Machine learning to guide clinical decision-making in abdominal surgery-a systematic literature review.

Abdominal surgery Clinical decision-making Digitalization Machine learning Postoperative complications Risk prediction

Journal

Langenbeck's archives of surgery
ISSN: 1435-2451
Titre abrégé: Langenbecks Arch Surg
Pays: Germany
ID NLM: 9808285

Informations de publication

Date de publication:
Feb 2022
Historique:
received: 05 05 2021
accepted: 03 10 2021
pubmed: 31 10 2021
medline: 19 2 2022
entrez: 30 10 2021
Statut: ppublish

Résumé

An indication for surgical therapy includes balancing benefits against risk, which remains a key task in all surgical disciplines. Decisions are oftentimes based on clinical experience while guidelines lack evidence-based background. Various medical fields capitalized the application of machine learning (ML), and preliminary research suggests promising implications in surgeons' workflow. Hence, we evaluated ML's contemporary and possible future role in clinical decision-making (CDM) focusing on abdominal surgery. Using the PICO framework, relevant keywords and research questions were identified. Following the PRISMA guidelines, a systemic search strategy in the PubMed database was conducted. Results were filtered by distinct criteria and selected articles were manually full text reviewed. Literature review revealed 4,396 articles, of which 47 matched the search criteria. The mean number of patients included was 55,843. A total of eight distinct ML techniques were evaluated whereas AUROC was applied by most authors for comparing ML predictions vs. conventional CDM routines. Most authors (N = 30/47, 63.8%) stated ML's superiority in the prediction of benefits and risks of surgery. The identification of highly relevant parameters to be integrated into algorithms allowing a more precise prognosis was emphasized as the main advantage of ML in CDM. A potential value of ML for surgical decision-making was demonstrated in several scientific articles. However, the low number of publications with only few collaborative studies between surgeons and computer scientists underpins the early phase of this highly promising field. Interdisciplinary research initiatives combining existing clinical datasets and emerging techniques of data processing may likely improve CDM in abdominal surgery in the future.

Identifiants

pubmed: 34716472
doi: 10.1007/s00423-021-02348-w
pii: 10.1007/s00423-021-02348-w
pmc: PMC8847247
doi:

Types de publication

Journal Article Systematic Review

Langues

eng

Sous-ensembles de citation

IM

Pagination

51-61

Informations de copyright

© 2021. The Author(s).

