{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T15:16:35Z","timestamp":1786115795078,"version":"build-2736575974"},"reference-count":23,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82501462"],"award-info":[{"award-number":["82501462"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82471222"],"award-info":[{"award-number":["82471222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M781354"],"award-info":[{"award-number":["2025M781354"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Neuroprotection"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Current diagnostic approaches for Alzheimer's disease (AD) largely rely on cerebrospinal fluid biomarkers and neuroimaging, which may be invasive, costly, and not readily accessible in routine clinical settings. We investigated whether serum elemental profiling combined with machine learning could provide complementary information for AD identification and exploratory cognitive score prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective cross\u2010sectional study included 874 participants enrolled between 2017 and 2023 from the Brain Aging National Cohort\u2013Peking Union Medical College cohort, comprising 427 cognitively normal controls (NCs) and 447 patients with clinically defined AD. Serum concentrations of 20 elements were quantified by inductively coupled plasma mass spectrometry. Associations between serum element concentrations and AD status were evaluated using age\u2010 and sex\u2010adjusted logistic regression models with false discovery rate (FDR) correction. Associations with Mini\u2010Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA) scores were assessed using linear regression models with FDR correction. Machine learning classification models were developed for AD identification, whereas regression models were developed for exploratory MMSE and MoCA score prediction. Model performance was evaluated in an internal hold\u2010out test set.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Age did not differ significantly between NC and AD participants (66.4\u2009\u00b1\u20099.9 vs. 67.1\u2009\u00b1\u20099.0 years;\n                      <jats:italic>t<\/jats:italic>\n                      (872)\u2009=\u2009\u22121.13,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.260), whereas the proportion of women was higher in the AD group than in the NC group (255\/447 [57.0%] vs. 211\/427 [49.4%];\n                      <jats:italic>\u03c7<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      (1)\u2009=\u20095.11,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.024). MMSE scores were significantly lower in patients with AD than in NC participants (AD:\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009277, median [interquartile range (IQR)]\u2009=\u200924 [19\u201327]; NC:\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009427, median [IQR]\u2009=\u200930 [30\u201330]; Mann\u2013Whitney\n                      <jats:italic>U<\/jats:italic>\n                      \u2009=\u20093043.5,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001), as were MoCA scores (AD:\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009240, median [IQR] = 18.00 [14.00\u201320.25]; NC:\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009427, median [IQR]\u2009=\u200930 [30.00\u201330.00]; Mann\u2013Whitney\n                      <jats:italic>U<\/jats:italic>\n                      \u2009=\u200913.5,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001). After adjustment for age and sex, higher serum lead (Pb) and tin (Sn) levels were associated with increased odds of AD (Pb: odds ratio [OR]\u2009=\u20094.95, 95% confidence interval [CI]: 3.42\u20137.37; Sn: OR\u2009=\u20091.45, 95% CI: 1.20\u20131.78), whereas higher serum antimony, nickel, manganese, cobalt, selenium, and calcium levels were associated with lower odds of AD (OR range: 0.50\u20130.81; all FDR\u2010adjusted\n                      <jats:italic>p<\/jats:italic>\n                      \u2010values\u2009&lt;\u20090.05). Among the eight classification models evaluated in the internal hold\u2010out test set, the random forest model showed the highest apparent performance for distinguishing AD from NC, achieving an accuracy of 88% and an area under the receiver operating (AUC) (acharacteristic curv of 0.94. Among the three regression models evaluated, the random forest regression showed the highest apparent performance for cognitive score prediction, yielding the strongest correlations between predicted and observed scores for both MMSE (\n                      <jats:italic>r<\/jats:italic>\n                      \u2009=\u20090.48,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001) and MoCA (\n                      <jats:italic>r<\/jats:italic>\n                      \u2009=\u20090.62,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Serum elemental profiles combined with machine learning may provide a minimally invasive and accessible complementary approach for AD identification and cognitive assessment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/nep3.70054","type":"journal-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T05:41:37Z","timestamp":1785994897000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Serum