Clinical outcomes, learning effectiveness, and patient-safety implications of AI-assisted HPB surgery for trainees: a systematic review and multiple meta-analyses

Abstract

Introduction: Artificial intelligence (AI) applications are increasingly integrated into hepato-pancreato-biliary (HPB) surgery training, yet their impact on educational outcomes and patient safety remains unclear. This systematic review and meta-analysis evaluate clinical outcomes, learning effectiveness, and safety implications of AI-assisted HPB surgery among surgical trainees.

Methods: A comprehensive search of six databases (PubMed, Cochrane CENTRAL, Embase, Web of Science, Scopus, and Semantic Scholar) was performed through May 2025. Studies involving surgical trainees utilizing AI-based platforms with measurable clinical, educational, or safety outcomes were included. Data extraction and risk-of-bias assessments were independently conducted (κ = 0.86-0.91). Random-effects models were applied to four outcomes: operative time, complications, learning curve metrics, and skill assessment accuracy. Subgroup and sensitivity analyses addressed heterogeneity, stratifying by procedure type and AI modality.

Results: Of 4,687 screened records, 80 studies (3,847 trainees) met inclusion criteria. Four separate meta-analyses revealed: (1) operative time reduction of 32.5 min (MD -32.5, 95% CI: -45.2 to -19.8; I² = 65%; 15 studies, 1,234 procedures); (2) decreased complications (RR 0.72, 95% CI: 0.58-0.89; I² = 42%; 18 studies, 2,156 patients); (3) accelerated learning with 2.3 fewer cases to proficiency (SMD -2.3, 95% CI: -2.8 to -1.8; I² = 55%; 10 studies, 423 trainees); and (4) AI skill assessment accuracy of 85.4% (95% CI: 81.2%-89.6%; I² = 78%; 12 studies, 847 assessments). Stratified analysis by AI technology type revealed differential impacts: computer vision systems achieved largest operative time reductions (-41.2 min, 95% CI: -54.3 to -28.1), augmented reality showed -38.7 min (95% CI: -49.8 to -27.6), while machine learning demonstrated -24.3 min (95% CI: -32.1 to -16.5); test for subgroup differences P = 0.02. Subgroup analysis showed greater benefits for complex procedures (pancreaticoduodenectomy: -48.3 min) versus simple procedures (cholecystectomy: -18.4 min, P = 0.003). Complications showed similar procedure-specific patterns, with pancreaticoduodenectomy achieving RR 0.65 versus cholecystectomy RR 0.78. Critical View of Safety achievement improved from 11% to 78% (RR 2.84, 95% CI: 2.12-3.81). Publication bias was not detected (Egger’s test P > 0.05 for all outcomes).

Discussion: AI-assisted HPB surgical training improves operative efficiency, reduces complications, enhances learning curves, and enables accurate skill assessment. These findings support systematic AI integration with standardized protocols and multicenter validation.

Keywords

Artificial intelligence / machine learning / hepato-pancreato-biliary surgery / surgical education / patient safety / systematic review / meta-analysis / robotic surgery / learning curve

References

[1] Cameron JL.Two thousand consecutive pancreaticoduodenectomies.J Am Coll Surg2015;220:530-6

[2] Vollmer CM Jr,Gondek S.Pancreatic Surgery Mortality Study GroupA root-cause analysis of mortality following major pancreatectomy.J Gastrointest Surg2012;16:89-102; discussion 102

[3] Sachdeva AK,Brigham TP.American College of Surgeons (ACS) Division of EducationAccreditation Council for Graduate Medical Education (ACGME)Interventions to address challenges associated with the transition from residency training to independent surgical practice.Surgery2014;155:867-82

[4] Hashimoto DA,Rus D.Artificial intelligence in surgery: promises and perils.Ann Surg2018;268:70-6

[5] Maier-Hein L,Speidel S.Surgical data science for next-generation interventions.Nat Biomed Eng2017;1:691-6

[6] Ward TM,Ban Y.Automated operative phase identification in peroral endoscopic myotomy.Surg Endosc2021;35:4008-15 PMCID:PMC7854950

[7] Topol EJ.High-performance medicine: the convergence of human and artificial intelligence.Nat Med2019;25:44-56

[8] Madani A, Namazi B, Altieri MS, et al. Artificial intelligence for intraoperative guidance: using semantic segmentation to identify surgical anatomy during laparoscopic cholecystectomy. Ann Surg. 2022;276:363-9. [Methods, pp. 364-5].