Références

Yang CK, Teng A, Lee DY, Rose K (2015) Pulmonary complications after major abdominal surgery: National Surgical Quality Improvement Program analysis. J Surg Res 198:441–449. https://doi.org/10.1016/j.jss.2015.03.028
doi: 10.1016/j.jss.2015.03.028 pubmed: 25930169
Kung J, Miller RR, Mackowiak PA (2012) Failure of Clinical Practice Guidelines to Meet Institute of Medicine Standards. Arch Intern Med 172:1628. https://doi.org/10.1001/2013.jamainternmed.56
doi: 10.1001/2013.jamainternmed.56 pubmed: 23089902
Marchegiani G, Salvia R (2021) Guidelines on Pancreatic Cystic Neoplasms: major inconsistencies with available evidence and clinical practice Results from an International survey. Gastroenterology. https://doi.org/10.1053/j.gastro.2021.02.026
doi: 10.1053/j.gastro.2021.02.026 pubmed: 34678216
Saklad M (1941) GRADING OF PATIENTS FOR SURGICAL PROCEDURES. Anesthesiology 2:281–284. https://doi.org/10.1097/00000542-194105000-00004
doi: 10.1097/00000542-194105000-00004
Bilimoria KY, Liu Y, Paruch JL et al (2013) Development and Evaluation of the Universal ACS NSQIP Surgical Risk Calculator: A Decision Aid and Informed Consent Tool for Patients and Surgeons. J Am Coll Surg 217:833-842.e3. https://doi.org/10.1016/j.jamcollsurg.2013.07.385
doi: 10.1016/j.jamcollsurg.2013.07.385 pubmed: 24055383 pmcid: 3805776
Moonesinghe SR, Mythen MG, Das P et al (2013) Risk Stratification Tools for Predicting Morbidity and Mortality in Adult Patients Undergoing Major Surgery. Anesthesiology 119:959–981. https://doi.org/10.1097/ALN.0b013e3182a4e94d
doi: 10.1097/ALN.0b013e3182a4e94d pubmed: 24195875
Bulian DR (2015) Systematic analysis of the safety and benefits of transvaginal hybrid-NOTES cholecystectomy. World J Gastroenterol 21:10915. https://doi.org/10.3748/wjg.v21.i38.10915
doi: 10.3748/wjg.v21.i38.10915 pubmed: 26478683 pmcid: 4600593
Murdoch TB, Detsky AS (2013) The Inevitable Application of Big Data to Health Care. JAMA 309:1351. https://doi.org/10.1001/jama.2013.393
doi: 10.1001/jama.2013.393 pubmed: 23549579
Nam JG, Park S, Hwang EJ et al (2019) Development and Validation of Deep Learning–based Automatic Detection Algorithm for Malignant Pulmonary Nodules on Chest Radiographs. Radiology 290:218–228. https://doi.org/10.1148/radiol.2018180237
doi: 10.1148/radiol.2018180237 pubmed: 30251934
Ehteshami Bejnordi B, Veta M, Johannes van Diest P et al (2017) Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer. JAMA 318:2199. https://doi.org/10.1001/jama.2017.14585
doi: 10.1001/jama.2017.14585 pubmed: 29234806 pmcid: 5820737
Rajkomar A, Dean J, Kohane I (2019) Machine Learning in Medicine. N Engl J Med 380:1347–1358. https://doi.org/10.1056/NEJMra1814259
doi: 10.1056/NEJMra1814259 pubmed: 30943338
Maier-Hein L, Vedula SS, Speidel S et al (2017) Surgical data science for next-generation interventions. Nat Biomed Eng 1:691–696. https://doi.org/10.1038/s41551-017-0132-7
doi: 10.1038/s41551-017-0132-7 pubmed: 31015666
Schardt C, Adams MB, Owens T et al (2007) Utilization of the PICO framework to improve searching PubMed for clinical questions. BMC Med Inform Decis Mak 7:16. https://doi.org/10.1186/1472-6947-7-16
doi: 10.1186/1472-6947-7-16 pubmed: 17573961 pmcid: 1904193
Moher D, Liberati A, Tetzlaff J, Altman DG (2009) Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement. PLoS Med 6:e1000097. https://doi.org/10.1371/journal.pmed.1000097
doi: 10.1371/journal.pmed.1000097 pubmed: 19621072 pmcid: 2707599
Brennan M, Puri S, Ozrazgat-Baslanti T et al (2019) Comparing clinical judgment with the MySurgeryRisk algorithm for preoperative risk assessment: A pilot usability study. Surgery 165:1035–1045. https://doi.org/10.1016/j.surg.2019.01.002
