{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T15:00:12Z","timestamp":1789398012380,"version":"build-2803163510"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science and Technology Planning Project of Jiangxi Provincial Administration of Traditional Chinese Medicine","award":["2025021340"],"award-info":[{"award-number":["2025021340"]}]},{"name":"Science and Technology Planning Project of Jiangxi Provincial Health Commission","award":["202510509"],"award-info":[{"award-number":["202510509"]}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Nutr."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early recurrence (ER) in colorectal cancer (CRC) leads to dismal outcomes. Current pTNM staging fails to capture the host\u2019s systemic pathophysiological status. We developed an interpretable machine learning (ML) model based on preoperative CT body composition radiomics to predict ER in CRC.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      This multicenter study enrolled 917 patients who underwent radical resection across three independent institutions, and the cohort was partitioned into a training set (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f548) and two external test sets (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f263 and\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f106). We extracted 1,896 radiomic features from four body composition compartments: skeletal muscle (SM), subcutaneous adipose tissue (SAT), intermuscular adipose tissue (IMAT), and visceral adipose tissue (VAT) at the L3 level on CT. Following feature selection using LASSO and Boruta algorithms, eight ML algorithms were evaluated. The optimal classifier was integrated with clinical risk factors. SHAP was utilized for model interpretability.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      An 11-feature radiomics signature was identified. The Random Forest model demonstrated optimal generalization, yielding AUCs of 0.807, 0.776, and 0.750 in the training and two test sets, respectively. SHAP analysis revealed that IMAT (46.1%) and SM (42.9%) features were primary drivers, and increased SM textural uniformity may reflect adverse muscle quality and possible myosteatosis-related tissue alterations. The individualized radiomics risk score effectively stratified patients, demonstrating significantly divergent recurrence-free and overall survival across all cohorts (\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.05). Decision curve analysis confirmed superior net clinical benefit over pTNM staging.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This interpretable ML model may improve ER risk stratification in CRC and provide a quantitative tool for individualized postoperative surveillance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnut.2026.1843436","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T04:34:12Z","timestamp":1780547652000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Machine learning based on body composition radiomics for predicting early recurrence in colorectal cancer: a multicenter study"],"prefix":"10.3389","volume":"13","author":[{"given":"Yongjie","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Radiology, Jiangxi Cancer Hospital & Institute, Jiangxi Clinical Research Center for Cancer, The Second Affiliated Hospital of Nanchang Medical College","place":["Nanchang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miaoping","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People\u2019s Hospital","place":["Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongming","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University","place":["Nanchang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University","place":["Nanchang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengfa","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Radiology, Ningdu County Hospital of Traditional Chinese Medicine","place":["Ganzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anni","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Jiangxi Cancer Hospital & Institute, Jiangxi Clinical Research Center for Cancer, The Second Affiliated Hospital of Nanchang Medical College","place":["Nanchang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sijia","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Radiology, Jiangxi Cancer Hospital & Institute, Jiangxi Clinical Research Center for Cancer, The Second Affiliated Hospital of Nanchang Medical College","place":["Nanchang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Jiangxi Cancer Hospital & Institute, Jiangxi Clinical Research Center for Cancer, The Second Affiliated Hospital of Nanchang Medical College","place":["Nanchang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linhua","family":"Zhong","sequence":"additional","affiliation":[{"name":"Department of Radiology, Jiangxi Cancer Hospital & Institute, Jiangxi Clinical Research Center for Cancer, The Second Affiliated Hospital of Nanchang Medical College","place":["Nanchang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"110482","DOI":"10.1016\/j.ejso.2025.110482","article-title":"CT-based radiomics deep learning signatures for noninvasive prediction of early recurrence after radical surgery in locally advanced colorectal cancer: a multicenter study","volume":"51","author":"Zhou","year":"2025","journal-title":"Eur J Surg Oncol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1038\/s41568-020-0285-7","article-title":"The