Artificial intelligence in hepatopancreaticobiliary surgery: a systematic review

Abstract

Aim: The aim of this systematic review was to provide an overview of Machine Learning applications within hepatopancreaticobiliary surgery. The secondary aim was to evaluate the predictive performances of applied Machine Learning models.

Methods: A systematic search was conducted in PubMed, EMBASE, Cochrane, and Web of Science. Studies were only eligible for inclusion when they described Machine Learning in hepatopancreaticobiliary surgery. The Cochrane and PROBAST risk of bias tools were used to evaluate the quality of studies and included Machine Learning models.

Results: Out of 1821 articles, 52 studies have met the inclusion criteria. The majority of Machine Learning models were developed to predict the course of disease, and postoperative complications. The course of disease has been predicted with accuracies up to 99%, and postoperative complications with accuracies up to 89%. Most studies had a retrospective study design, in which external validation was absent for Machine Learning models.

Conclusion: Machine learning models have shown promising accuracies in the prediction of short-term and long-term surgical outcomes after hepatopancreaticobiliary surgery. External validation of Machine Learning models is required to facilitate the clinical introduction of Machine Learning.

Keywords

Artificial intelligence / machine learning / hepatectomy / cholecystectomy / pancreatectomy

References

[1] Briganti G.Artificial intelligence in medicine: today and tomorrow.Front Med (Lausanne)2020;7:27 PMCID:PMC7012990

[2] Visvikis D,Jaouen V.Artificial intelligence, machine (deep) learning and radio(geno)mics: definitions and nuclear medicine imaging applications.Eur J Nucl Med Mol Imaging2019;46:2630-7

[3] Davenport T.The potential for artificial intelligence in healthcare.Future Healthc J2019;6:94-8 PMCID:PMC6616181

[4] Mintz Y.Introduction to artificial intelligence in medicine.Minim Invasive Ther Allied Technol2019;28:73-81

[5] Mayerhoefer ME,Langs G.Introduction to radiomics.J Nucl Med2020;61:488-95 PMCID:PMC9374044

[6] El Naqa I, Murphy MJ. What is machine learning? In: El Naqa I, Li R, Murphy M, editors. Machine learning in radiation oncology. Cham: Springer; 2015. p. 3-11.

[7] Song YY.Decision tree methods: applications for classification and prediction.Shanghai Arch Psychiatry2015;27:130-5 PMCID:PMC4466856

[8] Friedman JH.Stochastic gradient boosting.2002;38:367-78

[9] Breiman L.Random forests.Machine Learning2001;45:5-32

[10] Zhang L,Jiao L.Wavelet support vector machine.IEEE Trans Syst Man Cybern B Cybern2004;34:34-9

[11] Abraham A. Artificial neural networks. Handbook of measuring system design. New Jersey: John Wiley & Sons; 2005. p. 901-8.

[12] Albawi S,Al-Zawi S.Understanding of a convolutional neural network. 2017 International Conference on Engineering and Technology (ICET).

[13] Rusk N.Deep learning.Nat Methods2016;13:35-35

[14] Kumar V,Basu S.Radiomics: the process and the challenges.Magn Reson Imaging2012;30:1234-48 PMCID:PMC3563280

[15] Yu KH,Kohane IS.Artificial intelligence in healthcare.Nat Biomed Eng2018;2:719-31

[16] Andras I,van Leeuwen FWB.Artificial intelligence and robotics: a combination that is changing the operating room.World J Urol2020;38:2359-66

[17] Spolverato G,Hyder O,Pawlik TM.Failure to rescue as a source of variation in hospital mortality after hepatic surgery.Br J Surg2014;101:836-46

[18] Pulte D,Schröder CC.GEKID Cancer Survival Working GroupSurvival of patients with hepatobiliary tract and duodenal cancer sites in Germany and the United States in the early 21st century.Int J Cancer2018;143:324-32

[19] Versteijne E,Suker M.Dutch Pancreatic Cancer GroupNeoadjuvant chemoradiotherapy versus upfront surgery for resectable and borderline resectable pancreatic cancer: long-term results of the dutch randomized preopanc trial.J Clin Oncol2022;40:1220-30

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

[21] Moons KGM,Riley RD.PROBAST: a tool to assess risk of bias and applicability of prediction model studies: explanation and elaboration.Ann Intern Med2019;170:W1-W33

[22] Mai RY,Meng WD.Artificial neural network model to predict post-hepatectomy early recurrence of hepatocellular carcinoma without macroscopic vascular invasion.BMC Cancer2021;21:283 PMCID:PMC7962237