elemental profile\u2010based machine learning models for Alzheimer's disease identification and cognitive score prediction"],"prefix":"10.1002","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8550-7641","authenticated-orcid":false,"given":"Haotian","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Immunology, State Key Laboratory of Complex, Severe, and Rare Diseases, Institute of Basic Medical Sciences &amp; School of Basic Medicine Chinese Academy of Medical Sciences &amp; Peking Union Medical College Beijing China"},{"name":"Department of Human Anatomy, Histology and Embryology, Neuroscience Center, Institute of Basic Medical Sciences &amp; School of Basic Medicine Chinese Academy of Medical Sciences &amp; Peking Union Medical College Beijing China"},{"name":"National Human Brain Bank for Development and Function Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinnan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Human Anatomy, Histology and Embryology, Neuroscience Center, Institute of Basic Medical Sciences &amp; School of Basic Medicine Chinese Academy of Medical Sciences &amp; Peking Union Medical College Beijing China"},{"name":"National Human Brain Bank for Development and Function Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yashuang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Immunology, State Key Laboratory of Complex, Severe, and Rare Diseases, Institute of Basic Medical Sciences &amp; School of Basic Medicine Chinese Academy of Medical Sciences &amp; Peking Union Medical College Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Immunology, State Key Laboratory of Complex, Severe, and Rare Diseases, Institute of Basic Medical Sciences &amp; School of Basic Medicine Chinese Academy of Medical Sciences &amp; Peking Union Medical College Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Human Anatomy, Histology and Embryology, Neuroscience Center, Institute of Basic Medical Sciences &amp; School of Basic Medicine Chinese Academy of Medical Sciences &amp; Peking Union Medical College Beijing China"},{"name":"National Human Brain Bank for Development and Function Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Human Anatomy, Histology and Embryology, Neuroscience Center, Institute of Basic Medical Sciences &amp; School of Basic Medicine Chinese Academy of Medical Sciences &amp; Peking Union Medical College Beijing China"},{"name":"National Human Brain Bank for Development and Function Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9907-512X","authenticated-orcid":false,"given":"Wei","family":"Ge","sequence":"additional","affiliation":[{"name":"Department of Immunology, State Key Laboratory of Complex, Severe, and Rare Diseases, Institute of Basic Medical Sciences &amp; School of Basic Medicine Chinese Academy of Medical Sciences &amp; Peking Union Medical College Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"crossref","first-page":"e105","DOI":"10.1016\/S2468-2667(21)00249-8","article-title":"Estimation of the global prevalence of dementia in 2019 and forecasted prevalence in 2050: an analysis for the Global Burden of Disease Study 2019","volume":"7","author":"Nichols E","year":"2022","journal-title":"Lancet Public Health"},{"key":"e_1_2_11_3_1","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/s41392-024-02071-0","article-title":"Homeostasis and metabolism of iron and other metal ions in neurodegenerative diseases","volume":"10","author":"Chen L","year":"2025","journal-title":"Signal Transduct Target Ther"},{"key":"e_1_2_11_4_1","doi-asserted-by":"crossref","first-page":"1215","DOI":"10.3233\/JAD-200282","article-title":"Heavy metals exposure and Alzheimer's disease and related dementias","volume":"76","author":"Bakulski KM","year":"2020","journal-title":"J Alzheimers Dis"},{"key":"e_1_2_11_5_1","doi-asserted-by":"crossref","first-page":"361","DOI":"10.3233\/JAD-170811","article-title":"Circulatory levels of toxic metals (aluminum, cadmium, mercury, lead) in patients with Alzheimer's disease: a quantitative meta\u2010analysis and systematic review","volume":"62","author":"Xu L","year":"2018","journal-title":"J Alzheimers Dis"},{"key":"e_1_2_11_6_1","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.neuro.2019.07.007","article-title":"The role of zinc, copper, manganese and iron in neurodegenerative diseases","volume":"74","author":"Mezzaroba L","year":"2019","journal-title":"Neurotoxicology"},{"key":"e_1_2_11_7_1","doi-asserted-by":"crossref","first-page":"81","DOI":"10.3233\/JAD-2011-110414","article-title":"Selenium and Alzheimer's disease: a systematic review","volume":"26","author":"Loef M","year":"2011","journal-title":"J Alzheimers Dis"},{"key":"e_1_2_11_8_1","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1007\/s12603-023-1997-7","article-title":"Association between iodized salt intake and cognitive function in older adults in China","volume":"27","author":"Wu MN","year":"2023","journal-title":"J Nutr Health Aging"},{"key":"e_1_2_11_9_1","article-title":"The Brain Aging National Cohort\u2010PUMC: study design and baseline