[9] Mascagni P,Urade T.A computer vision platform to automatically locate critical events in surgical videos: documenting safety in laparoscopic cholecystectomy.Ann Surg2021;274:e93-5

[10] Birkmeyer JD,O'Reilly A.Michigan Bariatric Surgery CollaborativeSurgical skill and complication rates after bariatric surgery.N Engl J Med2013;369:1434-42

[11] Bektaş M,Marquering HA.Machine learning algorithms for predicting surgical outcomes after colorectal surgery: a systematic review.World J Surg2022;46:3100-10

[12] Lavanchy JL,Kirtac K.Surgical skill assessment using machine learning algorithms.Br J Surg2021;108:znab202.093

[13] Madani A, Namazi B, Altieri MS, et al. Artificial intelligence for intraoperative guidance: using semantic segmentation to identify surgical anatomy during laparoscopic cholecystectomy. Ann Surg. 2022;276:363-9. [Results, pp. 366-7].

[14] Endo Y,Mori Y.Impact of AI system on recognition for anatomical landmarks related to reducing bile duct injury during laparoscopic cholecystectomy.Surg Endosc2023;37:5752-9 PMCID:PMC10322759

[15] Hogg ME,Zenati M.Mastery-based virtual reality robotic simulation curriculum: the first step toward operative robotic proficiency.J Surg Educ2017;74:477-85

[16] Rashidian N, Giglio MC, Van Herzeele I, et al. Effectiveness of an immersive virtual reality environment on curricular training for complex cognitive skills in liver surgery: a multicentric crossover randomized trial. HPB. 2022;24:2086-95. [Methods, pp. 2087-9].

[17] Nota CL,Te Riele WW,Hagendoorn J.Stepwise implementation of robotic surgery in a high volume HPB practice in the Netherlands.HPB2020;22:1596-603

[18] Zwart MJW, van den Broek B, de Graaf N, et al; Dutch Pancreatic Cancer Group. The feasibility, proficiency, and mastery learning curves in 635 robotic pancreatoduodenectomies following a multicenter training program: "standing on the shoulders of giants". Ann Surg. 2023;278:e1232-41. [Methods, pp. e1233-5]. PMCID:PMC10631507

[19] Brian R,Gomes C.Artificial intelligence and robotic surgical education.Glob Surg Educ2024;3:12

[20] Lavanchy JL,Kirtac K.Automation of surgical skill assessment using a three-stage machine learning algorithm.Sci Rep2021;11:5197 PMCID:PMC7933408

[21] Ahmad J.Training in robotic Hepatobiliary and pancreatic surgery: a step up approach.HPB2022;24:806-8

[22] Fukumori D,Penninga L,Svendsen LB.Learning curves in robot-assisted minimally invasive liver surgery at a high-volume center in Denmark: report of the first 100 patients and review of literature.Scand J Surg2023;112:164-72

[23] Kawka M,Hand F.The influence of procedural volume on short-term outcomes for robotic pancreatoduodenectomy - a cohort study and a learning curve analysis.Surg Endosc2023;37:4719-27 PMCID:PMC10234850

[24] Primavesi F,Bartsch C.Implementing MIS HPB surgery including the first robotic hepatobiliary program in Austria: initial experience and outcomes after 85 cases.HPB2023;25:S554-5

[25] Fuentes SMS,López EMM. The impact of artificial intelligence in general surgery: enhancing precision, efficiency, and outcomes. Int J Res Med Sci. 2024;12:112-9. Available from: https://www.msjonline.org/index.php/ijrms/article/view/14394 [accessed 30 July 2025]

