Artificial intelligence-based detection of pre-operative surgical difficulty in laparoscopic cholecystectomy patients using gradient based model

Authors

  • Atul Kapoor Department of Radiology, Advanced Diagnostics, Amritsar, Punjab, India
  • Bholla Singh Sidhu Department of Surgery, Parwati Hospital Amritsar, Punjab, India
  • Jasdeep Singh Department of Surgery, Sukh Sagar Hospital, Amritsar, Punjab, India

DOI:

https://doi.org/10.18203/2349-2902.isj20250814

Keywords:

Laparoscopic cholecystectomy, Pericholecystic adhesion, Shear wave elastography, Ultrasonography

Abstract

Background: This study aimed to develop a gradient-based machine learning model to detect and assess potential challenges in laparoscopic cholecystectomy procedures.

Methods: This prospective study included 146 patients diagnosed with gallstones or long-term gallbladder inflammation. Ultrasound imaging and shear wave elastography were used to evaluate various factors including gallbladder location, wall thickness, stone size, cystic duct length, common bile duct, adhesions and complications. Patients were categorized into three groups based on surgical difficulty using a manual model (MM) and a machine learning (ML) model. The ML model utilized a gradient boost algorithm and was trained, validated and tested using patient data. Laparoscopic gallbladder removal was performed and the surgeon evaluated the difficulty and complications of the procedure. Statistical analyses, including parametric measures, correlation analyses and diagnostic analyses of both models, were conducted.

Results: Pericholecystic adhesions were the primary contributing factor to challenging laparoscopic cholecystectomies. The ML model achieved high accuracy (90%) for predicting preoperative surgical difficulty, with an area under the curve (AUC) of 1.0, for groups A and C and 0.89 for group B. Adhesion and cystic duct length were identified as the most significant factors in the ML model.

Conclusions: The study concluded that the application of machine learning, specifically the Gradient Boosting Machine (GBM) model, enhanced the results of the manual model and demonstrated superior precision in predicting preoperative surgical difficulty.

Metrics

Metrics Loading ...

References

Merkin A, Medvedev ON, Krishnamurthi R. Machine learning, artificial intelligence and dementia can predict current opinions in psychiatry. 2021;35(2);123–9. DOI: https://doi.org/10.1097/YCO.0000000000000768

Xie CY, Pang CL, Chan B, Wong EY, Dou Q, Vardhanabhuti V. Machine learning and radiomics applications in esophageal cancers using non-invasive imaging methods—a critical review of literature. Cancers. 2021;13(10):2469. DOI: https://doi.org/10.3390/cancers13102469

Kocak B. Key concepts, common pitfalls and best practices in artificial intelligence and machine learning: focus on radiomics. Diagn and Interventional Radiol. 2022;28(5):450–62. DOI: https://doi.org/10.5152/dir.2022.211297

Handelman GS, Asadi H, Chandra RV, Brooks, et al. Peering into the black box of artificial intelligence: evaluation metrics of machine learning methods. American J Roentgenol. 2018;212(1),38–43. DOI: https://doi.org/10.2214/AJR.18.20224

Buono G, Romano G, Galia M, Amato G, Maienza E, Vernuccio F, et al. Difficult laparoscopic cholecystectomy and preoperative predictive factors. Sci Rep. 2021;11(1):2559.

Liu CL. Factors Affecting Conversion of Laparoscopic Cholecystectomy to Open Surgery. Archives of Surg. 1996;31(1):98. DOI: https://doi.org/10.1001/archsurg.1996.01430130100022

Lee NW, Collins J, Britt LD. Evaluation of preoperative risk factors for conversion from laparoscopic to open cholecystectomy. The American Surgeon. 2012;78(8):831–3. DOI: https://doi.org/10.1177/000313481207800815

Di Buono G, Gulotta L, Maienza E. Difficult laparoscopic cholecystectomy and preoperative predictive factors. Scientific Reports. 2021;11(1):56-9. DOI: https://doi.org/10.1038/s41598-021-81938-6

Simopoulos C, Tripsianis G, Botaitis S. Risk factors for conversion from laparoscopic cholecystectomy to open cholecystectomy. Surg Endosc. 2005;19(7):905–9. DOI: https://doi.org/10.1007/s00464-004-2197-0

Mustapha A, Ali K, Mohamed L. An Overview of Gradient Descent Algorithm Optimization in Machine Learning: Application in the Ophthalmology Field. 2020: 349–359. DOI: https://doi.org/10.1007/978-3-030-45183-7_27

Zhou X, Gao Y, Li C, Huang Z. A multiple gradient descent design for multi-task learning on edge computing: Multi-objective machine learning approach. IEEE Transactions on Network Science and Engineering. 2021;9(1):121-33. DOI: https://doi.org/10.1109/TNSE.2021.3067454

Singh K, Ohri A. Laparoscopic cholecystectomy-is there a need to convert? J Minim Access Surg. 2005;1:59–62.

Yetkin G, Uludag M, Citgez B, Akgun I, Karakoc S. Predictive factors for conversion of laparoscopic cholecystectomy in patients with acute cholecystitis. Bratisl Lek Listy. 2009;110:688–91.

