{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T20:07:24Z","timestamp":1793390844484,"version":"4.5.0"},"reference-count":51,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T00:00:00Z","timestamp":1736208000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Key Laboratory of Science and Technology Innovation","award":["20170913A0410028"],"award-info":[{"award-number":["20170913A0410028"]}]},{"name":"Scientific\u00a0Research\u00a0Projects\u00a0of\u00a0Medical\u00a0and\u00a0Health\u00a0Institutions\u00a0of\u00a0Longhua\u00a0District","award":["2022033"],"award-info":[{"award-number":["2022033"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Polycystic ovary syndrome (PCOS) is a primary endocrine disorder affecting premenopausal women involving metabolic dysregulation. We aimed to screen serum biomarkers in PCOS patients using untargeted lipidomics and ensemble machine learning. Serum from PCOS patients and non-PCOS subjects were collected for untargeted lipidomics analysis. Through analyzing the classification of differential lipid metabolites and the association between differential lipid metabolites and clinical indexes, ensemble machine learning, data preprocessing, statistical test pre-screening, ensemble learning method secondary screening, biomarkers verification and evaluation, and diagnostic panel model construction and verification were performed on the data of untargeted lipidomics. Results indicated that different lipid metabolites not only differ between groups but also have close effects on different corresponding clinical indexes. PI (18:0\/20:3)-H and PE (18:1p\/22:6)-H were identified as candidate biomarkers. Three machine learning models, logistic regression, random forest, and support vector machine, showed that screened biomarkers had better classification ability and effect. In addition, the correlation of candidate biomarkers was low, indicating that the overlap between the selected biomarkers was low, and the combination of panels was more optimized. When the AUC value of the test set of the constructed diagnostic panel model was 0.815, the model\u2019s accuracy in the test set was 0.74, specificity was 0.88, and sensitivity was 0.7. This study demonstrated the applicability and robustness of machine learning algorithms to analyze lipid metabolism data for efficient and reliable biomarker screening. PI (18:0\/20:3)-H and PE (18:1p\/22:6)-H showed great potential in diagnosing PCOS.<\/jats:p>","DOI":"10.1371\/journal.pone.0313494","type":"journal-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T18:35:07Z","timestamp":1736274907000},"page":"e0313494","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":20,"title":["Screening of serum biomarkers in patients with PCOS through lipid omics and ensemble machine learning"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0487-2004","authenticated-orcid":true,"given":"Ji-ying","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wu-jie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi-ying","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li-lan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-qing","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong-gang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan-li","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,1,7]]},"reference":[{"issue":"5","key":"pone.0313494.ref001","doi-asserted-by":"crossref","first-page":"912","DOI":"10.1016\/j.fertnstert.2022.02.028","article-title":"Subclinical cardiovascular disease and polycystic ovary syndrome","volume":"117","author":"JMD Gomez","year":"2022","journal-title":"Fertil Steril"},{"issue":"11","key":"pone.0313494.ref002","article-title":"The Normal Body Mass Index (BMI) of Women with Polycystic Ovary Syndrome (PCOS) was Associated with IVF\/ICSI Assisted Conception Outcomes.","volume":"50","author":"N Ma","year":"2023","journal-title":"Clinical and Experimental Obstetrics & Gynecology."