{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T18:13:30Z","timestamp":1790014410066,"version":"4.0.1"},"reference-count":17,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Anhui Provincial Health Science Research Fund","award":["AHWJ2024BAb30015"],"award-info":[{"award-number":["AHWJ2024BAb30015"]}]},{"name":"Scientific Research Cultivation Fund of Anhui Provincial Public Health Clinical Center","award":["2024YKJ01"],"award-info":[{"award-number":["2024YKJ01"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    Gastrointestinal tumors lack non-invasive early screening tools, with most patients diagnosed at advanced stages. Serum tumor markers combined with machine learning show promise, but single markers have low specificity. This study aimed to construct a non-invasive diagnostic model using multiple laboratory variables. A retrospective study included 214 gastrointestinal tumor patients (observation group) and 130 non-tumor individuals (control group). Thirty-eight laboratory indicators were detected, and seven core variables (HCT, Age, TP, ALB, PLT, WBC, CST4) were identified via feature selection. Eleven machine learning algorithms were used to build models, with performance evaluated by AUC, sensitivity, specificity, calibration curves, and DCA. Serum CST4 levels were significantly higher in the observation group (\n                    <jats:italic>P<\/jats:italic>\n                    \u2009&lt;\u20090.001, AUC\u2009=\u20090.706). The SVM model showed the best performance: AUC\u2009=\u20090.85 (95% CI: 0.78\u20130.92), sensitivity\u2009=\u200995.4% (95% CI: 0.87\u20130.98), specificity\u2009=\u200961.5% (95% CI: 0.52\u20130.71), PPV\u2009=\u200980.5% (95% CI: 0.74\u20130.86), NPV\u2009=\u200988.9% (95% CI: 0.81\u20130.94) in the test set. Calibration curves demonstrated high consistency (deviation\u2009&lt;\u20095%), and DCA confirmed superior net benefits. SHapley Additive exPlanations (SHAP) analysis identified HCT, CST4, and Age as top contributors. This internally validated tool demonstrated promising preliminary performance for gastrointestinal tumor screening in high-risk populations (sensitivity 95.4%, specificity 61.5%). Due to its modest specificity, it is suitable as an auxiliary risk stratification tool for high-risk individuals but not for general population screening. External prospective multi-center validation is mandatory before clinical application.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0353753","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T17:53:10Z","timestamp":1790013190000},"page":"e0353753","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Serum Cystatin 4 combined with routine clinical laboratory indicators: A support vector machine diagnostic model for early screening of gastrointestinal tumors"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0630-8789","authenticated-orcid":true,"given":"Huijuan","family":"Bi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lina","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7242-4511","authenticated-orcid":true,"given":"Jilu","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"issue":"7","key":"pone.0353753.ref001","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1097\/CM9.0000000000001474","article-title":"Changing profiles of cancer burden worldwide and in China: a secondary analysis of the global cancer statistics 2020","volume":"134","author":"W Cao","year":"2021","journal-title":"Chin Med J (Engl)"},{"issue":"1","key":"pone.0353753.ref002","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1136\/gutjnl-2024-333227","article-title":"Epidemiology of gastrointestinal cancers: a systematic analysis from the Global Burden of Disease Study 2021","volume":"74","author":"P Danpanichkul","year":"2024","journal-title":"Gut"},{"issue":"3","key":"pone.0353753.ref003","first-page":"221","article-title":"Cancer incidence and mortality in China, 2022","volume":"46","author":"RS Zheng","year":"2024","journal-title":"Zhonghua Zhong Liu Za Zhi"},{"issue":"2","key":"pone.0353753.ref004","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1136\/gutjnl-2022-327736","article-title":"Global burden of colorectal cancer in 2020 and 2040: incidence and mortality estimates from GLOBOCAN","volume":"72","author":"E Morgan","year":"2023","journal-title":"Gut"},{"issue":"4","key":"pone.0353753.ref005","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1053\/j.gastro.2024.11.025","article-title":"Effect of