{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T10:00:47Z","timestamp":1784800847067,"version":"3.55.0"},"reference-count":35,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec id=\"j_med-2026-1415_abs_001\">\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>The diagnosis of Wilson disease (WD) is complicated by heterogeneous clinical phenotypes and inadequate performance of routine biomarkers. This study sought to screen age-specific urinary metabolic biomarkers to assist WD diagnosis via ensemble tree-based machine learning algorithms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"j_med-2026-1415_abs_002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Sixty participants were enrolled, comprising 30 WD patients (10 pediatric, 20 adult) and 30 healthy controls. Morning urine samples were analyzed using UPLC-Q-TOF-MS in both ionization modes. Orthogonal partial least squares discriminant analysis identified differential metabolites. Four ensemble algorithms (Random Forest, GBDT, XGBoost, LightGBM) were compared using nested cross-validation to minimize overfitting risk. LASSO regression selected optimal metabolite panels. Model performance was evaluated using 5-fold cross-validation with AUC as the primary metric.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"j_med-2026-1415_abs_003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>XGBoost achieved AUC values of 0.87\u00b10.03 (pediatric) and 0.96\u00b10.02 (adult) in nested validation, with permutation testing confirming performance above chance levels (p&gt;0.001). Sixty-eight differential metabolites were identified in pediatric patients versus 109 in adults, with 15 metabolites consistently altered across both age groups. Pathway analysis revealed age-specific disruptions: nucleotide metabolism in pediatric patients and oxidative stress pathways in adults. LASSO feature selection identified 7 metabolites for pediatric and 3 for adult classification while maintaining high diagnostic accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"j_med-2026-1415_abs_004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study successfully developed the first age-specific metabolomics-based diagnostic approach for WD using ensemble machine learning. The distinct metabolic signatures between age groups provide mechanistic insights into WD pathophysiology and support personalized diagnostic strategies for improved patient outcomes. These exploratory findings require independent validation before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1515\/med-2026-1415","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T09:01:02Z","timestamp":1784797262000},"source":"Crossref","is-referenced-by-count":0,"title":["Identification of age-specific urinary metabolic biomarkers in Wilson disease using machine learning: a comparative study of ensemble tree models"],"prefix":"10.1515","volume":"21","author":[{"given":"Shuxia","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Pediatrics , Beijing Chaoyang Hospital, Capital Medical University , Beijing , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0425-9357","authenticated-orcid":false,"given":"Yuguo","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Occupational Diseases and Toxicology , Beijing Chaoyang Hospital , Beijing , China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"374","published-online":{"date-parts":[[2026,7,24]]},"reference":[{"key":"2026072309005482024_j_med-2026-1415_ref_001","doi-asserted-by":"crossref","unstructured":"Qiu, Y, Su, M, Xiao, X, Zhou, D, Xie, L. Metabolomic profiling of wilson disease, an inherited disorder of copper metabolism, and diseases with similar symptoms but normal copper metabolism. Orphanet J Rare Dis 2023;18:282. https:\/\/doi.org\/10.1186\/s13023-023-02900-5.","DOI":"10.1186\/s13023-023-02900-5"},{"key":"2026072309005482024_j_med-2026-1415_ref_002","doi-asserted-by":"crossref","unstructured":"Sarode, GV, Kim, K, Kieffer, DA, Shibata, NM, Litwin, T, Czlonkowska, A, et al.. Metabolomics profiles of patients with Wilson disease reveal a distinct metabolic signature. Metabolomics 2019;15:43. https:\/\/doi.org\/10.1007\/s11306-019-1505-6.","DOI":"10.1007\/s11306-019-1505-6"},{"key":"2026072309005482024_j_med-2026-1415_ref_003","doi-asserted-by":"crossref","unstructured":"Sanchez-Monteagudo, A, Ripolles, E, Berenguer, M, Espinos, C. Wilson\u2019s disease: facing the challenge of diagnosing a rare disease. Biomedicines 2021;9:1100. https:\/\/doi.org\/10.3390\/biomedicines9091100.","DOI":"10.3390\/biomedicines9091100"},{"key":"2026072309005482024_j_med-2026-1415_ref_004","doi-asserted-by":"crossref","unstructured":"Salman, HM, Amin, M, Syed, J, Sarfraz, Z, Sarfraz, A, Sarfraz, M, et al.. Biochemical testing for the diagnosis of wilson\u2019s disease: a systematic review. J\u00a0Clin Lab Anal 2022;36:e24191. https:\/\/doi.org\/10.1002\/jcla.24191.","DOI":"10.1002\/jcla.24191"},{"key":"2026072309005482024_j_med-2026-1415_ref_005","doi-asserted-by":"crossref","unstructured":"Lorenzen, C, Dons, K, Garcia-Sola, C, Forns, X, Kirk, FT, Lynderup, EM, et al.. Relative exchangeable copper, exchangeable copper and total copper in the diagnosis of wilson disease. Liver Int 2025;45:e70089. https:\/\/doi.org\/10.1111\/liv.70089.","DOI":"10.1111\/liv.70089"},{"key":"2026072309005482024_j_med-2026-1415_ref_006","doi-asserted-by":"crossref","unstructured":"Ryan, A, Nevitt, SJ, Tuohy, O, Cook, P. Biomarkers for diagnosis of wilson\u2019s disease. Cochrane Database Syst Rev 2019;19:CD012267. https:\/\/doi.org\/10.1002\/14651858.CD012267.pub2.","DOI":"10.1002\/14651858.CD012267.pub2"},{"key":"2026072309005482024_j_med-2026-1415_ref_007","doi-asserted-by":"crossref","unstructured":"Ferenci, P, Stremmel, W, Czlonkowska, A, Szalay, F, Viveiros, A, Stattermayer, AF, et al.. Age and sex but not ATP7B genotype effectively influence the clinical phenotype of wilson disease. Hepatology 2019;69:1464\u201376. https:\/\/doi.org\/10.1002\/hep.30280.","DOI":"10.1002\/hep.30280"},{"key":"2026072309005482024_j_med-2026-1415_ref_008","doi-asserted-by":"crossref","unstructured":"Cai, L, Huang, X, Ye, Y, Yang, D, Xie, L, Fu, D, et al.. Role of gender and age in features of wilson\u2019s disease. Front Neurol 2023;14:1176946. https:\/\/doi.org\/10.3389\/fneur.2023.1176946.","DOI":"10.3389\/fneur.2023.1176946"},{"key":"2026072309005482024_j_med-2026-1415_ref_009","doi-asserted-by":"crossref","unstructured":"Wang, X, Xu, X, Jia, R, Xu, Y, Hu, P. UPLC-Q-TOF-MS-based unbiased serum metabolomics investigation of cholangiocarcinoma. Front Mol Biosci 2025;12:1549223. https:\/\/doi.org\/10.3389\/fmolb.2025.1549223.","DOI":"10.3389\/fmolb.2025.1549223"},{"key":"2026072309005482024_j_med-2026-1415_ref_010","doi-asserted-by":"crossref","unstructured":"Zhang, D, Li, Y, Liang, M, Liang, Y, Tian, J, He, Q, et