{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T06:05:27Z","timestamp":1790661927458,"version":"4.1.0"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Postoperative inflammatory\u2013nutritional deterioration may adversely affect recovery after colorectal cancer surgery. This study aimed to develop and internally validate an interpretable machine learning model for preoperative prediction of postoperative modified Glasgow Prognostic Score (mGPS)\u2009=\u20092.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This single-centre retrospective study included consecutive patients who underwent elective radical resection for colorectal cancer between 2020 and 2025. The cohort was divided into training and internal validation sets using stratified sampling. Recursive feature elimination identified eight predictors: age, prealbumin, albumin, cholinesterase, lymphocyte percentage, platelet count, fibrinogen and serum calcium. Eight conventional machine learning algorithms, TabICLv2 and SuperLearner ensembles were evaluated using discrimination, calibration and decision curve analyses. SHapley Additive exPlanations were used for model interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 1196 patients, 507 (42.4%) developed postoperative mGPS=2. In the internal validation cohort, TabICLv2 achieved an area under the receiver operating characteristic curve of 0.753 (95% confidence interval, 0.701\u20130.804) and a Brier score of 0.197. SuperLearner-W and SuperLearner-SR showed comparable discrimination, with areas under the curve of 0.752 and 0.751, respectively. Lymphocyte percentage, platelet count and fibrinogen were the leading contributors to model predictions. Learning-curve analysis revealed suboptimal convergence behaviour, with relatively flat cross-validation trajectories and persistent separation from training performance across increasing training fractions. A web-based research prototype was developed to provide individualised risk estimates, patient-level feature attribution and an applicability-domain assessment indicating the level of support from the model-development data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An interpretable model based on routinely available preoperative variables provided moderate discrimination for postoperative inflammatory\u2013nutritional deterioration after colorectal cancer surgery. The suboptimal learning-curve convergence indicates that the model is not suitable for clinical deployment without further development and independent external validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1938414","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T05:50:13Z","timestamp":1790661013000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Preoperative risk stratification for postoperative inflammatory\u2013nutritional deterioration after colorectal cancer surgery: an interpretable machine learning study"],"prefix":"10.3389","volume":"13","author":[{"given":"Yinchao","family":"Zhang","sequence":"first","affiliation":[{"name":"The Affiliated Wuxi People\u2019s Hospital of Nanjing Medical University, Wuxi People\u2019s Hospital, Wuxi Medical Center, Nanjing Medical University","place":["Wuxi, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingkun","family":"Hu","sequence":"additional","affiliation":[{"name":"The Affiliated Wuxi People\u2019s Hospital of Nanjing Medical University, Wuxi People\u2019s Hospital, Wuxi Medical Center, Nanjing Medical University","place":["Wuxi, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinke","family":"Cao","sequence":"additional","affiliation":[{"name":"The Affiliated Wuxi People\u2019s Hospital of Nanjing Medical University, Wuxi People\u2019s Hospital, Wuxi Medical Center, Nanjing Medical University","place":["Wuxi, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinquan","family":"Zan","sequence":"additional","affiliation":[{"name":"The Affiliated Wuxi People\u2019s Hospital of Nanjing Medical University, Wuxi People\u2019s Hospital, Wuxi Medical Center, Nanjing Medical University","place":["Wuxi, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Tian","sequence":"additional","affiliation":[{"name":"The Affiliated Wuxi People\u2019s Hospital of Nanjing Medical University, Wuxi People\u2019s Hospital, Wuxi Medical Center, Nanjing Medical University","place":["Wuxi, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Shen","sequence":"additional","affiliation":[{"name":"The Affiliated Wuxi People\u2019s Hospital of Nanjing Medical University, Wuxi People\u2019s Hospital, Wuxi Medical Center, Nanjing Medical