doi: 10.1016/j.surg.2019.01.002 pubmed: 30792011
Andres A, Montano-Loza A, Greiner R et al (2018) A novel learning algorithm to predict individual survival after liver transplantation for primary sclerosing cholangitis. PLoS ONE 13:1–14. https://doi.org/10.1371/journal.pone.0193523
doi: 10.1371/journal.pone.0193523
Ansari D, Nilsson J, Andersson R et al (2013) Artificial neural networks predict survival from pancreatic cancer after radical surgery. Am J Surg 205:1–7. https://doi.org/10.1016/j.amjsurg.2012.05.032
doi: 10.1016/j.amjsurg.2012.05.032 pubmed: 23245432
Aron-Wisnewsky J, Sokolovska N, Liu Y et al (2017) The advanced-DiaRem score improves prediction of diabetes remission 1 year post-Roux-en-Y gastric bypass. Diabetologia 60:1892–1902. https://doi.org/10.1007/s00125-017-4371-7
doi: 10.1007/s00125-017-4371-7 pubmed: 28733906
Briceño J, Cruz-Ramírez M, Prieto M et al (2014) Use of artificial intelligence as an innovative donor-recipient matching model for liver transplantation: Results from a multicenter Spanish study. J Hepatol 61:1020–1028. https://doi.org/10.1016/j.jhep.2014.05.039
doi: 10.1016/j.jhep.2014.05.039 pubmed: 24905493
Cruz-Ramírez M, Hervás-Martínez C, Fernández JC et al (2013) Predicting patient survival after liver transplantation using evolutionary multi-objective artificial neural networks. Artif Intell Med 58:37–49. https://doi.org/10.1016/j.artmed.2013.02.004
doi: 10.1016/j.artmed.2013.02.004 pubmed: 23489761
Debédat J, Sokolovska N, Coupaye M et al (2018) Long-term Relapse of Type 2 Diabetes After Roux-en-Y Gastric Bypass: Prediction and clinical relevance. Diabetes Care 41:2086–2095. https://doi.org/10.2337/dc18-0567
doi: 10.2337/dc18-0567 pubmed: 30082327
Ho WH, Lee KT, Chen HY et al (2012) Disease-free survival after hepatic resection in hepatocellular carcinoma patients: A prediction approach using artificial neural network. PLoS ONE 7:1–9. https://doi.org/10.1371/journal.pone.0029179
doi: 10.1371/journal.pone.0029179
Hsieh CH, Lu RH, Lee NH et al (2011) Novel solutions for an old disease: Diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks. Surgery 149:87–93. https://doi.org/10.1016/j.surg.2010.03.023
doi: 10.1016/j.surg.2010.03.023 pubmed: 20466403
Ichimasa K, Kudo SE, Mori Y et al (2018) Artificial intelligence may help in predicting the need for additional surgery after endoscopic resection of T1 colorectal cancer. Endoscopy 50:230–240. https://doi.org/10.1055/s-0043-122385
doi: 10.1055/s-0043-122385 pubmed: 29272905
Johnston SS, Morton JM, Kalsekar I et al (2019) Using Machine Learning Applied to Real-World Healthcare Data for Predictive Analytics: An Applied Example in Bariatric Surgery. Value Heal 22:580–586. https://doi.org/10.1016/j.jval.2019.01.011
doi: 10.1016/j.jval.2019.01.011
Kuwahara T, Hara K, Mizuno N et al (2019) Usefulness of deep learning analysis for the diagnosis of malignancy in intraductal papillary mucinous neoplasms of the pancreas. Clin Transl Gastroenterol 10:1–8. https://doi.org/10.14309/ctg.0000000000000045
doi: 10.14309/ctg.0000000000000045 pubmed: 31117111
Lau L, Kankanige Y, Rubinstein B et al (2017) Machine-Learning Algorithms Predict Graft Failure after Liver Transplantation. Transplantation 101:e125–e132. https://doi.org/10.1097/TP.0000000000001600
doi: 10.1097/TP.0000000000001600 pubmed: 27941428 pmcid: 7228574
Maubert A, Birtwisle L, Bernard JL et al (2019) Can machine learning predict resecability of a peritoneal carcinomatosis? Surg Oncol 29:120–125. https://doi.org/10.1016/j.suronc.2019.04.008