[23] Chong H,Pan X.Peritumoral dilation radiomics of gadoxetate disodium-enhanced MRI excellently predicts early recurrence of hepatocellular carcinoma without macrovascular invasion after hepatectomy.J Hepatocell Carcinoma2021;8:545-63 PMCID:PMC8200148

[24] Ning P,Hai J.Application of CT radiomics in prediction of early recurrence in hepatocellular carcinoma.Abdom Radiol (NY)2020;45:64-72

[25] Shan QY,Feng ST.CT-based peritumoral radiomics signatures to predict early recurrence in hepatocellular carcinoma after curative tumor resection or ablation.Cancer Imaging2019;19:11 PMCID:PMC6391838

[26] Wang W,Iwamoto Y.Deep fusion models of multi-phase CT and selected clinical data for preoperative prediction of early recurrence in hepatocellular carcinoma.IEEE Access2020;8:139212-20

[27] Ji GW,Xu Q.Machine-learning analysis of contrast-enhanced CT radiomics predicts recurrence of hepatocellular carcinoma after resection: A multi-institutional study.EBioMedicine2019;50:156-65 PMCID:PMC6923482

[28] Qin H,Zhang J.Machine-learning radiomics to predict early recurrence in perihilar cholangiocarcinoma after curative resection.Liver Int2021;41:837-50

[29] Schoenberg MB,Koch D.A novel machine learning algorithm to predict disease free survival after resection of hepatocellular carcinoma.Ann Transl Med2020;8:434 PMCID:PMC7210189

[30] Chiu HC,Lee KT,Ho WH.Mortality predicted accuracy for hepatocellular carcinoma patients with hepatic resection using artificial neural network.ScientificWorldJournal2013;2013:201976 PMCID:PMC3659648

[31] Qiao G,Huang A,Lau WY.Artificial neural networking model for the prediction of post-hepatectomy survival of patients with early hepatocellular carcinoma.J Gastroenterol Hepatol2014;29:2014-20

[32] Spelt L,Andersson R.Artificial neural networks - a method for prediction of survival following liver resection for colorectal cancer metastases.Eur J Surg Oncol2013;39:648-54

[33] Ho WH,Chen HY,Chiu HC.Disease-free survival after hepatic resection in hepatocellular carcinoma patients: a prediction approach using artificial neural network.PLoS One2012;7:e29179 PMCID:PMC3250424

[34] Dong Y,Xia W.Preoperative prediction of microvascular invasion in hepatocellular carcinoma: initial application of a radiomic algorithm based on grayscale ultrasound images.Front Oncol2020;10:353 PMCID:PMC7096379

[35] Feng ST,Liao B.Preoperative prediction of microvascular invasion in hepatocellular cancer: a radiomics model using Gd-EOB-DTPA-enhanced MRI.Eur Radiol2019;29:4648-59

[36] Song D,Wang W.Using deep learning to predict microvascular invasion in hepatocellular carcinoma based on dynamic contrast-enhanced MRI combined with clinical parameters.J Cancer Res Clin Oncol2021;147:3757-67

[37] Zhou W,Cen X.Prediction of microvascular invasion of hepatocellular carcinoma based on contrast-enhanced MR and 3D convolutional neural networks.Front Oncol2021;11:588010 PMCID:PMC8040801

[38] Mao B,Duan S,Tao Y.Preoperative classification of primary and metastatic liver cancer via machine learning-based ultrasound radiomics.Eur Radiol2021;31:4576-86

[39] Yao X,Yang C.A novel approach to assessing differentiation degree and lymph node metastasis of extrahepatic cholangiocarcinoma: prediction using a radiomics-based particle swarm optimization and support vector machine model.JMIR Med Inform2020;8:e23578 PMCID:PMC7573697

[40] Sahara K,Tsilimigras DI.Machine learning predicts unpredicted deaths with high accuracy following hepatopancreatic surgery.Hepatobiliary Surg Nutr2021;10:20-30 PMCID:PMC7867718

[41] Hamamoto I,Hashimoto T,Maeba T.Prediction of the early prognosis of the hepatectomized patient with hepatocellular carcinoma with a neural network.Computers in Biology and Medicine1995;25:49-59

[42] Zhu HB,Ye M.Deep learning-assisted magnetic resonance imaging prediction of tumor response to chemotherapy in patients with colorectal liver metastases.Int J Cancer2021;148:1717-30

[43] Chen Y,Mo Y.Prediction of post-hepatectomy liver failure in patients with hepatocellular carcinoma based on radiomics using Gd-EOB-DTPA-enhanced MRI: the liver failure model.Front Oncol2021;11:605296 PMCID:PMC7987905

[44] Zhu WS,Yang ZH,Shen J.Radiomics model based on preoperative gadoxetic acid-enhanced MRI for predicting liver failure.World J Gastroenterol2020;26:1208-20 PMCID:PMC7093309