University","place":["Wuxi, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"B1","first-page":"45","article-title":"Dynamic of IL-6 and IL-8 concentrations in patients after surgery treated with total parenteral nutrition","volume":"12","author":"S\u0142otwi\u0144ski","year":"2002","journal-title":"Pol Merkur Lekarski"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1007\/s11605-009-1034-0","article-title":"The relationship between the local and systemic inflammatory responses and survival in patients undergoing curative surgery for colon and rectal cancers","volume":"13","author":"Roxburgh","year":"2009","journal-title":"J Gastrointest Surg"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2832","DOI":"10.1245\/s10434-016-5204-5","article-title":"Postoperative systemic inflammatory response, complication severity, and survival following surgery for colorectal cancer","volume":"23","author":"McSorley","year":"2016","journal-title":"Ann Surg Oncol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.amjsurg.2007.12.052","article-title":"Relationship between emergency presentation, systemic inflammatory response, and cancer-specific survival in patients undergoing potentially curative surgery for colon cancer","volume":"197","author":"Crozier","year":"2009","journal-title":"Am J Surg"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1038\/sj.bjc.6604997","article-title":"Preoperative systemic inflammation predicts postoperative infectious complications in patients undergoing curative resection for colorectal cancer","volume":"100","author":"Moyes","year":"2009","journal-title":"Br J Cancer"},{"key":"B6","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1272\/jnms.84.224","article-title":"Worse preoperative status based on inflammation and host immunity is a risk factor for surgical site infections in colorectal cancer surgery","volume":"84","author":"Sagawa","year":"2017","journal-title":"J Nippon Med Sch"},{"key":"B7","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1007\/s00384-019-03491-z","article-title":"The C-reactive protein to albumin ratio predicts postoperative complications in oldest-old patients with colorectal cancer","volume":"35","author":"Hashimoto","year":"2020","journal-title":"Int J Colorectal Dis"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2387","DOI":"10.3390\/diagnostics15182387","article-title":"Colorectal cancer\u2014one disease, two fires: distinct inflammatory landscapes in colon and rectal cancer","volume":"15","author":"Feier","year":"2025","journal-title":"Diagnostics"},{"key":"B9","doi-asserted-by":"publisher","first-page":"65","DOI":"10.4143\/crt.2014.46.1.65","article-title":"Clinical implications of systemic inflammatory response markers as independent prognostic factors in colorectal cancer patients","volume":"46","author":"Paik","year":"2014","journal-title":"Cancer Res Treat"},{"key":"B10","doi-asserted-by":"publisher","first-page":"8583","DOI":"10.3748\/wjg.v20.i26.8583","article-title":"Prognostic significance of preoperative fibrinogen in patients with colon cancer","volume":"20","author":"Sun","year":"2014","journal-title":"World J Gastroenterol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"e0142159","DOI":"10.1371\/journal.pone.0142159","article-title":"The neutrophil-platelet score predicts survival in primary operable colorectal cancer and a variety of common cancers","volume":"10","author":"Watt","year":"2015","journal-title":"PLoS One"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1828","DOI":"10.1038\/s41416-021-01308-x","article-title":"The prognostic value of combined measures of the systemic inflammatory response in patients with colon cancer: an analysis of 1700 patients","volume":"124","author":"Golder","year":"2021","journal-title":"Br J Cancer"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1580","DOI":"10.3390\/medicina61091580","article-title":"Comparative prognostic role of PLR and NLR in colon cancer: a retrospective analysis of preoperative inflammatory markers","volume":"61","author":"Negrut","year":"2025","journal-title":"Medicina (B Aires)"},{"key":"B14","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s13304-017-0503-3","article-title":"Preoperative platelet-lymphocyte ratio is an independent factor of poor prognosis after curative surgery for colon cancer","volume":"70","author":"Bailon-Cuadrado","year":"2018","journal-title":"Updates Surg"},{"key":"B15","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1186\/s12967-025-06663-4","article-title":"Oncoe25: an AI model for predicting postoperative prognosis in early-onset stage I\u2013III colon and rectal cancer\u2014a population-based study using SEER with dual-centre