{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T06:13:11Z","timestamp":1779343991468,"version":"3.51.4"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"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. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Pathological upgrading in colorectal polyps, which occurs when resection specimens have a higher histological grade than preoperative biopsies, can lead to an underestimation of the severity of the disease and suboptimal treatment. Given the substantial global burden of colorectal cancer (CRC), improving preoperative risk stratification of colorectal polyps is essential for optimizing screening strategies and resource allocation in CRC prevention.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Between December 2019 and December 2024, 593 patients with colorectal polyps were included in this retrospective study, undergoing endoscopic biopsy and subsequent complete resection. Clinical and endoscopic variables were gathered, and feature selection was conducted using LASSO regression and the Boruta algorithm. Repeated ten-fold cross-validation was used to develop and evaluate six machine learning models: RF, CART, NNet, LR, GBM, and XGBoost. AUC, accuracy, sensitivity, specificity, MCC, and Brier score were used to assess the model's performance. A web-based calculator was developed to aid in clinical implementation, using SHapley Additive exPlanations (SHAP) to interpret the optimal model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Among the 593 patients, 150 (25.3%) experienced pathological upgrading. Five key predictors were identified: maximum tumor diameter, surface color, erosion, villous structure, and lesion location. With an AUC of 0.890 in the training set and 0.863 in the test set, the XGBoost model exhibited superior performance, along with strong calibration and discrimination. SHAP analysis showed that lesion location, particularly rectal location, was the most influential factor, followed by erosion and tumor size. To aid in individual risk prediction, a user-friendly online calculator was designed (available at:\n                      <jats:ext-link>https:\/\/changchangzhang2001.shinyapps.io\/blsj\/<\/jats:ext-link>\n                      ). The calculator will remain freely accessible for at least 3 years after publication, and the source code is available from the corresponding author upon reasonable request.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Researchers in this study devised a machine learning model that provides explanations for predicting pathological upgrading in colorectal polyps. The model serves as a useful instrument for assessing preoperative risks and aids in making decisions based on risk, potentially boosting early detection efficiency, refining endoscopic management approaches, and improving resource allocation in colorectal cancer prevention programs.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1845071","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T05:44:36Z","timestamp":1779342276000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Preoperative risk stratification for pathological upgrading in colorectal polyps using explainable machine learning: implications for screening optimization and resource allocation"],"prefix":"10.3389","volume":"14","author":[{"given":"Bo","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Gastroenterology and Hepatology, Guizhou Aerospace Hospital","place":["Zunyi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, The Fourth Affiliated Hospital of Anhui Medical University","place":["Hefei, China"]},{"name":"Anhui Medical University","place":["Hefei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingsu","family":"Gong","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology and Hepatology, Guizhou Aerospace Hospital","place":["Zunyi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.4240\/wjgs.v15.i6.1138","article-title":"Ability of lactulose breath test results to accurately identify colorectal polyps through the measurement of small intestine bacterial overgrowth","volume":"15","author":"Li","year":"2023","journal-title":"World J Gastrointest Surg."},{"key":"B2","doi-asserted-by":"publisher","first-page":"582","DOI":"10.4251\/wjgo.v12.i5.582","article-title":"Association of Helicobacter pylori infection with colorectal polyps and malignancy in China","volume":"12","author":"Wang","year":"2020","journal-title":"World J Gastrointest Oncol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"194","DOI":"10.3892\/ol.2021.12455","article-title":"Key genes in youth colorectal cancer based on data mining and verification by reverse transcription-quantitative PCR","volume":"21","author":"Chen","year":"2021","journal-title":"Oncol Lett."},{"key":"B4","doi-asserted-by":"publisher","first-page":"3000605221117218","DOI":"10.1177\/03000605221117218","article-title":"Alpha-fetoprotein-producing advanced colorectal cancer: a rare case report and literature review","volume":"50","author":"Ding","year":"2022","journal-title":"J Int Med Res."},{"key":"B5","doi-asserted-by":"publisher","first-page":"e070321","DOI":"10.1136\/bmjopen-2022-070321","article-title":"Endoscopic mucosal resection using cold snare versus hot snare in treatment for 10\u201319 mm non-pedunculated colorectal polyps: protocol of a non-inferiority randomised controlled study","volume":"13","author":"Jiang","year":"2023","journal-title":"BMJ Open."