al.. LC-MS\/MS based metabolomics and proteomics reveal candidate biomarkers and molecular mechanism of early IgA nephropathy. Clin Proteom 2022;19:51. https:\/\/doi.org\/10.1186\/s12014-022-09387-5.","DOI":"10.1186\/s12014-022-09387-5"},{"key":"2026072309005482024_j_med-2026-1415_ref_011","doi-asserted-by":"crossref","unstructured":"Pang, Z, Xu, L, Viau, C, Lu, Y, Salavati, R, Basu, N, et al.. MetaboAnalystR 4.0: a unified LC-MS workflow for global metabolomics. Nat Commun 2024;15:3675. https:\/\/doi.org\/10.1038\/s41467-024-48009-6.","DOI":"10.1038\/s41467-024-48009-6"},{"key":"2026072309005482024_j_med-2026-1415_ref_012","doi-asserted-by":"crossref","unstructured":"Guan, S, Liu, K, Liu, Z, Zhou, L, Jia, B, Wang, Z, et al.. UPLC-Q-TOF\/MS-based plasma and urine metabolomics contribute to the diagnosis of sepsis. J\u00a0Proteome Res 2022;21:209\u201319. https:\/\/doi.org\/10.1021\/acs.jproteome.1c00777.","DOI":"10.1021\/acs.jproteome.1c00777"},{"key":"2026072309005482024_j_med-2026-1415_ref_013","doi-asserted-by":"crossref","unstructured":"Armbruster, MR, Grady, SF, Cho, K, Patti, GJ, Bythell, BJ, Arnatt, CK, et al.. High-throughput metabolomics using 96-plex isotope tagging. Anal Chem 2024;96:12937\u201342. https:\/\/doi.org\/10.1021\/acs.analchem.4c02279.","DOI":"10.1021\/acs.analchem.4c02279"},{"key":"2026072309005482024_j_med-2026-1415_ref_014","doi-asserted-by":"crossref","unstructured":"Ghafari, N, Sleno, L. Challenges and recent advances in quantitative mass spectrometry-based metabolomics. Anal Sci Adv 2024;5:e2400007. https:\/\/doi.org\/10.1002\/ansa.202400007.","DOI":"10.1002\/ansa.202400007"},{"key":"2026072309005482024_j_med-2026-1415_ref_015","doi-asserted-by":"crossref","unstructured":"Broeckling, CD, Beger, RD, Cheng, LL, Cumeras, R, Cuthbertson, DJ, Dasari, S, et al.. Current practices in LC-MS untargeted metabolomics: a scoping review on the use of pooled quality control samples. Anal Chem 2023;95:18645\u201354. https:\/\/doi.org\/10.1021\/acs.analchem.3c02924.","DOI":"10.1021\/acs.analchem.3c02924"},{"key":"2026072309005482024_j_med-2026-1415_ref_016","doi-asserted-by":"crossref","unstructured":"Chen, Y, Wang, B, Zhao, Y, Shao, X, Wang, M, Ma, F, et al.. Metabolomic machine learning predictor for diagnosis and prognosis of gastric cancer. Nat Commun 2024;15:1657. https:\/\/doi.org\/10.1038\/s41467-024-46043-y.","DOI":"10.1038\/s41467-024-46043-y"},{"key":"2026072309005482024_j_med-2026-1415_ref_017","doi-asserted-by":"crossref","unstructured":"Acharjee, A, Larkman, J, Xu, Y, Cardoso, VR, Gkoutos, GV. A random forest based biomarker discovery and power analysis framework for diagnostics research. BMC Med Genom 2020;13:178. https:\/\/doi.org\/10.1186\/s12920-020-00826-6.","DOI":"10.1186\/s12920-020-00826-6"},{"key":"2026072309005482024_j_med-2026-1415_ref_018","doi-asserted-by":"crossref","unstructured":"Zhang, C, Lei, X, Liu, L. Predicting metabolite-disease associations based on LightGBM model. Front Genet 2021;12:660275. https:\/\/doi.org\/10.3389\/fgene.2021.660275.","DOI":"10.3389\/fgene.2021.660275"},{"key":"2026072309005482024_j_med-2026-1415_ref_019","doi-asserted-by":"crossref","unstructured":"Arslan, AK, Yagin, FH, Algarni, A, Karaaslan, E, Al-Hashem, F, Ardigo, LP, et al.. Enhancing type 2 diabetes mellitus prediction by integrating metabolomics and