characteristics","volume":"2","author":"Han F","year":"2023","journal-title":"Human Brain"},{"key":"e_1_2_11_10_1","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1016\/j.tips.2018.10.001","article-title":"Copper and zinc dysregulation in Alzheimer's disease","volume":"39","author":"Sensi SL","year":"2018","journal-title":"Trends Pharmacol Sci"},{"key":"e_1_2_11_11_1","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1001\/archpsyc.55.9.809","article-title":"The relationships between age, sex, and the incidence of dementia and Alzheimer disease: a meta\u2010analysis","volume":"55","author":"Gao S","year":"1998","journal-title":"Arch Gen Psychiatry"},{"key":"e_1_2_11_12_1","doi-asserted-by":"crossref","DOI":"10.1038\/srep22769","article-title":"Distinctive pattern of serum elements during the progression of Alzheimer's disease","volume":"6","author":"Paglia G","year":"2016","journal-title":"Sci Rep"},{"key":"e_1_2_11_13_1","doi-asserted-by":"crossref","first-page":"1871","DOI":"10.1007\/s12011-024-04326-x","article-title":"Alzheimer's disease and circulatory imbalance of toxic heavy metals: a systematic review and meta\u2010analysis of clinical studies","volume":"203","author":"Kooshki A","year":"2025","journal-title":"Biol Trace Elem Res"},{"key":"e_1_2_11_14_1","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1002\/ajim.20434","article-title":"Effects of lead on the adult brain: a 15\u2010year exploration","volume":"50","author":"Stewart WF","year":"2007","journal-title":"Am J Ind Med"},{"key":"e_1_2_11_15_1","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/0952-3278(91)90035-4","article-title":"Tin and fatty acids in dementia","volume":"43","author":"Corrigan FM","year":"1991","journal-title":"Prostaglandins Leukot Essent Fatty Acids"},{"key":"e_1_2_11_16_1","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1126\/science.179.4073.588","article-title":"Selenium: biochemical role as a component of glutathione peroxidase","volume":"179","author":"Rotruck JT","year":"1973","journal-title":"Science"},{"key":"e_1_2_11_17_1","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1016\/j.taap.2012.08.033","article-title":"Augmentation of aerobic respiration and mitochondrial biogenesis in skeletal muscle by hypoxia preconditioning with cobalt chloride","volume":"264","author":"Saxena S","year":"2012","journal-title":"Toxicol Appl Pharmacol"},{"key":"e_1_2_11_18_1","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1038\/ng1295-376","article-title":"Dilated cardiomyopathy and neonatal lethality in mutant mice lacking manganese superoxide dismutase","volume":"11","author":"Li Y","year":"1995","journal-title":"Nat Genet"},{"key":"e_1_2_11_19_1","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1186\/s12302-024-00980-z","article-title":"Circulatory trace element variations in Alzheimer's disease: a systematic review and meta\u2010analysis","volume":"36","author":"Qing Y","year":"2024","journal-title":"Environ Sci Eur"},{"key":"e_1_2_11_20_1","first-page":"112","article-title":"Metals dyshomeostasis in Alzheimer's disease: a systematic review","volume":"2","author":"Lucaroni F","year":"2017","journal-title":"Biomed Prev"},{"key":"e_1_2_11_21_1","doi-asserted-by":"crossref","first-page":"2135","DOI":"10.1002\/alz.12948","article-title":"Interpretable machine learning for dementia: a systematic review","volume":"19","author":"Martin SA","year":"2023","journal-title":"Alzheimers Dement"},{"key":"e_1_2_11_22_1","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1111\/joim.12959","article-title":"Current and emerging avenues for Alzheimer's disease drug targets","volume":"286","author":"Loera\u2010Valencia R","year":"2019","journal-title":"J Intern Med"},{"key":"e_1_2_11_23_1","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1002\/nep3.23","article-title":"Preserving cognitive function in patients with Alzheimer's disease: the Alzheimer's disease neuroprotection research initiative (ADNRI)","volume":"1","author":"Liu J","year":"2023","journal-title":"Neuroprotection"},{"key":"e_1_2_11_24_1","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/s00439-016-1636-z","article-title":"Improved prediction of complex diseases by common genetic markers: state of the art and further perspectives","volume":"135","author":"M\u00fcller B","year":"2016","journal-title":"Hum Genet"}],"container-title":["Neuroprotection"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/nep3.70054","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/nep3.70054","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/nep3.70054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T05:41:41Z","timestamp":1785994901000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/nep3.70054"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":23,"alternative-id":["10.1002\/nep3.70054"],"URL":"https:\/\/doi.org\/10.1002\/nep3.70054","archive":["Portico"],"relation":{},"ISSN":["2770-7296","2770-730X"],"issn-type":[{"value":"2770-7296","type":"print"},{"value":"2770-730X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"assertion":[{"value":"2025-12-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"nep3.70054"}}