[26] Davis J,Tschuor C.A novel application of cumulative sum (CuSUM) analytics for the objective evaluation of procedure specific technical dexterity in robotic hepatopancreatobiliary surgery.HPB2022;24:S24-5

[27] Kirubarajan A,Khan S,Sobel M.Artificial intelligence and surgical education: a systematic scoping review of interventions.J Surg Educ2022;79:500-15

[28] McGivern KG,Knight SR.Applying artificial intelligence to big data in hepatopancreatic and biliary surgery: a scoping review.Artif Intell Surg2023;3:98-112

[29] Ward TM,Ban Y,Meireles OR.Challenges in surgical video annotation.Comput Assist Surg2021;26:58-68

[30] Jung JJ,Lebovic G.First-year analysis of the operating room black box study.Ann Surg2020;271:122-7

[31] Collins JW,Ghazi A.Ethical implications of AI in robotic surgical training: a Delphi consensus statement.Eur Urol Focus2022;8:613-22

[32] Gordon L,Rudzicz F.Explainable artificial intelligence for safe intraoperative decision support.JAMA Surg2019;154:1064-5

[33] Page MJ,Bossuyt PM.The PRISMA 2020 statement: an updated guideline for reporting systematic reviews.BMJ2021;372:n71 PMCID:PMC8005924

[34] Stroup DF,Morton SC.Meta-analysis of observational studies in epidemiology: a proposal for reporting. Meta-analysis Of Observational Studies in Epidemiology (MOOSE) group.JAMA2000;283:2008-12

[35] Ouzzani M,Fedorowicz Z.Rayyan-a web and mobile app for systematic reviews.Syst Rev2016;5:210 PMCID:PMC5139140

[36] Sterne JAC,Page MJ.RoB 2: a revised tool for assessing risk of bias in randomised trials.BMJ2019;366:l4898

[37] Sterne JA,Reeves BC.ROBINS-I: a tool for assessing risk of bias in non-randomised studies of interventions.BMJ2016;355:i4919 PMCID:PMC5062054

[38] Shea BJ,Wells G.AMSTAR 2: a critical appraisal tool for systematic reviews that include randomised or non-randomised studies of healthcare interventions, or both.BMJ2017;358:j4008 PMCID:PMC5833365

[39] Wells GA,O’Connell D. The Newcastle-Ottawa Scale (NOS) for assessing the quality of nonrandomised studies in meta-analyses. Ottawa Hospital Research Institute. 2021. Available from: http://www.ohri.ca/programs/clinical_epidemiology/oxford.asp [accessed 30 July 2025].

[40] Wolff RF,Riley RD.PROBAST Group†PROBAST: a tool to assess the risk of bias and applicability of prediction model studies.Ann Intern Med2019;170:51-8

[41] Campbell M,Sowden A.Synthesis without meta-analysis (SWiM) in systematic reviews: reporting guideline.BMJ2020;368:l6890 PMCID:PMC7190266

[42] Guyatt GH,Vist GE.GRADE Working GroupGRADE: an emerging consensus on rating quality of evidence and strength of recommendations.BMJ2008;336:924-6

[43] Winkler-Schwartz A,Mirchi N.Machine learning identification of surgical and operative factors associated with surgical expertise in virtual reality simulation.JAMA Netw Open2019;2:e198363

[44] Back E,Holmgren K.Permanent stoma rates after anterior resection for rectal cancer: risk prediction scoring using preoperative variables.Br J Surg2021;108:1388-95 PMCID:PMC10364873

[45] Yu F,Kim TS.Assessment of automated identification of phases in videos of cataract surgery using machine learning and deep learning techniques.JAMA Netw Open2019;2:e191860 PMCID:PMC6450320

[46] Goodman ED,Zhang Y.Analyzing surgical technique in diverse open surgical videos with multitask machine learning.JAMA Surg2024;159:185-92 PMCID:PMC10701669

