{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T06:44:44Z","timestamp":1775198684127,"version":"3.50.1"},"reference-count":47,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Metabolites"],"abstract":"<jats:p>Background: Prostate cancer, benign prostatic hyperplasia, and prostatitis share substantial overlap in clinical symptoms and biological characteristics, which hampers non-invasive and early differential diagnosis. Untargeted metabolomics enables comprehensive profiling of disease-associated metabolic alterations; however, its high dimensionality and strong feature correlations challenge conventional statistical approaches. Methods: To address this, we analyzed serum untargeted LC\u2013MS data following standardized preprocessing. We adopted a nested cross-validation strategy to evaluate various feature selection methods and machine learning classifiers, ultimately determining that multiclass LASSO regression was the most effective feature selection approach. Results: An optimized Random Forest model demonstrated strong, superior performance in distinguishing between prostate cancer, prostatitis, benign prostatic hyperplasia, and healthy controls (out-of-fold accuracy: 93.8%; macro-F1: 0.937). Additionally, SHAP (SHapley Additive exPlanations) analysis translated feature statistical importance into biologically meaningful modules, revealing that distinct, disease-specific patterns of metabolic reprogramming drove the model\u2019s robust multiclass discrimination. Conclusions: This study demonstrates the value of integrating serum untargeted metabolomics with advanced explainable machine learning for effective multiclass differentiation of major prostate diseases, providing a promising non-invasive framework for diagnostic stratification and metabolic biomarker discovery.<\/jats:p>","DOI":"10.3390\/metabo16040237","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T16:34:08Z","timestamp":1774974848000},"page":"237","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Serum Untargeted Metabolomics Integrated with SHAP-Based Machine Learning for Multiclass Stratification of Prostate Cancer, Prostatitis, and Benign Prostatic Hyperplasia"],"prefix":"10.3390","volume":"16","author":[{"given":"Zijie","family":"Wang","sequence":"first","affiliation":[{"name":"School of Medical and Life Sciences, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7740-8359","authenticated-orcid":false,"given":"Jialu","family":"Xin","sequence":"additional","affiliation":[{"name":"School of Medical and Life Sciences, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuyan","family":"He","sequence":"additional","affiliation":[{"name":"School of Medical and Life Sciences, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shutong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Medical and Life Sciences, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinghan","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Acupuncture and Tuina, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Health Preservation and Rehabilitation, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Medical and Life Sciences, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Oseni, S.O., Naar, C., Pavlovi\u0107, M., Asghar, W., Hartmann, J.X., Fields, G.B., Esiobu, N., and Kumi-Diaka, J. (2023). The Molecular Basis and Clinical Consequences of Chronic Inflammation in Prostatic Diseases: Prostatitis, Benign Prostatic Hyperplasia, and Prostate Cancer. Cancers, 15.","DOI":"10.3390\/cancers15123110"},{"key":"ref_2","unstructured":"(2026, February 08). Campbell-Walsh Urology. Available online: https:\/\/elsevier-elibrary.com\/contents\/fullcontent\/58071\/epubcontent_v2\/OEBPS\/B9781416069119000918.htm."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"177","DOI":"10.7150\/jca.37235","article-title":"Correlation between Prostatitis, Benign Prostatic Hyperplasia and Prostate Cancer: A Systematic Review and Meta-Analysis","volume":"11","author":"Zhang","year":"2020","journal-title":"J. Cancer"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"120","DOI":"10.7326\/0003-4819-157-2-201207170-00459","article-title":"Screening for Prostate Cancer: U.S. Preventive Services Task Force Recommendation Statement","volume":"157","author":"Moyer","year":"2012","journal-title":"Ann. Intern. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"k3519","DOI":"10.1136\/bmj.k3519","article-title":"Prostate Cancer Screening with Prostate-Specific Antigen (PSA) Test: A Systematic Review and Meta-Analysis","volume":"362","author":"Ilic","year":"2018","journal-title":"BMJ"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1007\/s11523-022-00925-7","article-title":"Addressing Challenges and Controversies in the Management of Prostate Cancer with Multidisciplinary Teams","volume":"17","author":"Shore","year":"2022","journal-title":"Target. Oncol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.copbio.2018.07.010","article-title":"Challenges, Progress and Promises of Metabolite Annotation for LC-MS-Based Metabolomics","volume":"55","author":"Chaleckis","year":"2019","journal-title":"Curr. Opin. Biotechnol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1712","DOI":"10.1038\/bjc.2015.411","article-title":"Metabolic Markers in Blood Can Separate Prostate Cancer from Benign Prostatic Hyperplasia","volume":"113","author":"Hansen","year":"2015","journal-title":"Br. J. Cancer"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1038\/s41416-021-01435-5","article-title":"Metabolic Reprogramming in Prostate Cancer","volume":"125","author":"Ahmad","year":"2021","journal-title":"Br. J. Cancer"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.euo.2018.06.010","article-title":"The Metabolic Landscape of Prostate Cancer","volume":"2","author":"Giunchi","year":"2019","journal-title":"Eur. Urol. Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1074\/mcp.M115.052381","article-title":"Integration of Metabolomics and Transcriptomics Reveals Major Metabolic Pathways and Potential Biomarker Involved in Prostate Cancer","volume":"15","author":"Ren","year":"2016","journal-title":"Mol. Cell. Proteom."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wanjari, U.R., Mukherjee, A.G., Gopalakrishnan, A.V., Murali, R., Dey, A., Vellingiri, B., and Ganesan, R. (2023). Role of Metabolism and Metabolic Pathways in Prostate Cancer. Metabolites, 13.","DOI":"10.3390\/metabo13020183"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101","DOI":"10.4103\/aja202434","article-title":"Chronic Prostatitis\/Chronic Pelvic Pain Syndrome Induces Metabolomic Changes in Expressed Prostatic Secretions and Plasma","volume":"27","author":"Zhang","year":"2025","journal-title":"Asian J. Androl."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"He, J., Han, Z., Luo, W., Shen, J., Xie, F., Liao, L., Zou, G., Luo, X., Guo, Z., and Li, Y. (2023). Serum Organic Acid Metabolites Can Be Used as Potential Biomarkers to Identify Prostatitis, Benign Prostatic Hyperplasia, and Prostate Cancer. Front. Immunol., 13.","DOI":"10.3389\/fimmu.2022.998447"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"G\u00f3mez-Cebri\u00e1n, N., Rojas-Benedicto, A., Albors-Vaquer, A., L\u00f3pez-Guerrero, J.A., Pineda-Lucena, A., and Puchades-Carrasco, L. (2019). Metabolomics Contributions to the Discovery of Prostate Cancer Biomarkers. Metabolites, 9.","DOI":"10.3390\/metabo9030048"},{"key":"ref_16","first-page":"166910","article-title":"How Far Are We from Reliable Metabolomics-Based Biomarkers? The Often-Overlooked Importance of Addressing Inter-Individual Variability Factors","volume":"1870","year":"2024","journal-title":"Biochim. Biophys. Acta (BBA)-Mol. Basis Dis."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1038\/s44222-023-00023-x","article-title":"Translating Metabolomics into Clinical Practice","volume":"1","author":"Kirwan","year":"2023","journal-title":"Nat. Rev. Bioeng."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Di Minno, A., Gelzo, M., Caterino, M., Costanzo, M., Ruoppolo, M., and Castaldo, G. (2022). Challenges in Metabolomics-Based Tests, Biomarkers Revealed by Metabolomic Analysis, and the Promise of the Application of Metabolomics in Precision Medicine. Int. J. Mol. Sci., 23.","DOI":"10.3390\/ijms23095213"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Sanches, P.H.G., de Melo, N.C., Porcari, A.M., and de Carvalho, L.M. (2024). Integrating Molecular Perspectives: Strategies for Comprehensive Multi-Omics Integrative Data Analysis and Machine Learning Applications in Transcriptomics, Proteomics, and Metabolomics. Biology, 13.","DOI":"10.3390\/biology13110848"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"117333","DOI":"10.1016\/j.trac.2023.117333","article-title":"Machine Learning Facilitates the Application of Mass Spectrometry-Based Metabolomics to Clinical Analysis: A Review of Early Diagnosis of High Mortality Rate Cancers","volume":"168","author":"Ngan","year":"2023","journal-title":"TrAC Trends Anal. Chem."