cohort validation","volume":"23","author":"Yuan","year":"2025","journal-title":"J Transl Med"},{"key":"B16","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1186\/s12893-024-02543-8","article-title":"Machine learning model predicting factors for incisional infection following right hemicolectomy for colon cancer","volume":"24","author":"Li","year":"2024","journal-title":"BMC Surg"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1782613","DOI":"10.3389\/fonc.2026.1782613","article-title":"Multicentre machine learning study for long-term prediction of acute kidney injury after complete mesocolic excision: integrating inflammatory biomarkers and transfusion-related risk factors","volume":"16","author":"He","year":"2026","journal-title":"Front Oncol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1007\/s12672-024-01327-z","article-title":"Utilising machine learning algorithms for predicting risk factors for bone metastasis from right-sided colon carcinoma after complete mesocolic excision: a 10-year retrospective multicentre study","volume":"15","author":"Liu","year":"2024","journal-title":"Discov Oncol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s10151-025-03165-9","article-title":"Deep learning neural network prediction of postoperative complications in patients undergoing laparoscopic right hemicolectomy with or without CME and CVL for colon cancer: insights from SICE (societ\u00e0 italiana di chirurgia endoscopica) CoDIG data","volume":"29","author":"Anania","year":"2025","journal-title":"Techniques Coloproctology"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0000000000006847","article-title":"Super learner enhances postoperative complication prediction in colorectal surgery","author":"Violante","year":"2025","journal-title":"Annals Surgery"},{"key":"B21","doi-asserted-by":"publisher","first-page":"42","DOI":"10.3390\/surgeries7020042","article-title":"Stratified procedural risk assessment in colorectal surgery: a comparative analysis of statistical and machine learning approaches using combined surgical approach and operative duration categories","volume":"7","author":"Elengickal","year":"2026","journal-title":"Surgeries"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1845236","DOI":"10.3389\/fonc.2026.1845236","article-title":"Machine learning-based multicenter prediction of postoperative sepsis in emergency colon cancer: role of surgical approach and inflammatory markers","volume":"16","author":"Du","year":"2026","journal-title":"Frontiers Oncology"},{"key":"B23","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"Br Med J"},{"key":"B24","volume-title":"TabICLv2: A Better, Faster, Scalable, and Open tabular Foundation model","author":"Qu","year":"2026"},{"key":"B25","doi-asserted-by":"publisher","first-page":"938","DOI":"10.1245\/s10434-014-4065-z","article-title":"The impact of open versus laparoscopic resection for colon cancer on C-reactive protein concentrations as a predictor of postoperative infective complications","volume":"22","author":"Ramanathan","year":"2015","journal-title":"Ann Surg Oncol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"2577","DOI":"10.1007\/s00464-024-10749-3","article-title":"Robotic-assisted surgery for left-sided colon and rectal resections is associated with reduction in the postoperative surgical stress response and improved short-term outcomes: a cohort study","volume":"38","author":"Ingham","year":"2024","journal-title":"Surg Endosc"},{"key":"B27","doi-asserted-by":"publisher","first-page":"e0228580","DOI":"10.1371\/journal.pone.0228580","article-title":"The relationship between anaesthetic technique, clinicopathological characteristics and the magnitude of the postoperative systemic inflammatory response in patients undergoing elective surgery for colon cancer","volume":"15","author":"Alhayyan","year":"2020","journal-title":"PLoS One"},{"key":"B28","doi-asserted-by":"publisher","first-page":"576360","DOI":"10.2147\/CIA.S576360","article-title":"Bidirectional relationship between systemic immune-inflammation index and postoperative pneumonia in elderly patients undergoing colorectal cancer surgery: a retrospective cohort study","volume":"21","author":"Wu","year":"2026","journal-title":"Clin Interv Aging"},{"key":"B29","first-page":"1243","article-title":"Significance of perioperative neutrophil lymphocyte ratio (NLR) in gastric cancer and colon cancer","volume":"43","author":"Sagawa","year":"2016","journal-title":"Gan to Kagaku Ryoho"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2946","DOI":"10.7150\/jca.114813","article-title":"The predictive value of the cholesterol-to-natural killer cell