[47] Panteleimonitis S,Bissett-Amess R.EARCS CollaborativeShort-term clinical outcomes of a European training programme for robotic colorectal surgery.Surg Endosc2021;35:6796-806 PMCID:PMC8599412

[48] Wu S,Liu J.Impact of an AI-based laparoscopic cholecystectomy coaching program on the surgical performance: a randomized controlled trial.Int J Surg2024;110:7816-23 PMCID:PMC11634122

[49] Leifman G,Rivlin E,Assalia A.Real-time artificial intelligence validation of critical view of safety in laparoscopic cholecystectomy.Intell Based Med2024;4:45-53

[50] Mascagni P,Alapatt D.Artificial intelligence for surgical safety: automatic assessment of the critical view of safety in laparoscopic cholecystectomy using deep learning.Ann Surg2022;275:955-61

[51] Korndorffer JR Jr,Spain DA.Situating artificial intelligence in surgery: a focus on disease severity.Ann Surg2020;272:523-8

[52] Rashidian N, Giglio MC, Van Herzeele I, et al. Effectiveness of an immersive virtual reality environment on curricular training for complex cognitive skills in liver surgery: a multicentric crossover randomized trial. HPB. 2022;24:2086-95. [Results, pp. 2090-2].

[53] Tashiro Y,Kobayashi N.A novel image-guided laparoscopic liver resection with integrated fluorescent imaging and artificial intelligence: a preliminary study.J Clin Oncol2024;42:568

[54] Wang H,Hu P. Application effect of mixed reality in the teaching of hepatobiliary surgery. Chin J Med Educ Res. 2019;41:1230-4. Available from: https://scholar.google.com/scholar?hl=zh-CN&as_sdt=0%2C48&q=Application+effect+of+mixed+reality+in+the+teaching+of+hepatobiliary+surgery&btnG=#d=gs_qabs&t=1753759007709&u=%23p%3Dn0vBcU2TMMoJ [accessed 30 July 2025].

[55] Javaheri H,Widyaningsih R.Enhancing perioperative outcomes of pancreatic surgery with wearable augmented reality assistance system: a matched-pair analysis.Ann Surg Open2024;5:e516

[56] Zhu W,Hu H.Perioperative and disease-free survival outcomes after hepatectomy for centrally located hepatocellular carcinoma guided by augmented reality and indocyanine green fluorescence imaging: a single-center experience.J Am Coll Surg2023;236:328-37

[57] Magistri P,Ballarin R,Tarantino G.Improving outcomes defending patient safety: the learning journey in robotic liver resections.Biomed Res Int2019;2019:1835085 PMCID:PMC6476155

[58] Onoe S,Watanabe N.Utility of modified pancreaticoduodenectomy (Hi-cut PD) for middle-third cholangiocarcinoma: an alternative to hepatopancreaticoduodenectomy.HPB2024;26:530-40

[59] Sunakawa T,Kobayashi S.Deep learning-based automatic bleeding recognition during liver resection in laparoscopic hepatectomy.Surg Endosc2024;38:7656-62

[60] Twinanda AP,Mutter D,de Mathelin M.EndoNet: a deep architecture for recognition tasks on laparoscopic videos.IEEE Trans Med Imaging2017;36:86-97

[61] Ward TM,Madani A,Perretta S.Surgical data science and artificial intelligence for surgical education. J Surg Oncol. 2021;124:221-30.