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"7043","DOI":"10.1039\/D4AY01109K","article-title":"Discrimination of Serum Samples of Prostate Cancer and Benign Prostatic Hyperplasia with 1H-NMR Metabolomics","volume":"16","author":"Zniber","year":"2024","journal-title":"Anal. Methods"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1038\/s41585-019-0193-3","article-title":"A New Era: Artificial Intelligence and Machine Learning in Prostate Cancer","volume":"16","author":"Goldenberg","year":"2019","journal-title":"Nat. Rev. Urol."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Sun, L., Fan, X., Zhao, Y., Zhang, Q., and Jiang, M. (2024). Deep Learning-Based Metabolomics Data Study of Prostate Cancer. BMC Bioinform., 25.","DOI":"10.1186\/s12859-024-06016-w"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1186\/s40364-025-00804-z","article-title":"High-Throughput LDI MS Technology Decodes the Distinct Metabolic Landscape of Prostate Cancer in a Large-Scale Cohort","volume":"13","author":"Jiang","year":"2025","journal-title":"Biomark. Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"8118","DOI":"10.1038\/s41467-025-63536-6","article-title":"Knowledge and Data-Driven Two-Layer Networking for Accurate Metabolite Annotation in Untargeted Metabolomics","volume":"16","author":"Zhang","year":"2025","journal-title":"Nat. Commun."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"12925","DOI":"10.1021\/acs.analchem.0c01493","article-title":"Five Easy Metrics of Data Quality for LC\u2013MS-Based Global Metabolomics","volume":"92","author":"Zhang","year":"2020","journal-title":"Anal. Chem."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Faquih, T., van Smeden, M., Luo, J., le Cessie, S., Kastenm\u00fcller, G., Krumsiek, J., Noordam, R., van Heemst, D., Rosendaal, F.R., and van Hylckama Vlieg, A. (2020). A Workflow for Missing Values Imputation of Untargeted Metabolomics Data. Metabolites, 10.","DOI":"10.3390\/metabo10120486"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"W436","DOI":"10.1093\/nar\/gkaa258","article-title":"NOREVA: Enhanced Normalization and Evaluation of Time-Course and Multiclass Metabolomic Data","volume":"48","author":"Yang","year":"2020","journal-title":"Nucleic Acids Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"5542","DOI":"10.1021\/acs.analchem.2c04402","article-title":"Critical Assessment of the Biomarker Discovery and Classification Methods for Multiclass Metabolomics","volume":"95","author":"Yang","year":"2023","journal-title":"Anal. Chem."},{"key":"ref_30","unstructured":"Lundberg, S.M., and Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing 30 Systems, Curran Associates, Inc."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.bbcan.2019.01.001","article-title":"Prostate Cancer-Specific Hallmarks of Amino Acids Metabolism: Towards a Paradigm of Precision Medicine","volume":"1871","author":"Strmiska","year":"2019","journal-title":"Biochim. Biophys. Acta (BBA) Rev. Cancer"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.ccell.2019.12.011","article-title":"Emerging Roles for Branched-Chain Amino Acid Metabolism in Cancer","volume":"37","author":"Sivanand","year":"2020","journal-title":"Cancer Cell"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1038\/nrm.2017.107","article-title":"Sphingolipids and Their Metabolism in Physiology and Disease","volume":"19","author":"Hannun","year":"2018","journal-title":"Nat. Rev. Mol. Cell Biol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"4279","DOI":"10.1038\/s41467-020-17645-z","article-title":"Caveolin-1-Mediated Sphingolipid Oncometabolism Underlies a Metabolic Vulnerability of Prostate Cancer","volume":"11","author":"Vykoukal","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1038\/bjc.2012.14","article-title":"Circulating Sphingosine-1-Phosphate and Erythrocyte Sphingosine Kinase-1 Activity as Novel Biomarkers for Early Prostate Cancer Detection","volume":"106","author":"Nunes","year":"2012","journal-title":"Br. J. Cancer"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1016\/j.biopha.2018.06.139","article-title":"Role of Oxidative Stress in Pathology of Chronic Prostatitis\/Chronic Pelvic Pain Syndrome and Male Infertility and Antioxidants Function in Ameliorating Oxidative Stress","volume":"106","author":"Ihsan","year":"2018","journal-title":"Biomed. Pharmacother."