{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T07:47:20Z","timestamp":1791618440540,"version":"4.3.4"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>New-onset diabetes (NOD) represents a high-risk population for pancreatic ductal adenocarcinoma (PDAC), yet effective early detection tools for this specific subgroup remain an unmet clinical need.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a prospective serum metabolomic analysis using UHPLC-MS\/MS in 133 NOD patients aged &amp;gt;65 years, including 60 with PDAC (PDAC+NOD) and 73 without (NOD). Multivariate analysis (OPLS-DA) and machine learning approaches were employed to identify and optimize a diagnostic metabolic biomarker panel. Model performance was evaluated using a hold-out validation set following TRIPOD-ML guidelines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We identified 62 differentially expressed serum metabolites (P&amp;lt;0.05, FDR-corrected), primarily implicating branched-chain amino acid metabolism, bile acid biosynthesis, and sphingolipid signaling pathways. Notably, significant reductions in one-carbon metabolism-related metabolites (serine, glycine, homocysteine) were observed in PDAC+NOD patients. Feature selection yielded an optimized 5-metabolite panel comprising glycine, L-serine, L-methionine, L-homocysteine, and L-homocystine. This panel demonstrated high diagnostic accuracy with an AUC of 0.853 (95% CI: 0.786-0.920) and 75.0% accuracy in distinguishing PDAC+NOD from NOD patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Our study establishes a foundational metabolic biomarker strategy for precision screening of early-stage PDAC in NOD populations. The dysregulated one-carbon metabolites provide novel mechanistic insights into PDAC pathogenesis and offer actionable targets for clinical assay development. Future validation in multi-center cohorts is warranted to confirm clinical utility.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2025.1684608","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T06:30:34Z","timestamp":1765175434000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Machine learning-optimized metabolic biomarker panel for precision screening of early-stage pancreatic cancer in new-onset diabetes"],"prefix":"10.3389","volume":"16","author":[{"given":"Weiliang","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Mu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guo","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,8]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3322\/caac.21654","article-title":"Cancer statistics, 2021","volume":"71","author":"Siegel","year":"2021","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1038\/s41571-018-0112-1","article-title":"Optimizing the outcomes of pancreatic cancer surgery","volume":"16","author":"Strobel","year":"2019","journal-title":"Nat Rev Clin Oncol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1097\/MPA.0b013e318288107a","article-title":"Toward a better understanding of pancreatic ductal adenocarcinoma: Glimmers of hope","volume":"42","author":"Partensky","year":"2013","journal-title":"Pancreas"},{"key":"B4","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3322\/caac.21551","article-title":"Cancer statistics, 2019","volume":"69","author":"Siegel","year":"2019","journal-title":"CA Cancer J Clin"},{"key":"B5","doi-asserted-by":"publisher","first-page":"109500.40678708","DOI":"10.3748\/wjg.v31.i26.109500","article-title":"Serum exosomal hsa-let-7f-5p: A potential diagnostic biomarker for metastatic pancreatic cancer detection","volume":"31","author":"Ren","year":"2025","journal-title":"World J Gastroenterol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1053\/j.gastro.2020.11.052","article-title":"Lead-time trajectory of CA19\u20139 as an anchor marker for pancreatic cancer early detection","volume":"160","author":"Fahrmann","year":"2021","journal-title":"Gastroenterology."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0000000000002734","article-title":"Defining and predicting early recurrence in 957 patients with resected pancreatic ductal adenocarcinoma","volume":"269","author":"Groot","year":"2019","journal-title":"Ann Surg"},{"key":"B8","doi-asserted-by":"publisher","first-page":"188409","DOI":"10.1016\/j.bbcan.2020.188409","article-title":"Roles of CA19\u20139 in pancreatic cancer: biomark, predictor and promoter","volume":"1875","author":"Luo","year":"2020","journal-title":"Biochim Biophys Acta Rev Cancer"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djw266","article-title":"Sequential validation of blood-based protein biomarker candidates for early-stage pancreatic cancer","volume":"109","author":"Capello","year":"2017","journal-title":"J Natl Cancer Inst"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.molonc.2016.07.001","article-title":"Plasma protein profiling in a stage defined pancreatic cancer cohort\u2014Implications for early diagnosis","volume":"10","author":"Gerdtsson","year":"2016","journal-title":"Mol Oncol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprot.2014.10.001","article-title":"Evaluation in pre-diagnosis samples discounts ICAM-1 and TIMP-1 as biomarkers for earlier diagnosis of pancreatic cancer","volume":"113","author":"Jenkinson","year":"2015","journal-title":"J Proteom"},{"key":"B12","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1186\/1471-2407-13-404","article-title":"Validation of four candidate pancreatic cancer serological biomarkers that improve the performance of CA19-9","volume":"13","author":"Makawita","year":"2013","journal-title":"BMC Cancer"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1002\/pmic.201400476","article-title":"Proteomics analysis of bodily fluids in pancreatic cancer","volume":"15","author":"Pan","year":"2015","journal-title":"Proteomics."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.17463","article-title":"Large-scale clinical validation of biomarkers for pancreatic cancer using a mass spectrometry-based proteomics approach","volume":"8","author":"Park","year":"2017","journal-title":"Oncotarget"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.21861","article-title":"Diagnostic performance enhancement of pancreatic cancer using proteomic multimarker panel","volume":"8","author":"Park","year":"2017","journal-title":"Oncotarget."