},{"issue":"1","key":"pone.0313494.ref003","doi-asserted-by":"crossref","first-page":"e3464","DOI":"10.1002\/dmrr.3464","article-title":"Metabolic syndrome and its components in different phenotypes of polycystic ovary syndrome","volume":"38","author":"A Krentowska","year":"2022","journal-title":"Diabetes Metab Res Rev"},{"issue":"1","key":"pone.0313494.ref004","first-page":"13","article-title":"Phytotherapy of polycystic ovary syndrome: A review.","volume":"20","author":"F Azin","year":"2022","journal-title":"Int J Reprod Biomed"},{"issue":"4","key":"pone.0313494.ref005","doi-asserted-by":"crossref","DOI":"10.31083\/j.ceog5004088","article-title":"Fitness Assessments of Women with Polycystic Ovary Syndrome: A Prospective Process Feasibility Study.","volume":"50","author":"PJ Wright","year":"2023","journal-title":"Clinical and Experimental Obstetrics & Gynecology."},{"issue":"2","key":"pone.0313494.ref006","doi-asserted-by":"crossref","DOI":"10.3390\/ijms23020583","article-title":"Polycystic Ovary Syndrome: A Comprehensive Review of Pathogenesis, Management, and Drug Repurposing.","volume":"23","author":"HM Sadeghi","year":"2022","journal-title":"Int J Mol Sci."},{"issue":"3\u201304","key":"pone.0313494.ref007","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1055\/s-0041-1729841","article-title":"Metabolomic Biomarkers in Polycystic Ovary Syndrome: A Review of the Evidence.","volume":"39","author":"S Alesi","year":"2021","journal-title":"Semin Reprod Med."},{"issue":"5","key":"pone.0313494.ref008","doi-asserted-by":"crossref","first-page":"887","DOI":"10.1016\/j.fertnstert.2022.03.008","article-title":"Cardiometabolic biomarkers in women with polycystic ovary syndrome","volume":"117","author":"K van der Ham","year":"2022","journal-title":"Fertil Steril"},{"issue":"4","key":"pone.0313494.ref009","doi-asserted-by":"crossref","first-page":"397","DOI":"10.4103\/ijmr.IJMR_4608_20","article-title":"Serum anti-M\u00fcllerian hormone: A potential biomarker for polycystic ovary syndrome","volume":"158","author":"A Halder","year":"2023","journal-title":"Indian J Med Res"},{"key":"pone.0313494.ref010","article-title":"Insulin resistance is associated with increased circulating lipocalin-2 levels in polycystic ovary syndrome: a systematic review and meta-analysis.","author":"SR Varikasuvu","year":"2023","journal-title":"Minerva Endocrinol (Torino)."},{"issue":"22","key":"pone.0313494.ref011","doi-asserted-by":"crossref","DOI":"10.3390\/ijms242216247","article-title":"Essential Role of Granulosa Cell Glucose and Lipid Metabolism on Oocytes and the Potential Metabolic Imbalance in Polycystic Ovary Syndrome.","volume":"24","author":"CH Zhang","year":"2023","journal-title":"Int J Mol Sci"},{"issue":"4","key":"pone.0313494.ref012","doi-asserted-by":"crossref","first-page":"4522","DOI":"10.18632\/oncotarget.23393","article-title":"Lipidomics reveals altered biosynthetic pathways of glycerophospholipids and cell signaling as biomarkers of the polycystic ovary syndrome","volume":"9","author":"M Jov\u00e9","year":"2018","journal-title":"Oncotarget"},{"issue":"14","key":"pone.0313494.ref013","doi-asserted-by":"crossref","DOI":"10.3390\/ijms21144853","article-title":"Metabolomic Insight into Polycystic Ovary Syndrome-An Overview.","volume":"21","author":"A Rajska","year":"2020","journal-title":"Int J Mol Sci."},{"key":"pone.0313494.ref014","doi-asserted-by":"crossref","first-page":"628","DOI":"10.3389\/fendo.2020.00628","article-title":"Correlation Between Fecal Metabolomics and Gut Microbiota in Obesity and Polycystic Ovary Syndrome.","volume":"11","author":"L Zhou","year":"2020","journal-title":"Front Endocrinol (Lausanne)."},{"issue":"3","key":"pone.0313494.ref015","doi-asserted-by":"crossref","first-page":"221","DOI":"10.2174\/1871530318666180122165415","article-title":"Emerging Metabolomics Biomarkers of Polycystic Ovarian Syndrome; Targeting the Master Metabolic Disrupters for Diagnosis and Treatment.","volume":"18","author":"M Omabe","year":"2018","journal-title":"Endocr Metab Immune Disord Drug Targets."