Bayesian process mapping for intraoperative decision making in laparoscopic cholecystectomy

Abstract

Aim: Surgeon’s intraoperative decisions significantly impact patient outcomes. In the reconciliation cycle, interoperative decisions are guided by probabilistic reasoning, which is informed by the evolving intraoperative features. This paper aims to compare the utility of a traditional logistic regression (LR) model for critical view of safety (CVS) achievement to Bayesian network (BN) maps using intraoperative features. It hypothesizes that BN mapping better integrates with surgeon heuristics.

Methods: Using prospectively gathered intraoperative data, BN maps were developed and tested to determine their ability to predict critical view of safety achievement. Performance was compared to traditional logistic regression models to consider their utility in practice.

Results: In total, 4,663 patients were identified. Of these patients, 2,837 (61%) presented acutely and 3,122 (67%) were female. CVS was achieved in 4,131 (92%) of patients. In total, four BN were developed. Optimal performance was seen in model 2 with an AUC of 0.879 (0.798-0.960) (P < 0.001). Selecting a cut-off of 0.6 gave an optimized sensitivity of 99% and a specificity of 45% for CVS achievement. In comparison to this, for the combined acute LR model, ROC curve analysis gave an AUC of 0.829 (0.787-0.872 ) (P < 0.001). A cut-off of 75% probability resulted in a sensitivity of 95% and a specificity of 38% for CVS achievement.

Conclusion: The present study illustrates how BN modeling can map to surgeon decision making to facilitate reasoning in complex environments. Further work is needed to facilitate data capture and implementation. Despite this, they represent a promising avenue for intuitive decision support tools.

Keywords

Operative process / laparoscopic cholecystectomy / artificial intelligence / Bayesian networks

References

[1] Cristancho SM,Vanstone M.Thinking like an expert: surgical decision making as a cyclical process of being aware.Am J Surg2016;211:64-9 PMCID:PMC5578749

[2] Onoe S,Takayama Y,Kaneoka Y.A preoperative predictive scoring system to predict the ability to achieve the critical view of safety during laparoscopic cholecystectomy for acute cholecystitis.HPB2017;19:406-10

[3] Kyrimi E,Dube K,Fahmi A.A comprehensive scoping review of Bayesian networks in healthcare: past, present and future.Artif Intell Med2021;117:102108

[4] Cai ZQ,Si SB,Chen C.Analysis of prognostic factors for survival after surgery for gallbladder cancer based on a Bayesian network.Sci Rep2017;7:293 PMCID:PMC5428511

[5] Bradley A,Hwei NG.A predictive Bayesian network that risk stratifies patients undergoing Barrett’s surveillance for personalized risk of developing malignancy.PLoS One2020;15:e0240620 PMCID:PMC7549831

[6] Ivens GP.Chemical process dynamics: By Rezsö Mohilla and Béla Ferencz; published by Elsevier, Amsterdam, 1982; 300 pp.; price, Dfl. 150.Chem Eng J1983;27:120-1

[7] McLachlan S,Hitman GA,Kyrimi E.Bayesian networks in healthcare: distribution by medical condition.Artif Intell Med2020;107:101912

[8] Brunt LM, Deziel DJ, Telem DA, et al; Prevention of Bile Duct Injury Consensus Work Group. Safe cholecystectomy multi-society practice guideline and state-of-the-art consensus conference on prevention of bile duct injury during cholecystectomy.Surg Endosc2020;34:2827-55

[9] Wauben LSGL,Goossens RHM,Lange JF.Operative notes do not reflect reality in laparoscopic cholecystectomy.Br J Surg2011;98:1431-6

[10] Sebastian M,Rudnicki J.Recommendation for photographic documentation of safe laparoscopic cholecystectomy.World J Surg2021;45:81-7 PMCID:PMC7752874

[11] Nijssen MA,Meyer Z,Crolla RM.Complications after laparoscopic cholecystectomy: a video evaluation study of whether the critical view of safety was reached.World J Surg2015;39:1798-803

[12] Sakowska MM,Connor S.Hospital-wide implementation of an electronic-workflow solution aiming to make surgical practice improvement easy.ANZ J Surg2017;87:143-8

[13] Nassar AHM,Ng HJ.CholeS Study GroupWest Midlands Research CollaborativePredicting the difficult laparoscopic cholecystectomy: development and validation of a pre-operative risk score using an objective operative difficulty grading system.Surg Endosc2020;34:4549-61

[14] Wennmacker SZ,van Dijk AH,de Reuver PR.Predicting operative difficulty of laparoscopic cholecystectomy in patients with acute biliary presentations.ANZ J Surg2019;89:1451-6 PMCID:PMC6899702

[15] Madni TD,Imran JB.A comparison of cholecystitis grading scales.J Trauma Acute Care Surg2019;86:471-8

[16] Fenton N.Risk assessment and decision analysis with bayesian networks. 2nd ed. New York: Chapman and Hall/CRC. 2018.

[17] Kyrimi E,McLachlan S,Marsh W.Medical idioms for clinical Bayesian network development.J Biomed Inform2020;108:103495

[18] Nassar AHM,Wysocki AP,Gil IC.Achieving the critical view of safety in the difficult laparoscopic cholecystectomy: a prospective study of predictors of failure.Surg Endosc2021;35:6039-47 PMCID:PMC8523408

[19] Fawcett T.An introduction to ROC analysis.Pattern Recognit Lett2006;27:861-74

[20] Kass RE.Bayes factors.J Am Stat Assoc1995;90:773-95

[21] Tranter-Entwistle I,Hugh TJ.The artery first technique: re-examining the critical view of safety during laparoscopic cholecystectomy.Surg Endosc2023;37:4458-65

[22] Tranter-Entwistle I,Hugh TJ.Use of prospective video analysis to understand the impact of technical difficulty on operative process during laparoscopic cholecystectomy.HPB2022;24:2096-103

[23] Mascagni P,Urade T.Intraoperative time-out to promote the implementation of the critical view of safety in laparoscopic cholecystectomy: a video-based assessment of 343 procedures.J Am Coll Surg2021;233:497-505

[24] Tranter-Entwistle I,Eglinton T.A prospective cohort study of operative outcomes in laparoscopic cholecystectomy using operative difficulty grade-adjusted CUSUM analysis.Br J Surg2023;10:1068-71 PMCID:PMC10416680

[25] Cao Y,Szabo E,Näslund I.Using bayesian networks to predict long-term health-related quality of life and comorbidity after bariatric surgery: a study based on the scandinavian obesity surgery registry.J Clin Med2020;9:1895 PMCID:PMC7356516

[26] Hashimoto DA,Jones CB.Surgical procedural map scoring for decision-making in laparoscopic cholecystectomy.Am J Surg2019;217:356-61 PMCID:PMC6581213

[27] Korovin LN,Hsu CH,Ghaderi I.Surgeons’ expertise during critical event in laparoscopic cholecystectomy: an expert-novice comparison using protocol analysis.Am J Surg2020;219:340-5