SpringerLink
Log in

Artificial intelligence prediction of cholecystectomy operative course from automated identification of gallbladder inflammation

  • 2021 SAGES Oral
  • Published:
Surgical Endoscopy Aims and scope Submit manuscript

Abstract

Background

Operative courses of laparoscopic cholecystectomies vary widely due to differing pathologies. Efforts to assess intra-operative difficulty include the Parkland grading scale (PGS), which scores inflammation from the initial view of the gallbladder on a 1–5 scale. We investigated the impact of PGS on intra-operative outcomes, including laparoscopic duration, attainment of the critical view of safety (CVS), and gallbladder injury. We additionally trained an artificial intelligence (AI) model to identify PGS.

Methods

One surgeon labeled surgical phases, PGS, CVS attainment, and gallbladder injury in 200 cholecystectomy videos. We used multilevel Bayesian regression models to analyze the PGS’s effect on intra-operative outcomes. We trained AI models to identify PGS from an initial view of the gallbladder and compared model performance to annotations by a second surgeon.

Results

Slightly inflamed gallbladders (PGS-2) minimally increased duration, adding 2.7 [95% compatibility interval (CI) 0.3–7.0] minutes to an operation. This contrasted with maximally inflamed gallbladders (PGS-5), where on average 16.9 (95% CI 4.4–33.9) minutes were added, with 31.3 (95% CI 8.0–67.5) minutes added for the most affected surgeon. Inadvertent gallbladder injury occurred in 25% of cases, with a minimal increase in gallbladder injury observed with added inflammation. However, up to a 28% (95% CI − 2, 63) increase in probability of a gallbladder hole during PGS-5 cases was observed for some surgeons. Inflammation had no substantial effect on whether or not a surgeon attained the CVS. An AI model could reliably (Krippendorff’s α = 0.71, 95% CI 0.65–0.77) quantify inflammation when compared to a second surgeon (α = 0.82, 95% CI 0.75–0.87).

Conclusions

An AI model can identify the degree of gallbladder inflammation, which is predictive of cholecystectomy intra-operative course. This automated assessment could be useful for operating room workflow optimization and for targeted per-surgeon and per-resident feedback to accelerate acquisition of operative skills.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Germany)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Sugrue M, Sahebally SM, Ansaloni L, Zielinski MD (2015) Grading operative findings at laparoscopic cholecystectomy—a new scoring system. World J Emerg Surg 10:14. https://doi.org/10.1186/s13017-015-0005-x

    Article  PubMed  PubMed Central  Google Scholar 

  2. Nassar AHM, Ashkar KA, Mohamed AY, Hafiz AA (1995) Is laparoscopic cholecystectomy possible without video technology? Minim Invasive Ther 4:63–65. https://doi.org/10.3109/13645709509152757

    Article  Google Scholar 

  3. Madni TD, Leshikar DE, Minshall CT, Nakonezny PA, Cornelius CC, Imran JB, Clark AT, Williams BH, Eastman AL, Minei JP, Phelan HA, Cripps MW (2018) The Parkland grading scale for Cholecystitis. Am J Surg 215:625–630. https://doi.org/10.1016/j.amjsurg.2017.05.017

    Article  PubMed  Google Scholar 

  4. Sugrue M, Coccolini F, Bucholc M, Johnston A, Manatakis D, Ioannidis O, Bonilauri S, Gachabayov M, Isik A, Ghnnam W, Shelat V, Aremu M, Mohan R, Montori G, Walędziak M, Pisarska M, Kong V, Strzałka M, Fugazzola P, Nita GE, Nardi M, Major P, Negoi I, Allegri A, Konstantoudakis G, Di Carlo I, Massalou D, D’Amico G, Solaini L, Ceresoli M, Bini R, Zielinski M, Tomasoni M, Litvin A, De Simone B, Lostoridis E, Hernandez F, Panyor G, Machain VGM, Pentara I, Baiocchi L, Ng KC, Ansaloni L, Sartelli M, Arellano ML, Savala N, Couse N, McBride S, Contributors from WSES (2019) Intra-operative gallbladder scoring predicts conversion of laparoscopic to open cholecystectomy: a WSES prospective collaborative study. World J Emerg Surg 14:12. https://doi.org/10.1186/s13017-019-0230-9