doi: 10.1016/j.suronc.2019.04.008 pubmed: 31196475
Pesonen E, Eskelinen M, Juhola M (1996) Comparison of different neural network algorithms in the diagnosis of acute appendicitis. Int J Biomed Comput 40:227–233. https://doi.org/10.1016/0020-7101(95)01147-1
doi: 10.1016/0020-7101(95)01147-1 pubmed: 8666475
Prabhudesai SG, Gould S, Rekhraj S et al (2008) Artificial neural networks: Useful aid in diagnosing acute appendicitis. World J Surg 32:305–309. https://doi.org/10.1007/s00268-007-9298-6
doi: 10.1007/s00268-007-9298-6 pubmed: 18043966
Rahman SA, Walker RC, Lloyd MA et al (2020) Machine learning to predict early recurrence after oesophageal cancer surgery. Br J Surg 107:1042–1052. https://doi.org/10.1002/bjs.11461
doi: 10.1002/bjs.11461 pubmed: 31997313 pmcid: 7299663
Reismann J, Romualdi A, Kiss N et al (2019) Diagnosis and classification of pediatric acute appendicitis by artificial intelligence methods: An investigator-independent approach. PLoS ONE 14:1–11. https://doi.org/10.1371/journal.pone.0222030
doi: 10.1371/journal.pone.0222030
Sakai S, Kobayashi K, Toyabe SI et al (2007) Comparison of the levels of accuracy of an artificial neural network model and a logistic regression model for the diagnosis of acute appendicitis. J Med Syst 31:357–364. https://doi.org/10.1007/s10916-007-9077-9
doi: 10.1007/s10916-007-9077-9 pubmed: 17918689
Springer S, Masica DL, Dal Molin M et al (2019) A multimodality test to guide the management of patients with a pancreatic cyst. Sci Transl Med 11:eaav4772. https://doi.org/10.1126/scitranslmed.aav4772
doi: 10.1126/scitranslmed.aav4772 pubmed: 31316009 pmcid: 7859881
Tsilimigras DI, Mehta R, Moris D et al (2020) 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 Oncol 27:1110–1119. https://doi.org/10.1245/s10434-019-08067-3
doi: 10.1245/s10434-019-08067-3 pubmed: 31728792
Xu Y, Ju L, Tong J et al (2020) Machine Learning Algorithms for Predicting the Recurrence of Stage IV Colorectal Cancer After Tumor Resection. Sci Rep 10:1–9. https://doi.org/10.1038/s41598-020-59115-y
doi: 10.1038/s41598-020-59115-y
Bertsimas D, Dunn J, Velmahos GC, Kaafarani HMA (2018) Surgical Risk Is Not Linear: Derivation and Validation of a Novel, User-friendly, and Machine-learning-based Predictive OpTimal Trees in Emergency Surgery Risk (POTTER) Calculator. Ann Surg 268:574–583. https://doi.org/10.1097/SLA.0000000000002956
doi: 10.1097/SLA.0000000000002956 pubmed: 30124479
Bihorac A, Ozrazgat-Baslanti T, Ebadi A et al (2019) MySurgeryRisk: Development and Validation of a Machine-learning Risk Algorithm for Major Complications and Death After Surgery. Ann Surg 269:652–662. https://doi.org/10.1097/SLA.0000000000002706
doi: 10.1097/SLA.0000000000002706 pubmed: 29489489
Bronsert M, Singh AB, Henderson WG et al (2020) Identification of postoperative complications using electronic health record data and machine learning. Am J Surg 220:114–119. https://doi.org/10.1016/j.amjsurg.2019.10.009
doi: 10.1016/j.amjsurg.2019.10.009 pubmed: 31635792
Cao Y, Bass GA, Ahl R et al (2020) The statistical importance of P-POSSUM scores for predicting mortality after emergency laparotomy in geriatric patients. BMC Med Inform Decis Mak 20:1–11. https://doi.org/10.1186/s12911-020-1100-9
doi: 10.1186/s12911-020-1100-9
Chen D, Afzal N, Sohn S et al (2018) Postoperative bleeding risk prediction for patients undergoing colorectal surgery. Surgery 164:1209–1216. https://doi.org/10.1016/j.surg.2018.05.043
doi: 10.1016/j.surg.2018.05.043 pubmed: 30033185