immune contexture and Immunoscore in cancer prognosis and therapeutic efficacy","volume":"20","author":"Bruni","year":"2020","journal-title":"Nat Rev Cancer"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"2128","DOI":"10.1016\/S0140-6736(18)30789-X","article-title":"International validation of the consensus Immunoscore for the classification of colon cancer: a prognostic and accuracy study","volume":"391","author":"Pages","year":"2018","journal-title":"Lancet"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1038\/s41568-021-00347-z","article-title":"Systemic immunity in cancer","volume":"21","author":"Hiam-Galvez","year":"2021","journal-title":"Nat Rev Cancer"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"671","DOI":"10.2214\/AJR.22.27749","article-title":"CT-derived body composition assessment as a prognostic tool in oncologic patients: from opportunistic research to artificial intelligence-based clinical implementation","volume":"219","author":"Bates","year":"2022","journal-title":"Am J Roentgenol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1038\/s41574-018-0126-x","article-title":"The obese adipose tissue microenvironment in cancer development and progression","volume":"15","author":"Quail","year":"2019","journal-title":"Nat Rev Endocrinol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"102839","DOI":"10.1016\/j.critrevonc.2019.102839","article-title":"Myosteatosis and prognosis in cancer: systematic review and meta-analysis","volume":"145","author":"Aleixo","year":"2020","journal-title":"Crit Rev Oncol Hematol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"108874","DOI":"10.1016\/j.cmpb.2025.108874","article-title":"Interpretable machine learning models based on body composition and inflammatory nutritional index (BCINI) to predict early postoperative recurrence of colorectal cancer: multi-center study","volume":"269","author":"Zhou","year":"2025","journal-title":"Comput Methods Prog Biomed"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"8046","DOI":"10.21037\/jtd-2025-1211","article-title":"CT-based body composition and inflammatory nutritional biomarker nomogram for predicting early postoperative recurrence of non-small cell lung cancer: a multicenter study","volume":"17","author":"Zou","year":"2025","journal-title":"J Thorac Dis"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s00384-025-05061-y","article-title":"Prognostic impact of myosteatosis on postoperative outcomes and survival in colorectal cancer: a systematic review","volume":"41","author":"Han","year":"2026","journal-title":"Int J Color Dis"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s00259-025-07538-y","article-title":"Body composition radiomics combined with machine learning for early recurrence prediction in intrahepatic cholangiocarcinoma following curative surgery: a multi-center study","volume":"53","author":"Gan","year":"2026","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1016\/j.annonc.2025.05.537","article-title":"Enhanced risk stratification for stage II colorectal cancer using deep learning-based CT classifier and pathological markers to optimize adjuvant therapy decision","volume":"36","author":"Huang","year":"2025","journal-title":"Ann Oncol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1835","DOI":"10.3390\/diagnostics14161835","article-title":"Enhancing the clinical utility of Radiomics: addressing the challenges of repeatability and reproducibility in CT and MRI","volume":"14","author":"Teng","year":"2024","journal-title":"Diagnostics"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","article-title":"Radiomics: the bridge between medical imaging and personalized medicine","volume":"14","author":"Lambin","year":"2017","journal-title":"Nat Rev Clin Oncol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1186\/s13244-025-01952-4","article-title":"CT-based radiomics deep learning signatures for non-invasive prediction of metastatic potential in pheochromocytoma and paraganglioma: a multicohort study","volume":"16","author":"Zhou","year":"2025","journal-title":"Insights Imaging"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"2301","DOI":"10.1002\/jcsm.13315","article-title":"Prognostic role of radiomics-based body composition analysis for the 1-year survival for hepatocellular carcinoma patients","volume":"14","author":"Saalfeld","year":"2023","journal-title":"J Cachexia Sarcopenia Muscle"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1062937","DOI":"10.3389\/fonc.2023.1062937","article-title":"Identifying radiomics signatures in body composition imaging for the prediction of outcome following pancreatic cancer resection","volume":"13","author":"van der Kroft","year":"2023","journal-title":"Front Oncol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"2333","DOI":"10.1152\/japplphysiol.00744.2004","article-title":"Total body skeletal muscle and adipose tissue volumes: estimation from a single abdominal cross-sectional image","volume":"97","author":"Shen","year":"2004","journal-title":"J Appl Physiol"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"van Griethuysen","year":"2017","journal-title":"Cancer Res"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"m441","DOI":"10.1136\/bmj.m441","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e1003620","DOI":"10.1371\/journal.pmed.1003620","article-title":"Circulating tumor DNA dynamics and recurrence risk in patients undergoing curative