},{"issue":"4","key":"pone.0313494.ref016","doi-asserted-by":"crossref","first-page":"1819","DOI":"10.1152\/physrev.00035.2018","article-title":"Metabolomics for Investigating Physiological and Pathophysiological Processes","volume":"99","author":"DS Wishart","year":"2019","journal-title":"Physiol Rev"},{"issue":"6","key":"pone.0313494.ref017","doi-asserted-by":"crossref","first-page":"1645","DOI":"10.1016\/j.numecd.2021.01.008","article-title":"The evolving landscape of untargeted metabolomics.","volume":"31","author":"A Di Minno","year":"2021","journal-title":"Nutr Metab Cardiovasc Dis"},{"issue":"2","key":"pone.0313494.ref018","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1021\/acs.chemrestox.1c00299","article-title":"Metabolomic Study on Iohexol-Induced Nephrotoxicity in Rats Based on NMR and LC-MS Analyses","volume":"35","author":"L Wang","year":"2022","journal-title":"Chem Res Toxicol"},{"issue":"6","key":"pone.0313494.ref019","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1111\/joim.12822","article-title":"eDoctor: machine learning and the future of medicine","volume":"284","author":"GS Handelman","year":"2018","journal-title":"J Intern Med"},{"issue":"7","key":"pone.0313494.ref020","doi-asserted-by":"crossref","first-page":"e541","DOI":"10.1016\/S2352-3026(20)30121-6","article-title":"Machine learning in haematological malignancies","volume":"7","author":"N Radakovich","year":"2020","journal-title":"Lancet Haematol"},{"key":"pone.0313494.ref021","doi-asserted-by":"crossref","first-page":"S61","DOI":"10.1016\/j.jelectrocard.2019.08.008","article-title":"Machine learning in the electrocardiogram.","volume":"57s","author":"A Minchol\u00e9","year":"2019","journal-title":"J Electrocardiol."},{"issue":"3","key":"pone.0313494.ref022","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1007\/s40618-021-01672-8","article-title":"Polycystic ovary syndrome: clinical and laboratory variables related to new phenotypes using machine-learning models","volume":"45","author":"IS Silva","year":"2022","journal-title":"J Endocrinol Invest"},{"key":"pone.0313494.ref023","doi-asserted-by":"crossref","first-page":"111139","DOI":"10.1016\/j.mce.2020.111139","article-title":"Raman spectroscopy of follicular fluid and plasma with machine-learning algorithms for polycystic ovary syndrome screening","volume":"523","author":"X Zhang","year":"2021","journal-title":"Mol Cell Endocrinol"},{"issue":"1","key":"pone.0313494.ref024","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.fertnstert.2003.10.004","article-title":"Revised 2003 consensus on diagnostic criteria and long-term health risks related to polycystic ovary syndrome","volume":"81","year":"2004","journal-title":"Fertil Steril"},{"issue":"5","key":"pone.0313494.ref025","doi-asserted-by":"crossref","first-page":"3590","DOI":"10.1021\/acs.analchem.8b05592","article-title":"Systematic Error Removal Using Random Forest for Normalizing Large-Scale Untargeted Lipidomics Data","volume":"91","author":"S Fan","year":"2019","journal-title":"Anal Chem"},{"issue":"25","key":"pone.0313494.ref026","doi-asserted-by":"crossref","first-page":"4229","DOI":"10.1016\/j.chroma.2010.04.034","article-title":"Precise and global identification of phospholipid molecular species by an Orbitrap mass spectrometer and automated search engine Lipid Search","volume":"1217","author":"R Taguchi","year":"2010","journal-title":"J Chromatogr A"},{"issue":"18","key":"pone.0313494.ref027","doi-asserted-by":"crossref","first-page":"6510","DOI":"10.1093\/jxb\/erab300","article-title":"Sulfoquinovosyl diacylglycerol synthase 1 impairs glycolipid accumulation and photosynthesis in phosphate-deprived rice","volume":"72","author":"Y Sun","year":"2021","journal-title":"J Exp Bot"},{"issue":"3","key":"pone.0313494.ref028","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.3233\/JAD-215119","article-title":"Diagnostic Model