tree-based boosting approaches. Front Endocrinol 2024;15:1444282. https:\/\/doi.org\/10.3389\/fendo.2024.1444282.","DOI":"10.3389\/fendo.2024.1444282"},{"key":"2026072309005482024_j_med-2026-1415_ref_020","doi-asserted-by":"crossref","unstructured":"Li, L, Haijun, W, Tianyu, C, Wenjing, W, Zi, W, Yibing, C, et al.. Metabolomics and machine learning identify urine metabolic characteristics and potential biomarkers for severe mycoplasma pneumoniae pneumonia. Sci Rep 2025;15:17090. https:\/\/doi.org\/10.1038\/s41598-025-01895-2.","DOI":"10.1038\/s41598-025-01895-2"},{"key":"2026072309005482024_j_med-2026-1415_ref_021","doi-asserted-by":"crossref","unstructured":"She, H, Du, Y, Du, Y, Tan, L, Yang, S, Luo, X, et al.. Metabolomics and machine learning approaches for diagnostic and prognostic biomarkers screening in sepsis. BMC Anesthesiol 2023;23:367. https:\/\/doi.org\/10.1186\/s12871-023-02317-4.","DOI":"10.1186\/s12871-023-02317-4"},{"key":"2026072309005482024_j_med-2026-1415_ref_022","doi-asserted-by":"crossref","unstructured":"Jiang, JJ, Sham, TT, Gu, XF, Chan, CO, Dong, NP, Lim, WH, et al.. Insights into serum metabolic biomarkers for early detection of incident diabetic kidney disease in Chinese patients with type 2 diabetes by random forest. Aging (Albany NY) 2024;16:3420\u2013530. https:\/\/doi.org\/10.18632\/aging.205542.","DOI":"10.18632\/aging.205542"},{"key":"2026072309005482024_j_med-2026-1415_ref_023","doi-asserted-by":"crossref","unstructured":"Hong, W, Zhou, X, Jin, S, Lu, Y, Pan, J, Lin, Q, et al.. A comparison of XGBoost, random forest, and nomograph for the prediction of disease severity in patients with COVID-19 pneumonia: implications of cytokine and immune cell profile. Front Cell Infect Microbiol 2022;12:819267. https:\/\/doi.org\/10.3389\/fcimb.2022.819267.","DOI":"10.3389\/fcimb.2022.819267"},{"key":"2026072309005482024_j_med-2026-1415_ref_024","doi-asserted-by":"crossref","unstructured":"AlMansoori, ME, Jemimah, S, Abuhantash, F, AlShehhi, A. Predicting early Alzheimer\u2019s with blood biomarkers and clinical features. Sci Rep 2024;14:6039. https:\/\/doi.org\/10.1038\/s41598-024-56489-1.","DOI":"10.1038\/s41598-024-56489-1"},{"key":"2026072309005482024_j_med-2026-1415_ref_025","doi-asserted-by":"crossref","unstructured":"Mahajan, P, Uddin, S, Hajati, F, Moni, MA, Ensemble learning for disease prediction: a review. Healthcare (Basel) 2023;11:1808. https:\/\/doi.org\/ 10.3390\/healthcare11121808.","DOI":"10.3390\/healthcare11121808"},{"key":"2026072309005482024_j_med-2026-1415_ref_026","doi-asserted-by":"crossref","unstructured":"Yang, W, Xu, S, Zhou, M, Chan, P. Aging-related biomarkers for the diagnosis of parkinson\u2019s disease based on bioinformatics analysis and machine learning. Aging (Albany NY) 2024;16:12191\u2013208. https:\/\/doi.org\/10.18632\/aging.205954.","DOI":"10.18632\/aging.205954"},{"key":"2026072309005482024_j_med-2026-1415_ref_027","doi-asserted-by":"crossref","unstructured":"Mohr, I, Weiss, KH. Biochemical markers for the diagnosis and monitoring of wilson disease. Clin Biochem Rev 2019;40:59\u201377. https:\/\/doi.org\/10.33176\/AACB-18-00014.","DOI":"10.33176\/AACB-18-00014"},{"key":"2026072309005482024_j_med-2026-1415_ref_028","doi-asserted-by":"crossref","unstructured":"Jurich, CP, Jeppesen, MJ, Sakallioglu, IT, De Lima Leite, A, Yesselman, JD, Powers, R, et al.. Simulated LC\u2013MS data set