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0161009","article-title":"Identification of IGFBP2 and IGFBP3 as compensatory biomarkers for CA19\u20139 in early-stage pancreatic cancer using a combination of antibody-based and LC-MS\/MS-based proteomics","volume":"11","author":"Yoneyama","year":"2016","journal-title":"PloS One"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djy126","article-title":"A plasma-derived protein-metabolite multiplexed panel for early-stage pancreatic cancer","volume":"111","author":"Fahrmann","year":"2019","journal-title":"J Natl Cancer Inst"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.4251\/wjgo.v16.i4.1256","article-title":"Computed tomography-based radiomics diagnostic approach for differential diagnosis between early- and late-stage pancreatic ductal adenocarcinoma","volume":"16","author":"Ren","year":"2024","journal-title":"World J Gastrointest Oncol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"109373.40901350","DOI":"10.4329\/wjr.v17.i8.109373","article-title":"Developing and validating a computed tomography radiomics strategy to predict lymph node metastasis in pancreatic cancer","volume":"17","author":"Ren","year":"2025","journal-title":"World J Radiol"},{"key":"B20","doi-asserted-by":"publisher","first-page":"104805","DOI":"10.1016\/j.phrs.2020.104805","article-title":"Metabolomics identified new biomarkers for the precise diagnosis of pancreatic cancer and associated tissue metastasis","volume":"156","author":"Luo","year":"2020","journal-title":"Pharmacol Res"},{"key":"B21","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/S1470-2045(08)70337-1","article-title":"New-onset diabetes: A potential clue to the early diagnosis of pancreatic cancer","volume":"10","author":"Pannala","year":"2009","journal-title":"Lancet Oncol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1002\/mc.20771","article-title":"Diabetes and pancreatic cancer","volume":"51","author":"Li","year":"2012","journal-title":"Mol Carcinog"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)30974-0","article-title":"Pancreatic cancer","volume":"395","author":"Mizrahi","year":"2020","journal-title":"Lancet"},{"key":"B24","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1016\/S2468-1253(19)30416-9","article-title":"Early detection of pancreatic cancer","volume":"5","author":"Pereira","year":"2020","journal-title":"Lancet Gastroenterol Hepatol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.16249","article-title":"Serum metabolomics differentiating pancreatic cancer from new-onset diabetes","volume":"8","author":"He","year":"2017","journal-title":"Oncotarget"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.5296","article-title":"Biomarkers for pancreatic cancer based on tissue and serum metabolomics analysis in a multicenter study","volume":"12","author":"Zhao","year":"2023","journal-title":"Cancer Med"},{"key":"B27","doi-asserted-by":"publisher","first-page":"20552076231179007","DOI":"10.1177\/20552076231179007","article-title":"Untargeted metabolomics characterization of the resectab le pancreatic ductal adenocarcinoma","volume":"9","author":"Cao","year":"2023","journal-title":"Digit Health"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.CD-22-1134","article-title":"Cancer in 2022","volume":"12","year":"2022","journal-title":"Cancer Discov"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0000000000001731","article-title":"Pancreatic cancer surgery: the new R-status counts","volume":"265","author":"Strobel","year":"2017","journal-title":"Ann Surg"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jpba.2013.08.041","article-title":"Metabolomics in cancer biomarker discovery: current trends and future perspectives","volume":"87","author":"Armitage","year":"2014","journal-title":"J Pharm BioMed Anal"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.CD-20-1211","article-title":"Metabolic codependencies in the tumor microenvironment","volume":"11","author":"Dey","year":"2021","journal-title":"Cancer Discov"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccell.2020.06.001","article-title":"Oxidative stress in cancer","volume":"38","author":"Hayes","year":"2020","journal-title":"Cancer Cell"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcb.2020.03.002","article-title":"The complex interplay between antioxidants and ROS in cancer","volume":"30","author":"Harris","year":"2020","journal-title":"Trends Cell Biol"},{"key":"B34","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1186\/s12943-024-02164-y","article-title":"Molecular mechanisms and therapeutic significance of Tryptophan Metabolism and signaling in cancer","volume":"23","author":"Yan","year":"2024","journal-title":"Mol Cancer"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2014.04.045","article-title":"Serine, but not glycine, supports one-carbon metabolism and proliferation of cancer cells","volume":"7","author":"Labuschagne","year":"2014","journal-title":"Cell Rep"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmet.2022.04.006","article-title":"Glycine decarboxylase maintains mitochondrial protein lipoylation to support tumor growth","volume":"34","author":"Mukha","year":"2022","journal-title":"Cell Metab"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1016\/j.molcel.2020.11.027","article-title":"In Vivo Evidence for Serine Biosynthesis-Defined Sensitivity of Lung Metastasis, but Not of Primary Breast Tumors, to mTORC1 Inhibition","volume":"81","author":"Rinaldi","year":"2021","journal-title":"Mol Cell"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.15252\/embr.201948260","article-title":"The breast cancer oncogene IKKepsilon coordinates mitochondrial function and serine metabolism","volume":"21","author":"Xu","year":"2020","journal-title":"EMBO Rep"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1002\/1878-0261.13291","article-title":"Mitochondrial DNA mutations in ageing and cancer","volume":"16","author":"Smith","year":"2022","journal-title":"Mol Oncol"},{"key":"B40","doi-asserted-by":"publisher","first-page":"8:15965","DOI":"10.1038\/ncomms15965","article-title":"Compensatory metabolic networks in pancreatic cancers upon perturbation of glutamine metabolism","volume":"3","author":"Biancur","year":"2017","journal-title":"Nat Commun"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1684608\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T06:30:35Z","timestamp":1765175435000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1684608\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":40,"alternative-id":["10.3389\/fendo.2025.1684608"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2025.1684608","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,8]]},"article-number":"1684608"}}