[45] Mai RY,Bai T.Artificial neural network model for preoperative prediction of severe liver failure after hemihepatectomy in patients with hepatocellular carcinoma.Surgery2020;168:643-52

[46] Mai RY,Mo YS.Artificial neural network model for liver cirrhosis diagnosis in patients with hepatitis B virus-related hepatocellular carcinoma.Ther Clin Risk Manag2020;16:639-49 PMCID:PMC7381792

[47] Kato H,Zhang X.Computer-aided diagnosis of hepatic fibrosis: preliminary evaluation of MRI texture analysis using the finite difference method and an artificial neural network.AJR Am J Roentgenol2007;189:117-22

[48] Zhang T,He X.Prediction of remnant liver regeneration after right hepatectomy in patients with hepatocellular carcinoma using preoperative CT texture analysis and clinical features.Contrast Media Mol Imaging2021;2021:5572470 PMCID:PMC8213498

[49] Merath K,Mehta R.Use of machine learning for prediction of patient risk of postoperative complications after liver, pancreatic, and colorectal surgery.J Gastrointest Surg2020;24:1843-51

[50] Lei L,Xue Q,Zhou CM.A comparative study of machine learning algorithms for predicting acute kidney injury after liver cancer resection.PeerJ2020;8:e8583 PMCID:PMC7047869

[51] Tsilimigras DI,Moris D.Utilizing machine learning for pre- and postoperative assessment of patients undergoing resection for BCLC-0, A and B hepatocellular carcinoma: implications for resection beyond the BCLC guidelines.Ann Surg Oncol2020;27:866-74

[52] Tsilimigras DI,Moris D.A machine-based approach to preoperatively identify patients with the most and least benefit associated with resection for intrahepatic cholangiocarcinoma: an international multi-institutional analysis of 1146 patients.Ann Surg Oncol2020;27:1110-9

[53] Bagante F,Merath K.Intrahepatic cholangiocarcinoma tumor burden: a classification and regression tree model to define prognostic groups after resection.Surgery2019;166:983-90

[54] Tsilimigras DI,Paredes AZ.A novel classification of intrahepatic cholangiocarcinoma phenotypes using machine learning techniques: an international multi-institutional analysis.Ann Surg Oncol2020;27:5224-32

[55] Moro A,Tsilimigras DI.Prognostic factors differ according to KRAS mutational status: a classification and regression tree model to define prognostic groups after hepatectomy for colorectal liver metastasis.Surgery2020;168:497-503

[56] Gholipour C,Shalchi RA.Prediction of conversion of laparoscopic cholecystectomy to open surgery with artificial neural networks.BMC Surg2009;9:13 PMCID:PMC2745364

[57] Eldar S,Buzaglo D.Conversion of laparoscopic cholecystectomy to open cholecystectomy in acute cholecystitis: artificial neural networks improve the prediction of conversion.World J Surg2002;26:79-85

[58] Bouarfa L,Feussner H.Prediction of intraoperative complexity from preoperative patient data for laparoscopic cholecystectomy.Artif Intell Med2011;52:169-76

[59] Liew PL,Lin YC.Comparison of artificial neural networks with logistic regression in prediction of gallbladder disease among obese patients.Dig Liver Dis2007;39:356-62

[60] Vukicevic AM,Radovic M.Automated development of artificial neural networks for clinical purposes: Application for predicting the outcome of choledocholithiasis surgery.Comput Biol Med2016;75:80-9

[61] Shi HY,Tsai JT.Comparisons of prediction models of quality of life after laparoscopic cholecystectomy: a longitudinal prospective study.PLoS One2012;7:e51285 PMCID:PMC3532431

[62] Velez-Serrano JF,Hernandez-Barrera V.Prediction of in-hospital mortality after pancreatic resection in pancreatic cancer patients: a boosting approach via a population-based study using health administrative data.PLoS One2017;12:e0178757 PMCID:PMC5462391

[63] Mofidi R,Madhavan KK,Parks RW.Identification of severe acute pancreatitis using an artificial neural network.Surgery2007;141:59-66

[64] Ansari D,Andersson R,Tingstedt B.Artificial neural networks predict survival from pancreatic cancer after radical surgery.Am J Surg2013;205:1-7

[65] Walczak S.An evaluation of artificial neural networks in predicting pancreatic cancer survival.J Gastrointest Surg2017;21:1606-12

[66] Sala Elarre P,Yu KH.Use of machine-learning algorithms in intensified preoperative therapy of pancreatic cancer to predict individual risk of relapse.Cancers (Basel)2019;11:606 PMCID:PMC6562932