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Guerrero-Ochoa, P., Rodr\u00edguez-Zapater, S., Anel, A., Esteban, L.M., Cam\u00f3n-Fern\u00e1ndez, A., Espilez-Ortiz, R., Gil-Sanz, M.J., and Borque-Fernando, \u00c1. (2024). Prostate Cancer and the Mevalonate Pathway. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms25042152"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3320","DOI":"10.1158\/0008-5472.CAN-18-2529","article-title":"Upregulation of Scavenger Receptor B1 Is Required for Steroidogenic and Nonsteroidogenic Cholesterol Metabolism in Prostate Cancer","volume":"79","author":"Gordon","year":"2019","journal-title":"Cancer Res."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1002\/ijc.31313","article-title":"Metabolomics and Transcriptomics Profiles Reveal the Dysregulation of the Tricarboxylic Acid Cycle and Related Mechanisms in Prostate Cancer","volume":"143","author":"Shao","year":"2018","journal-title":"Int. J. Cancer"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Xu, H., Chen, Y., Gu, M., Liu, C., Chen, Q., Zhan, M., and Wang, Z. (2021). Fatty Acid Metabolism Reprogramming in Advanced Prostate Cancer. Metabolites, 11.","DOI":"10.3390\/metabo11110765"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"eaau5758","DOI":"10.1126\/scitranslmed.aau5758","article-title":"Suppressing Fatty Acid Uptake Has Therapeutic Effects in Preclinical Models of Prostate Cancer","volume":"11","author":"Watt","year":"2019","journal-title":"Sci. Transl. Med."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Li, J., Wu, B., Fan, G., Huang, J., Li, Z., and Cao, F. (2024). Lc\u2014Ms-Based Untargeted Metabolomics Reveals Potential Mechanisms of Histologic Chronic Inflammation Promoting Prostate Hyperplasia. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0314599"},{"key":"ref_43","first-page":"75","article-title":"Inflammatory Mechanisms and Oxidative Stress in Prostatitis: The Possible Role of Antioxidant Therapy","volume":"10","author":"Paulis","year":"2018","journal-title":"Res. Rep. Urol."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1002\/pros.23162","article-title":"Iterative Design of Emetine-Based Prodrug Targeting Fibroblast Activation Protein (FAP) and Dipeptidyl Peptidase IV DPPIV Using a Tandem Enzymatic Activation Strategy","volume":"76","author":"Akinboye","year":"2016","journal-title":"Prostate"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Xu, B., Chen, Y., Chen, X., Gan, L., Zhang, Y., Feng, J., and Yu, L. (2021). Metabolomics Profiling Discriminates Prostate Cancer from Benign Prostatic Hyperplasia Within the Prostate-Specific Antigen Gray Zone. Front. Oncol., 11.","DOI":"10.3389\/fonc.2021.730638"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Sha, C., Cuperlovic-Culf, M., and Hu, T. (2021). SMILE: Systems Metabolomics Using Interpretable Learning and Evolution. BMC Bioinform., 22.","DOI":"10.1186\/s12859-021-04209-1"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.1021\/jasms.3c00403","article-title":"Automated Machine Learning and Explainable AI (AutoML-XAI) for Metabolomics: Improving Cancer Diagnostics","volume":"35","author":"Bifarin","year":"2024","journal-title":"J. Am. Soc. Mass Spectrom."}],"container-title":["Metabolites"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2218-1989\/16\/4\/237\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:35:35Z","timestamp":1775190935000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2218-1989\/16\/4\/237"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,31]]},"references-count":47,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["metabo16040237"],"URL":"https:\/\/doi.org\/10.3390\/metabo16040237","relation":{},"ISSN":["2218-1989"],"issn-type":[{"value":"2218-1989","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,31]]}}}