{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T09:00:04Z","timestamp":1790845204760,"version":"4.1.0"},"reference-count":23,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: The aim of the present study was to identify machine learning (ML)-driven risk constellations to predict specific postoperative outcomes and recovery targets to support the development of targeted interventions, optimized to individual risk profiles. Methods: This retrospective institutional cohort study included consecutive patients who underwent elective colorectal surgery over an 11-year study period focusing on baseline patient characteristics, intraoperative details, and postoperative complications. Five supervised classification algorithms for specific complications and recovery targets were used: logistic regression, support vector machine (SVM), XGBoost, decision tree, and gradient boosting. The dataset was randomly divided into training (80%) and testing (20%) subsets. Model performance was assessed using F1-score for classification task, and for each prediction target; the best-performing model and hyperparameter combination were selected based on validation results. To interpret the contribution of individual features to model predictions, SHAP (Shapley Additive exPlanations) analysis was applied to the best-performing model identified for each prediction target. Results: Logistic regression was the best-performing model for six of the seven postoperative outcomes, whereas SVM performed best for postoperative ileus, indicating that optimal model selection was outcome-specific. Overall, however, none of the tested models clearly outperformed the others in their predictive potential. The discriminative power of the models, as measured by ROC-AUC (receiver operating characteristics\u2013area under the curve), was consistently higher than the baseline of 0.50, peaking at 0.93 for renal dysfunction. In terms of classification accuracy, the prediction of postoperative ileus was the most robust, yielding an F1-score of 0.87. For mobilization, the model showed balanced performance across F1-score (0.72), precision (0.74), and recall (0.71). Given the limited performance across all selected models, SHAP analysis was used to improve the interpretability of the predictions to better understand the contributions of each clinical variable. Conclusions: Complex models in the setting of a structured perioperative dataset only slightly outperform simpler approaches, highlighting the importance of data quality and feature richness rather than just increased model complexity. Future work on improving ML-based risk prediction strategies should thus ensure data quality and focus on integrating dynamic perioperative and postoperative measurements, exploring more flexible modeling frameworks, and validating model performance in larger external cohorts.<\/jats:p>","DOI":"10.3390\/diagnostics16193190","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T08:19:08Z","timestamp":1790842748000},"page":"3190","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning for Risk Prediction in Colorectal Surgery\u2014Game Changer or Unnecessary? An Institutional Pilot Study"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0248-8604","authenticated-orcid":false,"given":"He Ayu","family":"Xu","sequence":"first","affiliation":[{"name":"Biomedical Data Science Center, Lausanne University Hospital CHUV, University of Lausanne (UNIL), 1011 Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"}]},{"given":"Philip","family":"Deslarzes","sequence":"additional","affiliation":[{"name":"Department of Visceral Surgery, Lausanne University Hospital CHUV, University of Lausanne (UNIL), 1011 Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2052-6133","authenticated-orcid":false,"given":"Jean Louis","family":"Raisaro","sequence":"additional","affiliation":[{"name":"Biomedical Data Science Center, Lausanne University Hospital CHUV, University of Lausanne (UNIL), 1011 Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5595-4114","authenticated-orcid":false,"given":"Dieter","family":"Hahnloser","sequence":"additional","affiliation":[{"name":"Department of Visceral Surgery, Lausanne University Hospital CHUV, University of Lausanne (UNIL), 1011 Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4521-8279","authenticated-orcid":false,"given":"Martin","family":"H\u00fcbner","sequence":"additional","affiliation":[{"name":"Department of Visceral Surgery, Lausanne University Hospital CHUV, University of Lausanne (UNIL), 1011 Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9884-2879","authenticated-orcid":false,"given":"Fabian","family":"Grass","sequence":"additional","affiliation":[{"name":"Department of Visceral Surgery, Lausanne University Hospital CHUV, University of Lausanne (UNIL), 1011 Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3000","DOI":"10.1007\/s00268-023-07199-8","article-title":"Predicting Postoperative Complications in Patients Undergoing Colorectal Surgery with an Enhanced Recovery Pathway","volume":"47","author":"Ren","year":"2023","journal-title":"World J. Surg."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3100","DOI":"10.1007\/s00268-022-06728-1","article-title":"Machine Learning Algorithms for Predicting Surgical Outcomes after Colorectal Surgery: A Systematic Review","volume":"46","author":"Bektas","year":"2022","journal-title":"World J. Surg."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Deslarzes, P., Xu, H.A., Raisaro, J.L., Hubner, M., and Grass, F. (2025). Unsupervised Machine Learning to Identify Patient Clusters and Tailor Perioperative Care in Colorectal Surgery. Diagnostics, 15.","DOI":"10.3390\/diagnostics15172124"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1108","DOI":"10.1002\/bjs.9184","article-title":"Cost-effectiveness of the implementation of an enhanced recovery protocol for colorectal surgery","volume":"100","author":"Roulin","year":"2013","journal-title":"Br. J. Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1007\/s00268-018-4844-y","article-title":"Guidelines for Perioperative Care in Elective Colorectal Surgery: Enhanced Recovery After Surgery (ERAS((R))) Society Recommendations: 2018","volume":"43","author":"Gustafsson","year":"2019","journal-title":"World J. Surg."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1007\/s00384-017-2789-5","article-title":"Postoperative ileus in an enhanced recovery pathway-a retrospective cohort study","volume":"32","author":"Grass","year":"2017","journal-title":"Int. J. Color. Dis."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1097\/01.sla.0000133083.54934.ae","article-title":"Classification of surgical complications: A new proposal with evaluation in a cohort of 6336 patients and results of a survey","volume":"240","author":"Dindo","year":"2004","journal-title":"Ann. Surg."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2708","DOI":"10.1007\/s00268-018-4699-2","article-title":"Respiratory Complications After Colorectal Surgery: Avoidable or Fate?","volume":"42","author":"Jurt","year":"2018","journal-title":"World J. Surg."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1007\/s00268-019-04923-1","article-title":"Early Acute Kidney Injury Within an Established Enhanced Recovery Pathway: Uncommon and Transitory","volume":"43","author":"Grass","year":"2019","journal-title":"World J. Surg."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"940","DOI":"10.1007\/s00268-020-05926-z","article-title":"Swiss Validation of the Enhanced Recovery After Surgery (ERAS) Database","volume":"45","author":"Pache","year":"2021","journal-title":"World J. Surg."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"373","DOI":"10.5662\/wjm.v13.i5.373","article-title":"Challenges and limitations of synthetic minority oversampling techniques in machine learning","volume":"13","author":"Alkhawaldeh","year":"2023","journal-title":"World J. Methodol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"6067","DOI":"10.3758\/s13428-023-02335-7","article-title":"SHAP value-based ERP analysis (SHERPA): Increasing the sensitivity of EEG signals with explainable AI methods","volume":"56","author":"Sylvester","year":"2024","journal-title":"Behav. Res. Methods"},{"key":"ref_13","unstructured":"Iea, G. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, Curran Associates Inc."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1002\/bjs.1800780327","article-title":"POSSUM: A scoring system for surgical audit","volume":"78","author":"Copeland","year":"1991","journal-title":"Br. J. Surg."},{"key":"ref_15","unstructured":"Hendrix, J.M., and Garmon, E.H. (2026). American Society of Anesthesiologists Physical Status Classification System, StatPearls."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1213\/ANE.0000000000003718","article-title":"Use of the American College of Surgeons National Surgical Quality Improvement Program Surgical Risk Calculator During Preoperative Risk Discussion: The Patient Perspective","volume":"128","author":"Raymond","year":"2019","journal-title":"Anesth. Analg."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"8550","DOI":"10.1097\/JS9.0000000000003067","article-title":"Systematic review and meta-analysis of the role of machine learning in predicting postoperative complications following colorectal surgery: How far has machine learning come?","volume":"111","author":"Mohamedahmed","year":"2025","journal-title":"Int. J. Surg."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1001\/jamasurg.2019.4917","article-title":"Artificial Intelligence and Surgical Decision-making","volume":"155","author":"Loftus","year":"2020","journal-title":"JAMA Surg."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/j.surg.2020.01.019","article-title":"Challenges to accomplish stringent fluid management standards 7 years after enhanced recovery after surgery implementation-The surgeon\u2019s perspective","volume":"168","author":"Grass","year":"2020","journal-title":"Surgery"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1097\/SLA.0000000000005384","article-title":"Intraoperative Fluid Management a Modifiable Risk Factor for Surgical Quality\u2014Improving Standardized Practice","volume":"275","author":"Grass","year":"2022","journal-title":"Ann. Surg."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1097\/DCR.0000000000001522","article-title":"Potential Association Between Perioperative Fluid Management and Occurrence of Postoperative Ileus","volume":"63","author":"Grass","year":"2020","journal-title":"Dis. Colon Rectum"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1002\/bjs.11399","article-title":"Identification of patients eligible for discharge within 48 h of colorectal resection","volume":"107","author":"Grass","year":"2020","journal-title":"Br. J. Surg."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1097\/DCR.0000000000002559","article-title":"Improved Prediction of Surgical-Site Infection After Colorectal Surgery Using Machine Learning","volume":"66","author":"Chen","year":"2023","journal-title":"Dis. Colon Rectum"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/19\/3190\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T08:36:10Z","timestamp":1790843770000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/19\/3190"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":23,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["diagnostics16193190"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16193190","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]}}}