of Alzheimer\u2019s Disease in the Elderly Based on Protein and Metabolic Biomarkers","volume":"85","author":"L Yang","year":"2022","journal-title":"J Alzheimers Dis"},{"issue":"1","key":"pone.0313494.ref029","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1097\/01.ede.0000147512.81966.ba","article-title":"Optimal cut-point and its corresponding Youden Index to discriminate individuals using pooled blood samples","volume":"16","author":"EF Schisterman","year":"2005","journal-title":"Epidemiology"},{"issue":"2","key":"pone.0313494.ref030","doi-asserted-by":"crossref","DOI":"10.3390\/genes13020302","article-title":"A Review on CYP11A1, CYP17A1, and CYP19A1 Polymorphism Studies: Candidate Susceptibility Genes for Polycystic Ovary Syndrome (PCOS) and Infertility.","volume":"13","author":"R Heidarzadehpilehrood","year":"2022","journal-title":"Genes (Basel)."},{"issue":"10","key":"pone.0313494.ref031","doi-asserted-by":"crossref","first-page":"2037","DOI":"10.1111\/epi.16333","article-title":"Machine learning applications in epilepsy","volume":"60","author":"B Abbasi","year":"2019","journal-title":"Epilepsia"},{"issue":"3","key":"pone.0313494.ref032","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1136\/archdischild-2020-321023","article-title":"Future of machine learning in paediatrics","volume":"107","author":"SL Clarke","year":"2022","journal-title":"Arch Dis Child"},{"key":"pone.0313494.ref033","doi-asserted-by":"crossref","first-page":"107739","DOI":"10.1016\/j.biotechadv.2021.107739","article-title":"Using machine learning approaches for multi-omics data analysis: A review","volume":"49","author":"PS Reel","year":"2021","journal-title":"Biotechnol Adv"},{"issue":"4","key":"pone.0313494.ref034","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1093\/jnci\/dji008","article-title":"Signal in noise: evaluating reported reproducibility of serum proteomic tests for ovarian cancer","volume":"97","author":"KA Baggerly","year":"2005","journal-title":"J Natl Cancer Inst"},{"key":"pone.0313494.ref035","first-page":"6691096","article-title":"Integrated Learning: Screening Optimal Biomarkers for Identifying Preeclampsia in Placental mRNA Samples.","volume":"2021","author":"R Guo","year":"2021","journal-title":"Comput Math Methods Med."},{"issue":"1","key":"pone.0313494.ref036","first-page":"64","article-title":"Integrative network learning for multi-modality biomarker data.","volume":"15","author":"S Xie","year":"2021","journal-title":"Ann Appl Stat"},{"key":"pone.0313494.ref037","doi-asserted-by":"crossref","first-page":"274","DOI":"10.3389\/fpls.2019.00274","article-title":"Diverse Physiological Functions of FAB1 and Phosphatidylinositol 3,5-Bisphosphate in Plants.","volume":"10","author":"T Hirano","year":"2019","journal-title":"Front Plant Sci"},{"issue":"1","key":"pone.0313494.ref038","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1186\/s12964-021-00715-0","article-title":"Phosphoinositides signaling modulates microglial actin remodeling and phagocytosis in Alzheimer\u2019s disease","volume":"19","author":"SE Desale","year":"2021","journal-title":"Cell Commun Signal"},{"issue":"35","key":"pone.0313494.ref039","doi-asserted-by":"crossref","first-page":"8404","DOI":"10.1021\/acs.jpcb.7b12641","article-title":"Reorganization of Ternary Lipid Mixtures of Nonphosphorylated Phosphatidylinositol Interacting with Angiomotin","volume":"122","author":"AC Kimble-Hill","year":"2018","journal-title":"J Phys Chem B"},{"issue":"35","key":"pone.0313494.ref040","doi-asserted-by":"crossref","first-page":"23636","DOI":"10.1074\/jbc.M803600200","article-title":"Phosphatidylethanolamine in Trypanosoma brucei is organized in two separate pools and is synthesized exclusively by the Kennedy pathway","volume":"283","author":"A Signorell","year":"2008","journal-title":"J Biol Chem"},{"issue":"4","key":"pone.0313494.ref041","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1111\/cen.14421","article-title":"Obesity and polycystic ovary syndrome","volume":"95","author":"TM Barber","year":"2021","journal-title":"Clin Endocrinol (Oxf)."