ratio in colorectal cancer","volume":"16","author":"Liu","year":"2025","journal-title":"J Cancer"},{"key":"B31","doi-asserted-by":"publisher","first-page":"2875","DOI":"10.1080\/01635581.2022.2042570","article-title":"Novel and simple nomograms using inflammation and nutritional biomarkers for stage II\u2013III colon cancer, taking \u201ctime after curative surgery\u201d into consideration","volume":"74","author":"Mazaki","year":"2022","journal-title":"Nutr Cancer"},{"key":"B32","doi-asserted-by":"publisher","first-page":"28033","DOI":"10.1038\/s41598-024-78783-8","article-title":"Development and validation of a dynamic nomogram for individualized prediction of survival in patients with colon cancer","volume":"14","author":"Sun","year":"2024","journal-title":"Sci Rep"},{"key":"B33","doi-asserted-by":"publisher","first-page":"5985","DOI":"10.3390\/jcm14175985","article-title":"Decoding the effect of frailty vs. Physiologic age in octogenarian and nonagenarian colectomy outcomes for colon cancer","volume":"14","author":"Drohat","year":"2025","journal-title":"J Clin Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"e70438","DOI":"10.1111\/codi.70438","article-title":"Mild to moderate frailty among older adults does not affect long-term quality of life or functional outcomes after colon cancer surgery","volume":"28","author":"Normann","year":"2026","journal-title":"Colorectal Dis"},{"key":"B35","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1186\/s12876-025-04511-9","article-title":"Interpretable machine learning model for predicting 5-year postoperative recurrence risk in patients with stage III colon cancer using preoperative laboratory tests: a two-centre study","volume":"26","author":"Wei","year":"2026","journal-title":"BMC Gastroenterol"},{"key":"B36","doi-asserted-by":"publisher","first-page":"199","DOI":"10.21037\/tcr-2025-1-2893","article-title":"Triglyceride-to-glucose index and lymphocyte-to-monocyte ratio enhance prognostic accuracy for colorectal cancer patients: a multicentre machine learning cohort study","volume":"15","author":"Liang","year":"2026","journal-title":"Transl Cancer Res"},{"key":"B37","doi-asserted-by":"publisher","first-page":"25441","DOI":"10.1038\/s41598-025-11726-z","article-title":"Using machine learning algorithms to predict risk factors of heart failure after complete mesocolic excision in colorectal cancer patients","volume":"15","author":"Liu","year":"2025","journal-title":"Sci Rep"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1753529","DOI":"10.3389\/fdgth.2026.1753529","article-title":"Development and interpretable machine learning models for classification of pancreatic pseudocyst risk in acute pancreatitis","volume":"8","author":"Feng","year":"2026","journal-title":"Front Digit Health"},{"key":"B39","doi-asserted-by":"publisher","first-page":"68","DOI":"10.21037\/tp-2025-1-867","article-title":"Transfer learning prediction of surgical necrotizing enterocolitis in preterm infants without pneumoperitoneum on abdominal x-ray","volume":"15","author":"Sun","year":"2026","journal-title":"Transl Pediatr"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1780056","DOI":"10.3389\/fpsyt.2026.1780056","article-title":"Machine learning-based predictive model for postoperative delirium of elderly patients with coronary heart disease undergoing non-cardiac surgery: a retrospective cohort study","volume":"17","author":"Kong","year":"2026","journal-title":"Front Psychiatry"},{"key":"B41","doi-asserted-by":"publisher","first-page":"318","DOI":"10.21037\/qims-2025-1-2525","article-title":"An interpretable weighted ensemble based on routinely collected clinical data for the accurate prediction of axillary lymph node metastasis","volume":"16","author":"Wang","year":"2026","journal-title":"Quant Imaging Med Surg"},{"key":"B42","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s11701-025-02465-4","article-title":"Establishment of a machine learning-based predictive model with dual-centre external validation: investigating the role of robotic surgery in preventing delayed gastric emptying for right-sided colon cancer","volume":"19","author":"Fan","year":"2025","journal-title":"J Robot Surg"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1938414\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T05:50:14Z","timestamp":1790661014000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1938414\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":42,"alternative-id":["10.3389\/fmed.2026.1938414"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1938414","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]},"article-number":"1938414"}}