[62] Kennedy-Metz LR,Torralba A.Computer vision in the operating room: opportunities and caveats.IEEE Trans Med Robot Bionics2021;3:2-10 PMCID:PMC7908934

[63] Khalid S,Grantcharov T,Rudzicz F.Evaluation of deep learning models for identifying surgical actions and measuring performance.JAMA Netw Open2020;3:e201664 PMCID:PMC12124734

[64] Hung AJ,Gill IS.Automated performance metrics and machine learning algorithms to measure surgeon performance and anticipate clinical outcomes in robotic surgery.JAMA Surg2018;153:770-1 PMCID:PMC9084629

[65] Wagner M,Kenngott HG.A learning robot for cognitive camera control in minimally invasive surgery.Surg Endosc2021;35:5365-74 PMCID:PMC8346448

[66] Birkhoff DC,Schijven MP.A review on the current applications of artificial intelligence in the operating room.Surg Innov2021;28:611-9 PMCID:PMC8450995

[67] Kassahun Y,Tibebu AT.Surgical robotics beyond enhanced dexterity instrumentation: a survey of machine learning techniques and their role in intelligent and autonomous surgical actions.Int J Comput Assist Radiol Surg2016;11:553-68

[68] Datta S,Ruppert MM.Reinforcement learning in surgery.Surgery2021;170:329-32 PMCID:PMC8217129

[69] Luongo F,Nguyen JH,Hung AJ.Deep learning-based computer vision to recognize and classify suturing gestures in robot-assisted surgery.Surgery2021;169:1240-4 PMCID:PMC7994208

[70] Mellia JA,Toyoda Y.Natural language processing in surgery: a systematic review and meta-analysis.Ann Surg2021;273:900-8

[71] Zwart MJW, van den Broek B, de Graaf N, et al; Dutch Pancreatic Cancer Group. The feasibility, proficiency, and mastery learning curves in 635 robotic pancreatoduodenectomies following a multicenter training program: "standing on the shoulders of giants". Ann Surg. 2023;278:e1232-41. [Results, pp. e1236-9]. PMCID:PMC10631507

[72] Hashimoto DA,Witkowski ER.Computer vision analysis of intraoperative video: automated recognition of operative steps in laparoscopic sleeve gastrectomy.Ann Surg2019;270:414-21 PMCID:PMC7216040

[73] Macario A.What does one minute of operating room time cost?.J Clin Anesth2010;22:233-6

[74] Procter LD,Bernard AC.General surgical operative duration is associated with increased risk-adjusted infectious complication rates and length of hospital stay.J Am Coll Surg2010;210:60-5.e1

[75] Birkmeyer JD,Siewers AE,Wennberg DE.Surgeon volume and operative mortality in the United States.N Engl J Med2003;349:2117-27

[76] Way LW,Gantert W.Causes and prevention of laparoscopic bile duct injuries: analysis of 252 cases from a human factors and cognitive psychology perspective.Ann Surg2003;237:460-9

[77] Flum DR,Cheadle A,Koepsell T.Intraoperative cholangiography and risk of common bile duct injury during cholecystectomy.JAMA2003;289:1639-44

[78] Gao X,Dou Q. Automatic gesture recognition in robot-assisted surgery with reinforcement learning and tree search. In Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA); 2020 May 31-Aug 31; Paris, France. New York: IEEE; 2020. pp. 8440-6.

[79] Schmidt RA,Winstein C,Zelaznik HN. Motor control and learning: a behavioral emphasis. 5th ed. Champaign, IL: Human Kinetics; 2011.

[80] Martin JA,Reznick R.Objective structured assessment of technical skill (OSATS) for surgical residents.Br J Surg1997;84:273-8

[81] Vassiliou MC,Andrew CG.A global assessment tool for evaluation of intraoperative laparoscopic skills.Am J Surg2005;190:107-13

[82] Stahl CC,Rosser AA.Natural language processing and entrustable professional activity text feedback in surgery: a machine learning model of resident autonomy. Am J Surg. 2021;221:369-75. PMCID:PMC7969407

[83] Bartek MA,Solomon S.Improving operating room efficiency: machine learning approach to predict case-time duration.J Am Coll Surg2019;229:346-54.e3 PMCID:PMC7077507

[84] Schlemper J,Schaap M.Attention gated networks: learning to leverage salient regions in medical images.Med Image Anal2019;53:197-207 PMCID:PMC7610718

[85] Ericsson KA.Deliberate practice and the acquisition and maintenance of expert performance in medicine and related domains.Acad Med2004;79:S70-81