},{"issue":"5","key":"pone.0313494.ref042","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1084\/jem.182.5.1545","article-title":"Early redistribution of plasma membrane phosphatidylserine is a general feature of apoptosis regardless of the initiating stimulus: inhibition by overexpression of Bcl-2 and Abl","volume":"182","author":"SJ Martin","year":"1995","journal-title":"J Exp Med"},{"issue":"21","key":"pone.0313494.ref043","doi-asserted-by":"crossref","first-page":"4419","DOI":"10.1128\/MCB.00378-12","article-title":"Acid ceramidase (ASAH1) represses steroidogenic factor 1-dependent gene transcription in H295R human adrenocortical cells by binding to the receptor.","volume":"32","author":"NC Lucki","year":"2012","journal-title":"Mol Cell Biol"},{"key":"pone.0313494.ref044","doi-asserted-by":"crossref","first-page":"116093","DOI":"10.1016\/j.biopha.2023.116093","article-title":"Ampelopsis japonica aqueous extract improves ovulatory dysfunction in PCOS by modulating lipid metabolism","volume":"170","author":"H Zhu","year":"2024","journal-title":"Biomed Pharmacother"},{"issue":"1","key":"pone.0313494.ref045","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1186\/s12967-024-05167-x","article-title":"Integrated lipid metabolomics and proteomics analysis reveal the pathogenesis of polycystic ovary syndrome","volume":"22","author":"Y Qian","year":"2024","journal-title":"J Transl Med"},{"issue":"1","key":"pone.0313494.ref046","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1186\/s13048-021-00885-y","article-title":"Lipidomics analysis of human follicular fluid form normal-weight patients with polycystic ovary syndrome: a pilot study.","volume":"14","author":"Y Ban","year":"2021","journal-title":"J Ovarian Res"},{"issue":"3","key":"pone.0313494.ref047","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1007\/s11306-014-0726-y","article-title":"Lipidomic analysis of plasma samples from women with polycystic ovary syndrome.","volume":"11","author":"Z Haoula","year":"2015","journal-title":"Metabolomics"},{"issue":"1","key":"pone.0313494.ref048","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1530\/JME-17-0023","article-title":"The association of the lipidomic profile with features of polycystic ovary syndrome","volume":"59","author":"LJ Moran","year":"2017","journal-title":"J Mol Endocrinol"},{"issue":"5","key":"pone.0313494.ref049","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1093\/bioinformatics\/btg484","article-title":"Reproducibility of SELDI-TOF protein patterns in serum: comparing datasets from different experiments","volume":"20","author":"KA Baggerly","year":"2004","journal-title":"Bioinformatics"},{"issue":"1","key":"pone.0313494.ref050","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1186\/s12920-021-01058-y","article-title":"Untargeted metabolomic approach to study the serum metabolites in women with polycystic ovary syndrome","volume":"14","author":"Y Yu","year":"2021","journal-title":"BMC Med Genomics"},{"issue":"3","key":"pone.0313494.ref051","doi-asserted-by":"crossref","first-page":"e29967","DOI":"10.2196\/29967","article-title":"Machine-Aided Self-diagnostic Prediction Models for Polycystic Ovary Syndrome: Observational Study.","volume":"6","author":"A Zigarelli","year":"2022","journal-title":"JMIR Form Res."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0313494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T18:35:34Z","timestamp":1736274934000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0313494"}},"subtitle":[],"editor":[{"given":"Fabio Vasconcellos","family":"Comim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,1,7]]},"references-count":51,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1,7]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0313494","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,7]]}}}