[67] Mu W,Gao F.Prediction of clinically relevant pancreatico-enteric anastomotic fistulas after pancreatoduodenectomy using deep learning of preoperative computed tomography.Theranostics2020;10:9779-88 PMCID:PMC7449906

[68] Lin Z,Cai J.Preoperative prediction of clinically relevant postoperative pancreatic fistula after pancreaticoduodenectomy.Eur J Radiol2021;139:109693

[69] Han IW,Ryu Y.Risk prediction platform for pancreatic fistula after pancreatoduodenectomy using artificial intelligence.World J Gastroenterol2020;26:4453-64 PMCID:PMC7438201

[70] Skawran SM,Baessler B.Can magnetic resonance imaging radiomics of the pancreas predict postoperative pancreatic fistula?.Eur J Radiol2021;140:109733

[71] Cos H,Williams G.Predicting outcomes in patients undergoing pancreatectomy using wearable technology and machine learning: prospective cohort study.J Med Internet Res2021;23:e23595 PMCID:PMC8074869

[72] Kuwahara T,Mizuno N.Usefulness of deep learning analysis for the diagnosis of malignancy in intraductal papillary mucinous neoplasms of the pancreas.Clin Transl Gastroenterol2019;10:1-8 PMCID:PMC6602761

[73] Attiyeh MA,Gazit L.Preoperative risk prediction for intraductal papillary mucinous neoplasms by quantitative CT image analysis.HPB (Oxford)2019;21:212-8 PMCID:PMC6367060

[74] Chen Y,Zhang J.Prognostic value and predication model of microvascular invasion in patients with intrahepatic cholangiocarcinoma: a multicenter study from China.BMC Cancer2021;21:1299 PMCID:PMC8645153

[75] Ren Z,Fan X.Survival prediction model for postoperative hepatocellular carcinoma patients.Medicine (Baltimore)2017;96:e7902 PMCID:PMC5604640

[76] Orcutt ST.Liver resection and surgical strategies for management of primary liver cancer.Cancer Control2018;25:1073274817744621 PMCID:PMC5933574

[77] Zhu H,Du Y.Pancreatic cancer: challenges and opportunities.BMC Med2018;16:214 PMCID:PMC6249728

[78] Anwanwan D,Singh S,Singh R.Challenges in liver cancer and possible treatment approaches.Biochim Biophys Acta Rev Cancer2020;1873:188314 PMCID:PMC6981221

[79] Samim M,AbuHilal M.HPB-RISC Study GroupSurgeons’ assessment versus risk models for predicting complications of hepato-pancreato-biliary surgery (HPB-RISC): a multicenter prospective cohort study.HPB (Oxford)2018;20:809-14

[80] Li B,Qiu Z,Jiang X.A cohort study of hepatectomy-related complications and prediction model for postoperative liver failure after major liver resection in 1441 patients without obstructive jaundice.Ann Transl Med2021;9:305 PMCID:PMC7944277

[81] Ma KW,She WH.Risk prediction model for major complication after hepatectomy for malignant tumour - a validated scoring system from a university center.Surg Oncol2017;26:446-52

[82] Lu JH,Hu XY,Wang S.Construction and evaluation of a nomogram to predict gallstone disease based on body composition.Int J Gen Med2022;15:5947-56 PMCID:PMC9258801

[83] Shimizu Y,Hirono S.New model for predicting malignancy in patients with intraductal papillary mucinous neoplasm.Ann Surg2020;272:155-62

[84] Kim MS,Park HW.Preoperative prediction model for conversion of laparoscopic to open cholecystectomy in patient with acute cholecystitis: based on clinical, laboratory, and CT parameters.J Comput Assist Tomogr2014;38:727-32

[85] Liu R,Wang Z.Artificial intelligence in laparoscopic cholecystectomy: does computer vision outperform human vision?.Art Int Surg2022;2:80-92

[86] Tranter-entwistle I,Connor S.Operative difficulty in laparoscopic cholecystectomy: considering the role of machine learning platforms in clinical practice.Art Int Surg2022;

[87] Bzdok D,Krzywinski M.Statistics versus machine learning.Nat Methods2018;15:233-4 PMCID:PMC6082636

[88] Grant L,Nemnom MJ.Machine learning versus traditional methods for the development of risk stratification scores: a case study using original Canadian Syncope Risk Score data.Intern Emerg Med2022;17:1145-53

[89] Mandrekar JN.Receiver operating characteristic curve in diagnostic test assessment.J Thorac Oncol2010;5:1315-6

[90] Kusters R,Berry H.Interdisciplinary research in artificial intelligence: challenges and opportunities.Front Big Data2020;3:577974 PMCID:PMC7931862