT to perform physical examinations or interpret diagnostic images limits its role in the surgical environment.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationnone given

    ChatGPT responses cannot replace human expertise and judgment, at least at this stage.

    “It is important to note that ChatGPT responses cannot replace human expertise and judgment, at least at this stage.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    ChatGPT occasionally provides incorrect or misleading information.

    “Although it is designed to provide helpful suggestions and recommendations, it occasionally provides incorrect or misleading information.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing). May combine two claims.

    Interpretationcitation

    ChatGPT lacks the expert opinions necessary for in-depth orthopedic research, limiting its impact on orthopedic surgeons.

    “Nonetheless, it lacks the expert opinions necessary for in-depth orthopedic research, limiting its impact on orthopedic surgeons.17)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [17] Seth, 2023, J Orthop Sports Med source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationnone given

    Surgery involves human qualities such as empathy and emotional intelligence, which cannot be fully replaced by AI technology.

    “Surgery involves human qualities such as empathy and emotional intelligence, which cannot be fully replaced by AI technology.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Interpretationreasoning

    The accuracy of ChatGPT responses depends on the quality and relevance of user input and the accuracy of the data used to train the model.

    “The accuracy of ChatGPT responses depends on various factors, including the quality and relevance of the user input and the accuracy of the data used to train the model.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationcitation

    ChatGPT cannot replace professional or expert medical advice or prescriptions.

    “It is also important to note that ChatGPT cannot replace professional/expert medical advice/prescriptions.121920)”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites 121920

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.

    Interpretationreasoning

    ChatGPT is valuable but not a replacement for trained medical professionals, especially in orthopedic surgery.

    “ChatGPT is valuable but not a replacement for trained medical professionals, especially in orthopedic surgery.”
    Quote in the paperNot a substantial claim
62 of 62

  • The paper relies on this without support.

    ChatGPT's training data contains sufficient and accurate orthopedic knowledge to provide relevant and reliable information for the applications described.

    “Consequently, it can respond to a wide range of domains, including medicine and healthcare.5)”

  • The paper relies on this without support.

    The hypothetical questions and responses prepared by the authors are representative of real-world orthopedic queries and sufficient to evaluate ChatGPT's potential in orthopedic care.

    “To evaluate the above, we prepared a set of hypothetical questions and evaluated their responses (Supplementary Material 1, including responses to general queries and detailed description of the situation).”

  • The paper relies on this without support.

    The potential of ChatGPT in orthopedic research remains unclear.

    “In the healthcare sector, previous studies have explored the application of ChatGPT, but its potential in orthopedic research remains unclear.”

  • The paper relies on this without support.

    Language used in medicine is often technical and can be influenced by cultural and social factors.

    “Language used in medicine is often technical and can be influenced by cultural and social factors.”

  • The paper relies on this without support.

    AI's ability to provide fast and reliable diagnostic data can significantly reduce the time required for treatment planning and design.

    “AI’s ability to provide fast and reliable diagnostic data can significantly reduce the time required for treatment planning and design.”
5 of 5

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

  • Conflicting claims about interpreting diagnostic images

    Major

    The limitations section says ChatGPT cannot interpret diagnostic images, while the image-recognition section says it can analyze live fluoroscopy and CT scans and assist with anatomical identification and instrument placement.

  • Orthopedic examination claim cites a radiology study

    Minor

    The cited reference 40 concerns retrieval of clinical radiological information, not the Fellowship of the Royal College of Surgeons examination described in the text.

  • Radiology-visit claim cites a thumb-arthritis study

    Minor

    The text attributes findings about patients' radiologist visits to reference 41, whose listed subject is base-of-thumb arthritis.

  • Thumb-arthritis claim cites a general AI overview

    Minor

    The thumb-arthritis study described in the text is listed as reference 41, but the sentence cites reference 42, a general overview of AI in medicine.

4 of 4

Cites

Flagged first, then by citations

1 of the 45 references couldn’t be matched to a known paper.

Research works printed but not linked: 6

  1. Vaswani, Attention is all you need: advances in neural information processing systems, 1
  2. Carpenter, 2023, Thoughts on AI’s impact on scholarly communications? an interview with ChatGPT
  3. Huang, 2023, Am J Cancer Res, 13, 1148
  4. Bhattacharyya, 2023, Cureus, 15, e39238
  5. Khan, 2023, Pak J Med Sci, 39, 605
  6. Tomar, 2023, Cureus, 15, e36290

Cited by

Sorted by citations

Related

Authors
Morya, V. K., Lee, H.-W., Shahid, H., Magar, A. G., Lee, J.-H., Kim, J.-H., Jun, L., & Noh, K.-C.
Affiliations
  • Hallym University Kangnam Sacred Heart Hospital (KR)
  • Department of Orthopedic Surgery, Hallym University Kangnam Sacred Heart Hospital, Seoul, Korea.
Corresponding author
Noh, Kyu-Cheol
ORCID
Venue
Clinics in Orthopedic Surgery
Publisher
XMLink
Published
2024
Volume
16
Issue
3
Pages
347
ISSN
  • 2005-291X (ISSN-L)
  • 2005-4408
DOI
10.4055/cios23181
PMC
PMC11130626
OpenAlex
W4398173188
Semantic Scholar
ec475c1997f97f069ea83cd457212e7b7a37a27c
Cited by
44
References
45
Citations by year
2026: 14 · 2025: 25 · 2024: 5
FWCI
1.00
Type
journal article
Language
en
Open access
Licence
Locations
  • Clinics in Orthopedic Surgery (publishedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by-nc)
  • PubMed (publishedVersion)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
  • Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Technology and Human Factors in Education and Health
Keywords
ChatGPT, large language models, orthopedic surgery, surgical planning, surgical technique, patient education, orthopaedic education, algorithmic bias, AI ethics, natural language processing
MeSH terms
Artificial Intelligence, Patient Care, Humans, Natural Language Processing, Orthopedic Procedures

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-07.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-07.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review