    Article  PubMed  PubMed Central  Google Scholar 

  5. West Midlands Research Collaborative, Griffiths EA, Hodson J, Vohra RS, Marriott P, Katbeh T, Zino S, Nassar AHM (2019) Utilisation of an operative difficulty grading scale for laparoscopic cholecystectomy. Surg Endosc 33:110–121. https://doi.org/10.1007/s00464-018-6281-2

    Article  Google Scholar 

  6. Madni TD, Nakonezny PA, Barrios E, Imran JB, Clark AT, Taveras L, Cunningham HB, Christie A, Eastman AL, Minshall CT, Luk S, Minei JP, Phelan HA, Cripps MW (2019) Prospective validation of the Parkland grading scale for Cholecystitis. Am J Surg 217:90–97. https://doi.org/10.1016/j.amjsurg.2018.08.005

    Article  PubMed  Google Scholar 

  7. Stepaniak PS, Heij C, Mannaerts GHH, de Quelerij M, de Vries G (2009) Modeling procedure and surgical times for current procedural terminology-anesthesia-surgeon combinations and evaluation in terms of case-duration prediction and operating room efficiency: a multicenter study. Anesth Analg 109:1232–1245. https://doi.org/10.1213/ANE.0b013e3181b5de07

    Article  PubMed  Google Scholar 

  8. Bellard F (2021) FFmpeg. https://ffmpeg.org/about.html. Accessed 21 Jun 2021

  9. Ban Y, Rosman G, Ward T, Hashimoto D, Kondo T, Iwaki H, Meireles O, Rus D (2021) Aggregating long-term context for learning laparoscopic and robot-assisted surgical workflows. Accessed https://arxiv.org/abs/2009.00681

  10. Strasberg SM, Hertl M, Soper NJ (1995) An analysis of the problem of biliary injury during laparoscopic cholecystectomy. J Am Coll Surg 180:101–125

    CAS  PubMed  Google Scholar 

  11. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)

  12. Howard J, Gugger S (2020) Fastai: a layered API for deep learning. Information 11:108. https://doi.org/10.3390/info11020108

    Article  Google Scholar 

  13. Smith LN (2017) Cyclical learning rates for training neural networks. In: 2017 IEEE winter conference on applications of computer vision (WACV). pp 464–472

  14. Strum DP, May JH, Vargas LG (2000) Modeling the uncertainty of surgical procedure times. Anesthesiology 92:1160–1167. https://doi.org/10.1097/00000542-200004000-00035

    Article  CAS  PubMed  Google Scholar 

  15. R Core Team (2021) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna

    Google Scholar 

  16. McElreath R (2020) Rethinking: statistical rethinking book package. CRC Press, Boca Raton

    Book  Google Scholar 

  17. Gabry J, Češnovar R (2020) cmdstanr: R interface to “CmdStan”

  18. Vehtari A, Gelman A, Simpson D, Carpenter B, Bürkner P-C (2021) Rank-normalization, folding, and localization: an improved Rˆ for assessing convergence of MCMC. Bayesian Anal 1:1–38. https://doi.org/10.1214/20-BA1221

    Article  Google Scholar 

  19. Krippendorff K (2004) Content analysis: an introduction to its methodology, 2nd edn. Sage, Thousand Oaks

    Google Scholar 

  20. Gamer M, Lemon J, Singh IFP (2019) irr: various coefficients of interrater reliability and agreement. CRAN

  21. Wickham H (2016) ggplot2: elegant graphics for data analysis. Springer-Verlag, New York

    Book  Google Scholar 

  22. Kay M (2021) ggdist: visualizations of distributions and uncertainty

  23. Ward TM (2021) tmward/pgs: artificial intelligence prediction of cholecystectomy operative course from automated identification of gallbladder inflammation code. Accessed https://doi.org/10.5281/zenodo.5328655

  24. Levine WC, Dunn PF (2015) Optimizing operating room scheduling. Anesthesiol Clin 33:697–711. https://doi.org/10.1016/j.anclin.2015.07.006

    Article  PubMed  Google Scholar 

  25. Thiels CA, Yu D, Abdelrahman AM, Habermann EB, Hallbeck S, Pasupathy KS, Bingener J (2017) The use of patient factors to improve the prediction of operative duration using laparoscopic cholecystectomy. Surg Endosc 31:333–340. https://doi.org/10.1007/s00464-016-4976-9