for assessing the metabolomics data processing pipeline implemented into MVAPACK. Analytical chemistry 2024;96:12943\u201356. https:\/\/doi.org\/10.1021\/acs.analchem.3c04979.","DOI":"10.1021\/acs.analchem.3c04979"},{"key":"2026072309005482024_j_med-2026-1415_ref_029","doi-asserted-by":"crossref","unstructured":"Wang, L, Fan, Z, Ma, S, Wu, S, Ma, C, Zeng, H, et al.. UPLC-Q-TOF\/MS based metabolite profiling and quality marker constituents screening of root, stem and rhizome extracts of ilex asprella. Fitoterapia 2024;173:105832. https:\/\/doi.org\/10.1016\/j.fitote.2024.105832.","DOI":"10.1016\/j.fitote.2024.105832"},{"key":"2026072309005482024_j_med-2026-1415_ref_030","doi-asserted-by":"crossref","unstructured":"Bansal, Y, Mujib, A, Mamgain, J, Syeed, R, Mohsin, M, Nafees, A, et al.. Integrated GC-MS and UPLC-ESI-QTOF-MS based untargeted metabolomics analysis of in\u00a0vitro raised tissues of Digitalis purpurea L. Front Plant Sci 2024;15:1433634. https:\/\/doi.org\/10.3389\/fpls.2024.1433634.","DOI":"10.3389\/fpls.2024.1433634"},{"key":"2026072309005482024_j_med-2026-1415_ref_031","doi-asserted-by":"crossref","unstructured":"Belhadi, A, Djenouri, Y, Belbachir, AN. Ensemble fuzzy deep learning for brain tumor detection. Sci Rep 2025;15:6124. https:\/\/doi.org\/10.1038\/s41598-025-90572-5.","DOI":"10.1038\/s41598-025-90572-5"},{"key":"2026072309005482024_j_med-2026-1415_ref_032","doi-asserted-by":"crossref","unstructured":"Abdullah, TA, Zahid, MSM, Ali, W. A review of interpretable ML in healthcare: taxonomy, applications, challenges, and future directions. Symmetry 2021;13:2439. https:\/\/doi.org\/10.3390\/sym13122439.","DOI":"10.3390\/sym13122439"},{"key":"2026072309005482024_j_med-2026-1415_ref_033","doi-asserted-by":"crossref","unstructured":"Johnson, MD, Kehl-Fie, TE, Klein, R, Kelly, J, Burnham, C, Mann, B, et al.. Role of copper efflux in pneumococcal pathogenesis and resistance to macrophage-mediated immune clearance. Infect Immun 2015;83:1684\u201394. https:\/\/doi.org\/10.1128\/iai.03015-14.","DOI":"10.1128\/IAI.03015-14"},{"key":"2026072309005482024_j_med-2026-1415_ref_034","doi-asserted-by":"crossref","unstructured":"Lutsenko, S, LeShane, ES, Shinde, U. Biochemical basis of regulation of human copper-transporting ATPases. Arch Biochem Biophys 2007;463:134\u201348. https:\/\/doi.org\/10.1016\/j.abb.2007.04.013.","DOI":"10.1016\/j.abb.2007.04.013"},{"key":"2026072309005482024_j_med-2026-1415_ref_035","doi-asserted-by":"crossref","unstructured":"Hatori, Y, Lutsenko, S. The role of copper chaperone Atox1 in coupling redox homeostasis to intracellular copper distribution. Antioxidants 2016;5:25. https:\/\/doi.org\/10.3390\/antiox5030025.","DOI":"10.3390\/antiox5030025"}],"container-title":["Open Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/med-2026-1415\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/med-2026-1415\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T09:01:36Z","timestamp":1784797296000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/med-2026-1415\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,7,24]]},"published-print":{"date-parts":[[2026,1,23]]}},"alternative-id":["10.1515\/med-2026-1415"],"URL":"https:\/\/doi.org\/10.1515\/med-2026-1415","relation":{},"ISSN":["2391-5463"],"issn-type":[{"value":"2391-5463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]},"article-number":"20261415"}}