Dinkel HP, Kraus S, Heimbucher J, Moll R, Knüpffer J, Gassel HJ, et al. Sonography for selecting candidates for laparoscopic cholecystectomy: A prospective study. AJR Am J Roentgenol. 2000;174:1433–9.

Singh K, Ohri A. Laparoscopic cholecystectomy-is there a need to convert? J Minim Access Surg. 2005;1:59–62. DOI: https://doi.org/10.4103/0972-9941.16528

Yetkin G, Uludag M, Citgez B, Akgun I, Karakoc S. Predictive factors for conversion of laparoscopic cholecystectomy in patients with acute cholecystitis. Bratisl Lek Listy. 2009;110:688–91

Dinkel HP, Kraus S, Heimbucher J, Moll R, Knüpffer J, Gassel HJ, et al. Sonography for selecting candidates for laparoscopic cholecystectomy: A prospective study. AJR Am J Roentgenol. 2000;174:1433–9. DOI: https://doi.org/10.2214/ajr.174.5.1741433

Lal P, Agarwal PN, Malik VK, Chakravarti AL. A difficult laparoscopic cholecystectomy that requires conversion to an open procedure can be predicted using preoperative ultrasonography. JSLS. 2002;6:59–63

Corr P, Tate JJ, Lau WY, Dawson JW, Li AK. Preoperative ultrasonography to predict technical difficulties and complications in laparoscopic cholecystectomy. Am J Surg. 1994;168:54–6. DOI: https://doi.org/10.1016/S0002-9610(05)80071-6

Ramírez-Giraldo C, Isaza-Restrepo A, Conde Monroy D, Castillo-Barbosa AC, Rubio-Avilez JJ, Van-Londoño I. What is the best score for predicting a difficult laparoscopic cholecystectomy? Diagnostic Trial Study. Int J Surg. 2023;109(7):1871-9. DOI: https://doi.org/10.1097/JS9.0000000000000354

Randhawa JS, Pujahari AK. Preoperative prediction of difficult lap chole: A scoring method. Indian J Surg. 2009;71(4):198-201. DOI: https://doi.org/10.1007/s12262-009-0055-y

Naito K, Suda K, Shinoda K, Hashiba T, Sano W, Chiku T, et al. Preoperative difficulty factors in delayed laparoscopic cholecystectomy: Tokyo guidelines 2018 surgical difficulty score Analysis. Asian J Endosc Surg. 2024;17(2):13309. DOI: https://doi.org/10.1111/ases.13309

Teerawiwatchai C, Polprative J, Rattanachueskul K, Thomtong R. Preoperative score development: predicting difficulty in elective laparoscopic cholecystectomy. J Health Sci Med Res. 2023;29;2023994. DOI: https://doi.org/10.31584/jhsmr.2023994

Serrano-González R, Rivero Y, Hernandez-Velasquez A, Rodriguez-Rugel T. Predicting difficulty in laparoscopic cholecystectomies: an evaluation of the labbad-vivas scores and its correlation with the parkland grading scale. Cureus. 2024;16(3):56. DOI: https://doi.org/10.7759/cureus.56185

Vivek MA, Augustine AJ, Rao R. A comprehensive predictive scoring method for difficult laparoscopic cholecystectomy. Journal of Min Acc Surg. 2014;10(2):62-7. DOI: https://doi.org/10.4103/0972-9941.129947

Chhaparia S, Dewangan KP, Rao Geddam S.: Prediction of difficult laparoscopic cholecystectomy based on preoperative ultrasonography assessment. Int Surg J. 2023;27;11(1):75–87. DOI: https://doi.org/10.18203/2349-2902.isj20233926

Islam M, Korayem, Samer S, Bessa E. Preoperative predictors of difficult early laparoscopic cholecystectomy in Egyptian patients with acute calculous cholecystitis BMC Surgery.2024;24(1):78. DOI: https://doi.org/10.1186/s12893-024-02532-x

Ramakrishna UN, Potnuri R, Sahu RK, Chavda H. A prospective study of various preoperative factors and the development of a scoring system for predicting difficult laparoscopic cholecystectomy. Asian J Med Sci. 2024;15(6):130–5. DOI: https://doi.org/10.71152/ajms.v15i6.1891

Abbing Julian R, Voskens FJ, Gerats BGA, Egging RM, Milletari F, Broeders IAMJ. AI-based assessment model of surgical difficulty during early phase laparoscopic cholecystectomy. Comput Methods Biomech Biomed Eng Imaging Vis. 2023;11(4):1299–306. DOI: https://doi.org/10.1080/21681163.2022.2163296

Downloads

Published

2025-03-26

How to Cite

Kapoor, A., Sidhu, B. S., & Singh, J. (2025). Artificial intelligence-based detection of pre-operative surgical difficulty in laparoscopic cholecystectomy patients using gradient based model . International Surgery Journal, 12(4), 555–561. https://doi.org/10.18203/2349-2902.isj20250814

Issue

Section

Original Research Articles