    Article  PubMed  Google Scholar 

  26. Ban Y, Rosman G, Ward T, Hashimoto D, Kondo T, Iwaki H, Meireles O, Rus D (2021) SUrgical PRediction GAN for events anticipation. Accessed https://arxiv.org/abs/2105.04642

  27. Twinanda AP, Yengera G, Mutter D, Marescaux J, Padoy N (2019) RSDNet: learning to predict remaining surgery duration from laparoscopic videos without manual annotations. IEEE Trans Med Imaging 38:1069–1078. https://doi.org/10.1109/TMI.2018.2878055

    Article  PubMed  Google Scholar 

  28. The Prevention of Bile Duct Injury Consensus Work Group, Michael Brunt L, Deziel DJ, Telem DA, Strasberg SM, Aggarwal R, Asbun H, Bonjer J, McDonald M, Alseidi A, Ujiki M, Riall TS, Hammill C, Moulton C-A, Pucher PH, Parks RW, Ansari MT, Connor S, Dirks RC, Anderson B, Altieri MS, Tsamalaidze L, Stefanidis D (2020) Safe cholecystectomy multi-society practice guideline and state-of-the-art consensus conference on prevention of bile duct injury during cholecystectomy. Surg Endosc 34:2827–2855. https://doi.org/10.1007/s00464-020-07568-7

    Article  Google Scholar 

  29. Ward TM, Mascagni P, Madani A, Padoy N, Perretta S, Hashimoto DA (2021) Surgical data science and artificial intelligence for surgical education. J Surg Oncol 124:221–230. https://doi.org/10.1002/jso.26496

    Article  PubMed  Google Scholar 

  30. Twinanda AP, Shehata S, Mutter D, Marescaux J, de Mathelin M, Padoy N (2017) EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans Med Imaging 36:86–97. https://doi.org/10.1109/TMI.2016.2593957

    Article  PubMed  Google Scholar 

  31. Mascagni P, Vardazaryan A, Alapatt D, Urade T, Emre T, Fiorillo C, Pessaux P, Mutter D, Marescaux J, Costamagna G, Dallemagne B, Padoy N (2021) Artificial Intelligence for Surgical Safety: Automatic Assessment of the Critical View of Safety in Laparoscopic Cholecystectomy Using Deep Learning. Ann Surg. https://doi.org/10.1097/SLA.0000000000004351

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

This work was supported by a 2018 research award from the Risk Management Foundation of the Harvard Medical Institutions Incorporated (CRICO/RMF), grant number 233456. The authors thank Caitlin E. Stafford, CCRP, for her assistance and support in research management, and Allison J. Navarrete-Welton, for her assistance in data collection.

Funding

This study was funded by the Risk Management Foundation of the Harvard Medical Institutions Incorporated (CRICO/RMF), Grant Number 233456.

Author information

Authors and Affiliations

  1. Surgical Artificial Intelligence and Innovation Laboratory, Department of Surgery, Massachusetts General Hospital, 15 Parkman St., WAC 460, Boston, MA, 02114, USA

    Thomas M. Ward, Daniel A. Hashimoto, Yutong Ban, Guy Rosman & Ozanan R. Meireles

  2. Distributed Robotics Laboratory, Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA

    Yutong Ban & Guy Rosman

Authors
  1. Thomas M. Ward
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Daniel A. Hashimoto
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yutong Ban
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guy Rosman
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ozanan R. Meireles
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Thomas M. Ward.

Ethics declarations

Disclosures

Drs. Ban, Hashimoto, Meireles, Rosman, and Ward receive research support from Olympus Corporation. Drs. Ban, Hashimoto, Meireles, Rosman, and Ward have received research support from the Risk Management Foundation of the Harvard Medical Institutions Incorporated (CRICO/RMF). Dr. Hashimoto is a consultant for Johnson & Johnson, Activ Surgical, and Verily Life Sciences. Dr. Hashimoto has received research support from the Intuitive Foundation and the Society of American Gastrointestinal and Endoscopic Surgeons. Dr. Rosman receives research support from Toyota Research Institute (TRI). Dr. Meireles is a consultant for Medtronic and Olympus Corporation.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 29 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ward, T.M., Hashimoto, D.A., Ban, Y. et al. Artificial intelligence prediction of cholecystectomy operative course from automated identification of gallbladder inflammation. Surg Endosc 36, 6832–6840 (2022). https://doi.org/10.1007/s00464-022-09009-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00464-022-09009-z

Keywords

Search

Navigation