Chiew CJ, Liu N, Wong TH, et al (2019) Utilizing Machine Learning Methods for Preoperative Prediction of Postsurgical Mortality and Intensive Care Unit Admission. Ann Surg Publish Ah:1–7. https://doi.org/10.1097/sla.0000000000003297
Chiu HC, Ho TW, Lee KT, et al (2013) Mortality predicted accuracy for hepatocellular carcinoma patients with hepatic resection using artificial neural network. Sci World J 2013. https://doi.org/10.1155/2013/201976
Corey KM, Kashyap S, Lorenzi E et al (2018) Development and validation of machine learning models to identify high-risk surgical patients using automatically curated electronic health record data (Pythia): A retrospective, single-site study. PLoS Med 15:1–19. https://doi.org/10.1371/journal.pmed.1002701
doi: 10.1371/journal.pmed.1002701
Datta S, Loftus TJ, Ruppert MM et al (2020) Added Value of Intraoperative Data for Predicting Postoperative Complications: The MySurgeryRisk PostOp Extension. J Surg Res 254:350–363. https://doi.org/10.1016/j.jss.2020.05.007
doi: 10.1016/j.jss.2020.05.007 pubmed: 32531520 pmcid: 7755426
Ehlers AP, Roy SB, Khor S, et al (2017) Improved Risk Prediction Following Surgery Using Machine Learning Algorithms. eGEMs (Generating Evid Methods to Improv patient outcomes) 5:3. https://doi.org/10.13063/2327-9214.1278
Ershoff BD, Lee CK, Wray CL et al (2020) Training and Validation of Deep Neural Networks for the Prediction of 90-Day Post-Liver Transplant Mortality Using UNOS Registry Data. Transplant Proc 52:246–258. https://doi.org/10.1016/j.transproceed.2019.10.019
doi: 10.1016/j.transproceed.2019.10.019 pubmed: 31926745 pmcid: 7523496
Francis NK, Luther A, Salib E et al (2015) The use of artificial neural networks to predict delayed discharge and readmission in enhanced recovery following laparoscopic colorectal cancer surgery. Tech Coloproctol 19:419–428. https://doi.org/10.1007/s10151-015-1319-0
doi: 10.1007/s10151-015-1319-0 pubmed: 26084884
Fritz BA, Cui Z, Zhang M et al (2019) Deep-learning model for predicting 30-day postoperative mortality. Br J Anaesth 123:688–695. https://doi.org/10.1016/j.bja.2019.07.025
doi: 10.1016/j.bja.2019.07.025 pubmed: 31558311 pmcid: 6993109
Hill BL, Brown R, Gabel E et al (2019) An automated machine learning-based model predicts postoperative mortality using readily-extractable preoperative electronic health record data. Br J Anaesth 123:877–886. https://doi.org/10.1016/j.bja.2019.07.030
doi: 10.1016/j.bja.2019.07.030 pubmed: 31627890 pmcid: 6883494
Hyer JM, White S, Cloyd J et al (2020) Can We Improve Prediction of Adverse Surgical Outcomes? Development of a Surgical Complexity Score Using a Novel Machine Learning Technique. J Am Coll Surg 230:43-52.e1. https://doi.org/10.1016/j.jamcollsurg.2019.09.015
doi: 10.1016/j.jamcollsurg.2019.09.015 pubmed: 31672674
Jauk S, Kramer D, Stark G et al (2019) Development of a Machine Learning Model Predicting an ICU Admission for Patients with Elective Surgery and Its Prospective Validation in Clinical Practice. Stud Health Technol Inform 264:173–177. https://doi.org/10.3233/SHTI190206
doi: 10.3233/SHTI190206 pubmed: 31437908
Kambakamba P, Mannil M, Herrera PE et al (2020) The potential of machine learning to predict postoperative pancreatic fistula based on preoperative, non-contrast-enhanced CT: A proof-of-principle study. Surg (United States) 167:448–454. https://doi.org/10.1016/j.surg.2019.09.019
doi: 10.1016/j.surg.2019.09.019
Lee CK, Hofer I, Gabel E et al (2018) Development and Validation of a Deep Neural Network Model for Prediction of Postoperative In-hospital Mortality. Anesthesiology 129:649–662. https://doi.org/10.1097/ALN.0000000000002186
doi: 10.1097/ALN.0000000000002186 pubmed: 29664888