},{"key":"B6","doi-asserted-by":"publisher","first-page":"561","DOI":"10.2147\/TCRM.S358708","article-title":"Discrepancy between forceps biopsy and resection in colorectal polyps: a 1686 paired screening-therapeutic colonoscopic finding","volume":"18","author":"Jiang","year":"2022","journal-title":"Ther Clin Risk Manag."},{"key":"B7","doi-asserted-by":"publisher","first-page":"78","DOI":"10.5009\/gnl220060","article-title":"A prediction model based on the risk factors associated with pathological upgrading in patients with early-stage gastric neoplasms diagnosed by endoscopic forceps biopsy","volume":"17","author":"Zhao","year":"2023","journal-title":"Gut Liver."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1097\/DCR.0000000000001440","article-title":"Forceps biopsies are not reliable in the workup of large colorectal lesions referred for endoscopic resection: should they be abandoned?","volume":"62","author":"R\u00f6nnow","year":"2019","journal-title":"Dis Colon Rectum."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.2147\/NSS.S516912","article-title":"Construction and validation of a machine learning-based risk prediction model for sleep quality in patients with OSA","volume":"17","author":"Tong","year":"2025","journal-title":"Nat Sci Sleep."},{"key":"B10","doi-asserted-by":"publisher","first-page":"204","DOI":"10.5498\/wjp.v12.i2.204","article-title":"Screening dementia and predicting high dementia risk groups using machine learning","volume":"12","author":"Byeon","year":"2022","journal-title":"World J Psychiatry."},{"key":"B11","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1186\/s12889-025-21412-4","article-title":"Prediction and unsupervised clustering of fertility intention among migrant workers based on machine learning: a cross-sectional survey from Henan, China","volume":"25","author":"Guo","year":"2025","journal-title":"BMC Public Health."},{"key":"B12","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1055\/a-1185-3109","article-title":"Post-polypectomy colonoscopy surveillance: European Society of Gastrointestinal Endoscopy (ESGE) guideline\u2014update 2020","volume":"52","author":"Hassan","year":"2020","journal-title":"Endoscopy."},{"key":"B13","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1002\/ueg2.12106","article-title":"Post-polypectomy surveillance colonoscopy: comparison of the updated guidelines","volume":"9","author":"Abu-Freha","year":"2021","journal-title":"United European Gastroenterol J."},{"key":"B14","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1016\/j.gie.2024.05.021","article-title":"Risk factors for metachronous colorectal cancer or advanced lesions after endoscopic resection of serrated polyps: a systematic review and meta-analysis","volume":"100","author":"Baile-Maxia","year":"2024","journal-title":"Gastrointest Endosc"},{"key":"B15","doi-asserted-by":"publisher","first-page":"3017","DOI":"10.1093\/nar\/gkad055","article-title":"Deepbio: an automated and interpretable deep-learning platform for high-throughput biological sequence prediction, functional annotation and visualization analysis","volume":"51","author":"Wang","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"B16","doi-asserted-by":"publisher","first-page":"32322","DOI":"10.1021\/acsomega.2c03696","article-title":"Identifying transcription factors that prefer binding to methylated DNA using reduced g-gap dipeptide composition","volume":"7","author":"Nguyen","year":"2022","journal-title":"ACS Omega."},{"key":"B17","doi-asserted-by":"publisher","first-page":"4923","DOI":"10.2147\/IJGM.S325609","article-title":"Machine learning model applied on chest X-ray images enables automatic detection of COVID-19 cases with high accuracy","volume":"14","author":"Erdaw","year":"2021","journal-title":"Int J Gen Med."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1018","DOI":"10.21037\/tp-22-236","article-title":"Establishment of a predictive model for purulent meningitis in preterm infants","volume":"11","author":"Cheng","year":"2022","journal-title":"Transl Pediatr."},{"key":"B19","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1186\/s12893-026-03554-3","article-title":"Interpretable machine learning model for predicting the risk of dysphagia in patients after cardiac surgery","volume":"26","author":"Ren","year":"2026","journal-title":"BMC Surg."},{"key":"B20","doi-asserted-by":"publisher","first-page":"e1024","DOI":"10.1097\/CCE.0000000000001024","article-title":"Intracranial pressure prediction algorithm using machine learning (I-CARE): training and validation study","volume":"6","author":"Fong","year":"2023","journal-title":"Crit Care Explor."},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1101\/2025.09.12.675904","article-title":"Integrative spatial omics for systems-level mapping of pathological niches","author":"Kruse","year":"2025","journal-title":"bioRxiv.2025.09.12.675904"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.2147\/DMSO.S508067","article-title":"Establishing a prediction model for weight loss outcomes after LSG in Chinese obese patients with BMI \u2265325 kg\/m2 using body composition data","volume":"18","author":"Wang","year":"2025","journal-title":"Diabetes Metab Syndr Obes"},{"key":"B23","doi-asserted-by":"publisher","first-page":"621","DOI":"10.2147\/TCRM.S520362","article-title":"Development and validation of an interpretable machine learning model for prediction of the risk of clinically ineffective reperfusion in patients following thrombectomy for ischemic stroke","volume":"21","author":"Hu","year":"2025","journal-title":"Ther Clin Risk Manag."},{"key":"B24","doi-asserted-by":"publisher","first-page":"586115","DOI":"10.2147\/CIA.S586115","article-title":"Development and validation of a prognostic model for one-year mortality in older adults with acute myocardial infarction incorporating activities of daily living impairment","volume":"21","author":"Zhang","year":"2026","journal-title":"Clin Interv Aging."},{"key":"B25","doi-asserted-by":"publisher","first-page":"ofab130","DOI":"10.1093\/ofid\/ofab130","article-title":"Development and validation of a multivariable prediction model for missed HIV health care provider visits in a large US clinical cohort","volume":"8","author":"Pettit","year":"2021","journal-title":"Open Forum Infect Dis"},{"key":"B26","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1002\/pros.23968","article-title":"Development of a multivariable risk model integrating urinary cell DNA methylation and cell-free RNA data for the detection of significant prostate cancer","volume":"80","author":"Connell","year":"2020","journal-title":"Prostate."},{"key":"B27","doi-asserted-by":"publisher","first-page":"67","DOI":"10.4168\/aair.2023.15.1.67","article-title":"Development, validation and comparison of artificial neural network and logistic regression models predicting eosinophilic chronic rhinosinusitis with nasal polyps","volume":"15","author":"Zhou","year":"2023","journal-title":"Allergy Asthma Immunol Res."},{"key":"B28","doi-asserted-by":"publisher","first-page":"2276","DOI":"10.3748\/wjg.v26.i19.2276","article-title":"Serrated polyps of the colon and rectum: remove or not?","volume":"26","author":"Sano","year":"2020","journal-title":"World J Gastroenterol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"284","DOI":"10.23922\/jarc.2023-028","article-title":"Clinical guidelines for diagnosis and management of Cowden syndrome\/PTEN hamartoma tumor syndrome in children and adults\u2014secondary publication","volume":"7","author":"Takayama","year":"2023","journal-title":"J Anus Rectum Colon."},{"key":"B30","doi-asserted-by":"publisher","first-page":"475","DOI":"10.5217\/ir.2018.16.3.475","article-title":"Histologic discrepancy between endoscopic forceps biopsy and endoscopic mucosal resection specimens of colorectal polyp in actual clinical practice","volume":"16","author":"Hwang","year":"2018","journal-title":"Intest Res."},{"key":"B31","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1016\/j.gie.2013.04.185","article-title":"Endoscopic prediction of deep submucosal invasive carcinoma: validation of the narrow-band imaging international colorectal endoscopic (NICE) classification","volume":"78","author":"Hayashi","year":"2013","journal-title":"Gastrointest Endosc."},{"key":"B32","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1007\/s00535-014-1021-4","article-title":"Evidence-based clinical practice guidelines for management of colorectal polyps","volume":"50","author":"Tanaka","year":"2015","journal-title":"J Gastroenterol."},{"key":"B33","doi-asserted-by":"publisher","first-page":"109468","DOI":"10.1016\/j.surg.2025.109468","article-title":"Cancer-specific survival of colorectal adenocarcinomas according to the type of pre-existing adenoma: a surveillance, epidemiology, and end results registry analysis","volume":"184","author":"Emile","year":"2025","journal-title":"Surgery."},{"key":"B34","doi-asserted-by":"publisher","first-page":"1915458","DOI":"10.1155\/2022\/1915458","article-title":"Potential factors predicting histopathologically upgrade discrepancies between endoscopic forceps biopsy of colorectal low-grade intraepithelial neoplasia and endoscopic resection specimens","volume":"2022","author":"Hong","year":"2022","journal-title":"Biomed Res Int."},{"key":"B35","doi-asserted-by":"publisher","first-page":"e029374","DOI":"10.1161\/JAHA.123.029374","article-title":"Improvement in the prediction of cerebrovascular events with white matter hyperintensity","volume":"12","author":"de Havenon","year":"2023","journal-title":"J Am Heart Assoc."},{"key":"B36","doi-asserted-by":"publisher","first-page":"7531368","DOI":"10.1155\/2018\/7531368","article-title":"Diagnostic accuracy of NICE classification system for optical recognition of predictive morphology of colorectal polyps","volume":"2018","author":"Patrun","year":"2018","journal-title":"Gastroenterol Res Pract."},{"key":"B37","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1097\/MLR.0000000000001830","article-title":"Using explainable artificial intelligence to predict potentially preventable hospitalizations: a population-based cohort study in Denmark","volume":"61","author":"Riis","year":"2023","journal-title":"Med Care."}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1845071\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T05:44:37Z","timestamp":1779342277000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1845071\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,21]]},"references-count":37,"alternative-id":["10.3389\/fpubh.2026.1845071"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1845071","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,21]]},"article-number":"1845071"}}