an Endoscopy Screening on Upper Gastrointestinal Cancer Mortality: A Community-Based Multicenter Cluster Randomized Clinical Trial","volume":"168","author":"C Xia","year":"2025","journal-title":"Gastroenterology"},{"issue":"4","key":"pone.0353753.ref006","article-title":"CEA, CA19-9, and CA72-4 in Gastric Cancer Diagnosis and Progression: a Chinese Retrospective Case-Control Study","volume":"71","author":"L Deng","year":"2025","journal-title":"Clin Lab"},{"issue":"2","key":"pone.0353753.ref007","doi-asserted-by":"crossref","first-page":"384","DOI":"10.3892\/ol.2024.14517","article-title":"Clinical application of serum CST4 combined with tumor markers in the diagnosis of digestive system malignant tumors","volume":"28","author":"D Zhou","year":"2024","journal-title":"Oncol Lett"},{"key":"pone.0353753.ref008","doi-asserted-by":"crossref","first-page":"11795549241311404","DOI":"10.1177\/11795549241311404","article-title":"Serum Cystatin S (CST4): A Novel Prognostic Marker for Gastric Cancer","volume":"19","author":"C Gu","year":"2025","journal-title":"Clin Med Insights Oncol"},{"key":"pone.0353753.ref009","doi-asserted-by":"crossref","first-page":"15330338231164232","DOI":"10.1177\/15330338231164232","article-title":"The Diagnosis Significance of Serum Cysteine Protease Inhibitors (CST4) in Colorectal Cancer","volume":"22","author":"M Huang","year":"2023","journal-title":"Technol Cancer Res Treat"},{"issue":"1","key":"pone.0353753.ref010","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1186\/s12876-025-04297-w","article-title":"The diagnostic value of serum cysteine protease inhibitor (CST4) in colorectal cancer: a preliminary study","volume":"25","author":"Y Lan","year":"2025","journal-title":"BMC Gastroenterol"},{"issue":"8","key":"pone.0353753.ref011","doi-asserted-by":"crossref","first-page":"6051","DOI":"10.1007\/s00210-024-03014-w","article-title":"Cysteine protease inhibitor S promotes lymph node metastasis of esophageal cancer cells via VEGF-MAPK\/ERK-MMP9\/2 pathway","volume":"397","author":"J Guo","year":"2024","journal-title":"Naunyn Schmiedebergs Arch Pharmacol"},{"key":"pone.0353753.ref012","doi-asserted-by":"crossref","first-page":"1640646","DOI":"10.3389\/fonc.2025.1640646","article-title":"Clinical value of cystatin S in patients with colorectal cancer chemotherapy","volume":"15","author":"T Han","year":"2025","journal-title":"Front Oncol"},{"issue":"1","key":"pone.0353753.ref013","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1007\/s10875-024-01806-6","article-title":"Machine Learning of Laboratory Data in Predicting 30-Day Mortality for Adult Hemophagocytic Lymphohistiocytosis","volume":"45","author":"J Zhou","year":"2024","journal-title":"J Clin Immunol"},{"issue":"3","key":"pone.0353753.ref014","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1158\/1055-9965.EPI-23-1048","article-title":"Hematocrit Is Associated with Cancer-Related Fatigue in Colorectal Cancer Survivors: A Longitudinal Analysis","volume":"33","author":"J Kiebach","year":"2024","journal-title":"Cancer Epidemiol Biomarkers Prev"},{"key":"pone.0353753.ref015","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.clnu.2024.12.032","article-title":"Association between C-reactive protein-albumin-lymphocyte index and overall survival in patients with esophageal cancer","volume":"45","author":"P Jia","year":"2025","journal-title":"Clin Nutr"},{"issue":"5","key":"pone.0353753.ref016","doi-asserted-by":"crossref","first-page":"1755","DOI":"10.3390\/jcm12051755","article-title":"Establishment and Validation of Predictive Model of Tophus in Gout Patients","volume":"12","author":"T Lei","year":"2023","journal-title":"J Clin Med"},{"key":"pone.0353753.ref017","doi-asserted-by":"crossref","first-page":"1597864","DOI":"10.3389\/fnut.2025.1597864","article-title":"Machine learning with decision curve analysis evaluates nutritional metabolic biomarkers for cardiovascular-kidney-metabolic risk: an NHANES analysis","volume":"12","author":"J Huang","year":"2025","journal-title":"Front Nutr"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353753","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T17:53:17Z","timestamp":1790013197000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353753"}},"subtitle":[],"editor":[{"given":"GV Narasimha","family":"Kumar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":17,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0353753","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]}}}