Liu CL, Soong RS, Lee WC et al (2020) Predicting Short-term Survival after Liver Transplantation using Machine Learning. Sci Rep 10:1–10. https://doi.org/10.1038/s41598-020-62387-z
doi: 10.1038/s41598-020-62387-z
Merath K, Hyer JM, Mehta R et al (2020) Use of Machine Learning for Prediction of Patient Risk of Postoperative Complications After Liver, Pancreatic, and Colorectal Surgery. J Gastrointest Surg 24:1843–1851. https://doi.org/10.1007/s11605-019-04338-2
doi: 10.1007/s11605-019-04338-2 pubmed: 31385172
Soguero-Ruiz C, Hindberg K, Mora-Jiménez I et al (2016) Predicting colorectal surgical complications using heterogeneous clinical data and kernel methods. J Biomed Inform 61:87–96. https://doi.org/10.1016/j.jbi.2016.03.008
doi: 10.1016/j.jbi.2016.03.008 pubmed: 26980235
Sohn S, Larson DW, Habermann EB et al (2017) Detection of clinically important colorectal surgical site infection using Bayesian network. J Surg Res 209:168–173. https://doi.org/10.1016/j.jss.2016.09.058
doi: 10.1016/j.jss.2016.09.058 pubmed: 28032554
Thottakkara P, Ozrazgat-Baslanti T, Hupf BB et al (2016) Application of machine learning techniques to high-dimensional clinical data to forecast postoperative complications. PLoS ONE 11:1–19. https://doi.org/10.1371/journal.pone.0155705
doi: 10.1371/journal.pone.0155705
Weller GB, Lovely J, Larson DW et al (2018) Leveraging electronic health records for predictive modeling of post-surgical complications. Stat Methods Med Res 27:3271–3285. https://doi.org/10.1177/0962280217696115
doi: 10.1177/0962280217696115 pubmed: 29298612
Topol EJ (2019) High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25:44–56. https://doi.org/10.1038/s41591-018-0300-7
doi: 10.1038/s41591-018-0300-7 pubmed: 30617339
Knapp EA, Fink AK, Goss CH et al (2016) The Cystic Fibrosis Foundation Patient Registry. Design and Methods of a National Observational Disease Registry. Ann Am Thorac Soc 13:1173–1179. https://doi.org/10.1513/AnnalsATS.201511-781OC
doi: 10.1513/AnnalsATS.201511-781OC pubmed: 27078236
Zhao Q, Adeli E, Pohl KM (2020) Training confounder-free deep learning models for medical applications. Nat Commun 11:6010. https://doi.org/10.1038/s41467-020-19784-9
doi: 10.1038/s41467-020-19784-9 pubmed: 33243992 pmcid: 7691500
Christodoulou E, Ma J, Collins GS et al (2019) A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol 110:12–22. https://doi.org/10.1016/j.jclinepi.2019.02.004
doi: 10.1016/j.jclinepi.2019.02.004 pubmed: 30763612
Alba AC, Agoritsas T, Walsh M et al (2017) Discrimination and Calibration of Clinical Prediction Models. JAMA 318:1377. https://doi.org/10.1001/jama.2017.12126
doi: 10.1001/jama.2017.12126 pubmed: 29049590
Majnik M, Bosnić Z (2013) ROC analysis of classifiers in machine learning: A survey. Intell Data Anal 17:531–558. https://doi.org/10.3233/IDA-130592
doi: 10.3233/IDA-130592

Auteurs

Jonas Henn (J)

Department of General, Visceral, Thoracic and Vascular Surgery, University of Bonn, Bonn, Germany.

Andreas Buness (A)

Institute for Medical Biometry, Informatics and Epidemiology, University of Bonn, Bonn, Germany.
Institute for Genomic Statistics and Bioinformatics, University of Bonn, Bonn, Germany.

Matthias Schmid (M)

Institute for Medical Biometry, Informatics and Epidemiology, University of Bonn, Bonn, Germany.

Jörg C Kalff (JC)

Department of General, Visceral, Thoracic and Vascular Surgery, University of Bonn, Bonn, Germany.

Hanno Matthaei (H)

Department of General, Visceral, Thoracic and Vascular Surgery, University of Bonn, Bonn, Germany. hanno.matthaei@ukbonn.de.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH