SMART NOTES IN THE OPERATION THEATRE: A CROSS-SECTIONAL COMPARISON OF CHATGPT VERSUS SURGEON GENERATED OPERATIVE DOCUMENTATION IN LAPAROSCOPIC CHOLECYSTECTOMY
DOI:
https://doi.org/10.69980/ajpr.v28i5.824Keywords:
Large Language Models (LLM), ChatGPT, AI-generated operative note, Conventional operative note, Laparoscopic CholecystectomyAbstract
Objective: To compare the completeness, guideline adherence, time efficiency and user satisfaction of operative notes generated by ChatGPT versus those written by general surgery residents.
Methods: This study included 118 patients undergoing Laparoscopic Cholecystectomy in the Department of General Surgery, Dow University Hospital over a period of three months from August to October 2025. For each case, operative notes were generated using ChatGPT (open AI platform) with a standardized prompt and compared with conventional surgeon written notes. AI generated data was reviewed for factual inconsistencies. Using Royal College of Surgeons guidelines, completeness, accuracy and guideline adherence was assessed. Time for each note completion was recorded. User satisfaction was also assessed. Using SPSS version 27, data was assessed.
Results: A total of 118 patients were enrolled in this study with the mean age of 43.75 ± 14.21 years. There were 54.2% females and 45.8% males. Symptomatic Cholelithiasis was the most common diagnosis. ChatGPT generated operative notes took considerably less amount of time than human written notes (6.6 seconds vs 5.43 minutes; p value of < 0.001). A 100% guideline adherence was observed in AI generated notes to 59.3% in human written notes. Factual inaccuracies were noted in 32 (27.11%) of the cases but those became less evident with each new entry. Documentation of anticipated blood loss and DVT prophylaxis was more significant in AI generated notes. For AI-generated notes, 93.3% of the surgeons reported being very satisfied, and for conventional notes, and 80% reported their satisfaction. A majority of respondents (96.7%) stated that they would recommend AI generated operative notes for clinical documentation.
Conclusion: Large Language Models such as ChatGPT may facilitate structured, comprehensive and time efficient operative note writing, reducing burden of documentation in busy surgical settings. However, the accuracy and reliability of AI generated notes depend on precise surgeon input, and human oversight remains essential to ensure clinical accountability.
References
1. Ghosh A. An audit of orthopedic operation notes: what are we missing? Clin Audit. 2010;2:37-40. doi:10.2147/CA.S9665
2. Mathew J, Baylis C, Saklani A, Al-Dabbagh A. Quality of operative notes in a district general hospital: a time for change? Internet J Surg. 2002;5:10.
3. Desiree RM, Kabir R. Wrist fracture management and the role of surgical care practitioner through the patient’s journey. J Perioper Pract. 2022;32:115–22.
4. Mathioudakis A, Rousalova I, Gagnat AA, et al. How to keep good clinical records. Breathe (Sheff). 2016;12:369–73.
5. Ma GW, Pooni A, Forbes SS, et al. Quality of inguinal hernia operative reports: room for improvement. Can J Surg. 2013;56:393.
6. Singh R, Chauhan R, Anwar S. Improving the quality of general surgical operation notes in accordance with the Royal College of Surgeons guidelines: a prospective completed audit loop. J Eval Clin Pract. 2012;18(3):578–80. doi:10.1111/j.1365-2753.2010.01626.
7. De Angelis L, Colaprico A, Carcagnì A, et al. ChatGPT and the rise of large language models: the new AI-driven infodemic threat in public health. Front Public Health. 2023;11:1180842.
8. Kasneci E, Seßler K, Küchemann S, Bannert M, Dementieva D, Fischer F, et al. ChatGPT for good? On opportunities and challenges of large language models for education. Learn Individ Differ. 2023;103:102274.
9. Webb M. A generative AI primer [Internet]. Bristol (UK): Jisc; 2023 [cited 2025 May 24]. Available from: https://nationalcentreforai.jiscinvolve.org/wp/2023/05/11/generative-ai-primer/
10. Abdelhady AM, Davis CR. Plastic surgery and artificial intelligence: how ChatGPT improved operation note accuracy, time, and education. Mayo Clin Proc Digit Health. 2023;1(3):299–308.
11. Lefter LP, Walker SR, Dewhurst F, Turner RWL. An audit of operative notes: Facts and ways to improve. ANZ J Surg. 2008; 78(9):800-2.
12. Cutting J, Hossain T, Maude K. Quality of operation note documentation in general surgical patients: Re-audit results. Int J Surg 2014; 12:S50.
13. Robinson A, Aggarwal S, Aggarwal Jr S. When precision meets penmanship: ChatGPT and surgery documentation. Cureus. 2023 Jun 17;15(6).
14. Bhattacharyya M, Miller VM, Bhattacharyya D, Miller LE, Miller V. High rates of fabricated and inaccurate references in ChatGPT-generated medical content. Cureus. 2023 May 19;15(5).
15. Li Y, Li Z, Zhang K, Dan R, Zhang Y. ChatDoctor: a medical chat model fine-tuned on LLaMA model using medical domain knowledge. Preprint. Published online March. 2023;24.
16. Ma C, Wu Z, Wang J, et al. ImpressionGPT: An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT. Preprint. Published online April 17, 2023.
17. Powles J, Hodson H. Google DeepMind and healthcare in an age of algorithms. Health Technol (Berl). 2017;7(4):351-367.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 American Journal of Psychiatric Rehabilitation
This work is licensed under a Creative Commons Attribution 4.0 International License.
This is an Open Access article distributed under the terms of the Creative Commons Attribution 4.0 International License permitting all use, distribution, and reproduction in any medium, provided the work is properly cited.
This work is licensed under a 