intent resection of colorectal cancer liver metastases: a prospective cohort study","volume":"18","author":"Tie","year":"2021","journal-title":"PLoS Med"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"2261","DOI":"10.1056\/NEJMoa2200075","article-title":"Circulating tumor DNA analysis guiding adjuvant therapy in stage II Colon Cancer","volume":"386","author":"Tie","year":"2022","journal-title":"N Engl J Med"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1001\/jamaoncol.2018.0137","article-title":"Association of muscle and adiposity measured by computed tomography with survival in patients with nonmetastatic breast cancer","volume":"4","author":"Caan","year":"2018","journal-title":"JAMA Oncol"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1007\/s00384-021-03839-4","article-title":"Sarcopenia predicts worse postoperative outcomes and decreased survival rates in patients with colorectal cancer: a systematic review and meta-analysis","volume":"36","author":"Trejo-Avila","year":"2021","journal-title":"Int J Color Dis"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1002\/cam4.4448","article-title":"Sarcopenia predicts an adverse prognosis in patients with combined hepatocellular carcinoma and cholangiocarcinoma after surgery","volume":"11","author":"Hou","year":"2022","journal-title":"Cancer Med"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"371","DOI":"10.2214\/AJR.22.28043","article-title":"Utility of fully automated body composition measures on pretreatment abdominal CT for predicting survival in patients with colorectal Cancer","volume":"220","author":"Lee","year":"2023","journal-title":"Am J Roentgenol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"2859","DOI":"10.1016\/j.acra.2024.01.008","article-title":"CT-based Radiomics analysis of different machine learning models for discriminating the risk stratification of Pheochromocytoma and Paraganglioma: a multicenter study","volume":"31","author":"Zhou","year":"2024","journal-title":"Acad Radiol"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1288","DOI":"10.1245\/s10434-025-18815-3","article-title":"Development and validation of time-to-event machine learning models for predicting disease-free survival in patients with locally advanced colorectal Cancer: a multicenter cohort study","volume":"33","author":"Zhou","year":"2026","journal-title":"Ann Surg Oncol"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1016\/j.ebiom.2019.10.034","article-title":"Skeletal muscle as potential central link between sarcopenia and immune senescence","volume":"49","author":"Nelke","year":"2019","journal-title":"EBioMedicine"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"102538","DOI":"10.1016\/j.redox.2022.102538","article-title":"Multi-omics profiling reveals Chitinase-3-like protein 1 as a key mediator in the crosstalk between sarcopenia and liver cancer","volume":"58","author":"Lu","year":"2022","journal-title":"Redox Biol"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1038\/s41574-022-00784-2","article-title":"Intermuscular adipose tissue in metabolic disease","volume":"19","author":"Goodpaster","year":"2023","journal-title":"Nat Rev Endocrinol"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s41574-023-00932-2","article-title":"Emerging mechanisms of obesity-associated immune dysfunction","volume":"20","author":"Shaikh","year":"2024","journal-title":"Nat Rev Endocrinol"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1172\/JCI88883","article-title":"The ominous triad of adipose tissue dysfunction: inflammation, fibrosis, and impaired angiogenesis","volume":"127","author":"Crewe","year":"2017","journal-title":"J Clin Invest"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/j.cell.2021.12.016","article-title":"Adipose-tissue plasticity in health and disease","volume":"185","author":"Sakers","year":"2022","journal-title":"Cell"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"CD13259","DOI":"10.1002\/14651858.CD013259.pub3","article-title":"Prehabilitation versus no prehabilitation to improve functional capacity, reduce postoperative complications and improve quality of life in colorectal cancer surgery","volume":"5","author":"Molenaar","year":"2023","journal-title":"Cochrane Database Syst Rev"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.3390\/nu17091509","article-title":"Feasibility of a pre-operative Morphofunctional assessment and the effect of an intervention program with Oral nutritional supplements and physical exercise","volume":"17","author":"Mudarra-Garcia","year":"2025","journal-title":"Nutrients"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"3049","DOI":"10.1016\/j.clnu.2020.01.008","article-title":"Automated body composition analysis of clinically acquired computed tomography scans using neural networks","volume":"39","author":"Paris","year":"2020","journal-title":"Clin Nutr"}],"container-title":["Frontiers in Nutrition"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1843436\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T04:34:21Z","timestamp":1780547661000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1843436\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,4]]},"references-count":38,"alternative-id":["10.3389\/fnut.2026.1843436"],"URL":"https:\/\/doi.org\/10.3389\/fnut.2026.1843436","relation":{},"ISSN":["2296-861X"],"issn-type":[{"value":"2296-861X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,4]]},"article-number":"1843436"}}