An artificial intelligence chatbot as a substitute for physician-patient counselling on perioperative anaesthesia in knee-related surgeries

Year 2026, Volume: 6 Issue: 1, 34 - 43, 12.03.2026

Mehmet Şahap , Nihal Gökbulut Özaslan , Enejd Veizi

https://doi.org/10.66235/kumj.1906313

https://izlik.org/JA98WB26BC

Abstract

Aims: The aim of this study was to evaluate the potential of Bard AI to provide patients with accurate and comprehensive information about spinal and general anaesthesia for knee-related surgeries, while also emphasizing the importance of physician oversight in interpreting AI-generated content.

Methods: Bard AI was asked to generate responses to questions on spinal and general anaesthesia and evaluated their accuracy based on current guidelines and physician experience. The questions were designed to emulate a real conversation. Two authors evaluated the responses for accuracy and comprehensiveness at the patient level.

Results: Some of the answers include a note emphasizing that the approach to each patient may differ. Generally, no major errors or misdirection were observed but specific questions, such as those on migraine, received answers deemed incomplete.

Conclusion: Bard Google AI can be utilized as a complementary tool in doctor-patient consultations for preoperative education. However, the role of doctors remains indispensable, and it is important for patients to consult their doctors to have their questions addressed and alleviate their concerns.

Keywords

Anaesthesia , artificial intelligence , bard , ChatGPT , arthroplasty

Ethical Statement

Real patients were not used in this study. The questions directed to the artificial intelligence robot were evaluated by experts. Therefore, ethics committee approval was not obtained.

References

• 1. Erivan R, Tardieu A, Villatte G, et al. Knee surgery trends and projections in France from 2008 to 2070. Orthop Traumatol Surg Res. 2020;106(5):893-902. doi:10.1016/j.otsr.2020.02.018
• 2. Khusid E, Lui B, Weber M, Kelleher DC, White RS. Enhanced recovery after hip/knee arthroplasty: Gaps in outcomes by race, ethnicity, and other social determinants of health. J Clin Anesth. 2023;89:111157. doi:10.1016/j.jclinane.2023.111157
• 3. Montes FR, Zarate E, Grueso R, et al. Comparison of spinal anaesthesia with combined sciatic-femoral nerve block for outpatient knee arthroscopy. J Clin Anesth. 2008;20(6):415-420. doi:10.1016/j.jclinane.2008.04.003
• 4. De Jong A, Penne C, Kapandji N, et al. Determinants of information provided by anaesthesiologists to relatives of patients during surgical procedures. BJA Open. 2023;7:100205. doi:10.1016/j.bjao.2023.100205
• 5. Urquhart AC, Antoniotti NM, Berg RL. Telemedicine--an efficient and cost-effective approach in parathyroid surgery. Laryngoscope. 2011;121(7):1422-1425. doi:10.1002/lary.21812
• 6. Şahin E, Yavuz Veizi BG, Naharci MI. Telemedicine interventions for older adults: A systematic review. J Telemed Telecare. 2024;30(2):305-319. doi:10.1177/1357633X211058340
• 7. Ram B, Pratima Verma PV. Artificial intelligence AI-based chatbot study of ChatGPT, Google AI Bard, and Baidu AI. World J Adv Eng Technol. Sci. 2023;8(1):258-261. doi.org/10.30574/wjaets.2023.8.1.0045
• 8. Totlis T, Natsis K, Filos D, et al. The potential role of ChatGPT and artificial intelligence in anatomy education: a conversation with ChatGPT. Surg Radiol Anat. 2023;45(10):1321-1329. doi:10.1007/s00276-023-03229-1
• 9. Kaarre J, Feldt R, Keeling LE, et al. Exploring the potential of ChatGPT as a supplementary tool for providing orthopaedic information. Knee Surg Sports Traumatol Arthrosc. 2023;31(11):5190-5198. doi:10.1007/s00167-023-07529-2
• 10. Giannakopoulos K, Kavadella A, Aaqel Salim A, Stamatopoulos V, Kaklamanos EG. Evaluation of the Performance of Generative AI Large Language Models ChatGPT, Google Bard, and Microsoft Bing Chat in Supporting Evidence-Based Dentistry: Comparative Mixed Methods Study. J Med Internet Res. 2023;25:e51580. doi:10.2196/51580
• 11. Javaid M, Haleem A, Singh RP. ChatGPT for healthcare services: an emerging stage for an innovative perspective. BenchCouncil Trans Benchmarks Stand Eval. 2023;3(1):100105. doi:10.1016/j.tbench.2023.100105
• 12. Goldstein JC, Goldstein HV. Artificial intelligence in anesthesiology: What are the missing pieces?. J Clin Anesth. 2021;71:110219. doi:10.1016/j.jclinane.2021.110219
• 13. Kanjee Z, Crowe B, Rodman A. Accuracy of a Generative Artificial Intelligence Model in a Complex Diagnostic Challenge. JAMA. 2023;330(1):78-80. doi:10.1001/jama.2023.8288
• 14. Albrecht E, Wegrzyn J, Dabetic A, El-Boghdadly K. The analgesic efficacy of iPACK after knee surgery: A systematic review and meta-analysis with trial sequential analysis. J Clin Anesth. 2021;72:110305. doi:10.1016/j.jclinane.2021.110305
• 15. Baratta JL, Schwenk ES. Regional versus general anaesthesia for ambulatory total hip and knee arthroplasty. Curr Opin Anaesthesiol. 2022;35(5):621-625. doi:10.1097/ACO.0000000000001170
• 16. Liao CY, Li CC, Liu HY, et al. Migraine Headaches after Major Surgery with General or Neuraxial Anaesthesia: A Nationwide Propensity-Score Matched Study. Int J Environ Res Public Health. 2021;19(1):362. doi:10.3390/ijerph19010362
• 17. Radkowski P, Fadrowska-Szleper M, Podhorodecka K, Mieszkowski M. Neurological Complications of Regional Anaesthesia: An Updated Review with Clinical Guidelines. Med Sci Monit. 2023;29:e940399. doi:10.12659/MSM.940399
• 18. Chervenak J, Lieman H, Blanco-Breindel M, Jindal S. The promise and peril of using a large language model to obtain clinical information: ChatGPT performs strongly as a fertility counseling tool with limitations. Fertil Steril. 2023;120(3 Pt 2):575-583. doi:10.1016/j.fertnstert.2023.05.151
• 19. Moore J, Grabb D, Agnew W, et al. Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers. FAccT. 2025;599–627. doi:10.1145/3715275.3732039.