[86] Moglia A,Morelli L,Mosca F.A systematic review of virtual reality simulators for robot-assisted surgery.Eur Urol2016;69:1065-80

[87] Vedula SS,Hager GD.Objective assessment of surgical technical skill and competency in the operating room.Annu Rev Biomed Eng2017;19:301-25 PMCID:PMC5555216

[88] Frank JR,Cate OT.Competency-based medical education: theory to practice.Med Teach2010;32:638-45

[89] Childers CP.Understanding costs of care in the operating room.JAMA Surg2018;153:e176233 PMCID:PMC5875376

[90] Spanjersberg WR,Keus F.Fast track surgery versus conventional recovery strategies for colorectal surgery.Cochrane Database Syst Rev2011:CD007635

[91] Stefanidis D,Paige J.Association for Surgical Education Simulation CommitteeSimulation in surgery: what’s needed next?.Ann Surg2015;261:846-53

[92] Strasberg SM.A three-step conceptual roadmap for avoiding bile duct injury in laparoscopic cholecystectomy: an invited perspective review.J Hepatobiliary Pancreat Sci2019;26:123-7

[93] Pucher PH,Qurashi M.Meta-analysis of the effect of postoperative in-hospital morbidity on long-term patient survival.Br J Surg2014;101:1499-508

[94] Winkler-Schwartz A,Mirchi N.Artificial intelligence in medical education: best practices using machine learning to assess surgical expertise in virtual reality simulation.J Surg Educ2019;76:1681-90

[95] Lam K,Wang Z.Machine learning for technical skill assessment in surgery: a systematic review.NPJ Digit Med2022;5:24 PMCID:PMC8894462

[96] Park A,Seagull FJ,Dexter D.Patients benefit while surgeons suffer: an impending epidemic.J Am Coll Surg2010;210:306-13

[97] Fitts PM. Human performance. Belmont, CA: Brooks/Cole; 1967.

[98] Cate O. Competency-based postgraduate medical education: past, present and future.GMS J Med Educ2017;34:Doc69 PMCID:PMC5704607

[99] Bilgic E,Watanabe Y.Effectiveness of telementoring in surgery compared with on-site mentoring: a systematic review.Surg Innov2017;24:379-85

[100] Stewart LA,Rovers M.PRISMA-IPD Development GroupPreferred reporting items for systematic review and meta-analyses of individual participant data: the PRISMA-IPD statement.JAMA2015;313:1657-65

[101] Kirkham JJ,Altman DG.Core outcome set-STAndards for development: the COS-STAD recommendations.PLoS Med2017;14:e1002447 PMCID:PMC5689835

[102] Barkun JS,Feldman LS.Balliol CollaborationEvaluation and stages of surgical innovations.Lancet2009;374:1089-96

[103] Peters DH,Alonge O,Tran N.Implementation research: what it is and how to do it.BMJ347:f6753

[104] Husereau D,Petrou S.CHEERS Task ForceConsolidated Health Economic Evaluation Reporting Standards (CHEERS) statement.BMJ2013;346:f1049

[105] Li T,Talwalkar A.Federated learning: challenges, methods, and future directions.IEEE Signal Process Mag2020;37:50-60

[106] Holzinger A,Denk H,Müller H.Causability and explainability of artificial intelligence in medicine.Wiley Interdiscip Rev Data Min Knowl Discov2019;9:e1312 PMCID:PMC7017860

[107] Tao F,Liu A.Digital twin in industry: state-of-the-art.IEEE Trans Ind Inf2019;15:2405-15

[108] Arute F,Babbush R.Quantum supremacy using a programmable superconducting processor.Nature2019;574:505-10

[109] Haddaway NR,Pritchard CC.PRISMA2020: An R package and Shiny app for producing PRISMA 2020-compliant flow diagrams, with interactivity for optimised digital transparency and open synthesis.Campbell Syst Rev2022;18:e1230 PMCID:PMC8958186