{"title":"使用尿金属和人口统计数据预测老年人认知障碍的机器学习框架。","authors":"Fengchun Ren, Xiao Zhao, Qin Yang, Huaqiang Liao, Yudong Zhang, Xuemei Liu","doi":"10.3389/fgene.2025.1631228","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Cognitive impairment in older adults poses a significant global public health concern, with environmental metal exposure emerging as a major risk factor. However, the combined effects of multiple metals and the modulatory roles of demographic variables remain insufficiently explored.</p><p><strong>Methods: </strong>This study analyzed data from four NHANES cycles (1999-2000, 2001-2002, 2011-2012, 2013-2014), comprising 1,230 participants aged ≥ 60 years. Urinary concentrations of nine metals and creatinine were quantified in conjunction with demographic variables. Cognitive status was classified using data-driven quartile thresholds on the Digit Symbol Substitution Test, CERAD Word-Learning Test, and Animal Fluency tests. Six machine learning algorithms were trained and evaluated using sensitivity (SN), specificity (SP), accuracy (ACC), Matthews correlation coefficient (MCC) and AUC.</p><p><strong>Results: </strong>The eXtreme gradient boosting (XGBoost) model demonstrated superior performance across all metrics (SN = 0.78, SP = 0.84, ACC = 0.81, MCC = 0.62, AUC = 0.90), and was selected for subsequent interpretation. SHAP analysis identified educational level, age, race/ethnicity, and creatinine as primary predictors. Elevated thallium and molybdenum levels and reduced barium levels also contributed to cognitive risk. Ultimately, a user-friendly webserver was deployed for the predictive model and is freely accessed at http://bio-medical.online/admxp/.</p><p><strong>Discussion: </strong>The associated webserver enables accessible risk screening and underpins precision prevention strategies in aging populations.</p>","PeriodicalId":12750,"journal":{"name":"Frontiers in Genetics","volume":"16 ","pages":"1631228"},"PeriodicalIF":2.8000,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12237647/pdf/","citationCount":"0","resultStr":"{\"title\":\"A machine learning framework for predicting cognitive impairment in aging populations using urinary metal and demographic data.\",\"authors\":\"Fengchun Ren, Xiao Zhao, Qin Yang, Huaqiang Liao, Yudong Zhang, Xuemei Liu\",\"doi\":\"10.3389/fgene.2025.1631228\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction: </strong>Cognitive impairment in older adults poses a significant global public health concern, with environmental metal exposure emerging as a major risk factor. However, the combined effects of multiple metals and the modulatory roles of demographic variables remain insufficiently explored.</p><p><strong>Methods: </strong>This study analyzed data from four NHANES cycles (1999-2000, 2001-2002, 2011-2012, 2013-2014), comprising 1,230 participants aged ≥ 60 years. Urinary concentrations of nine metals and creatinine were quantified in conjunction with demographic variables. Cognitive status was classified using data-driven quartile thresholds on the Digit Symbol Substitution Test, CERAD Word-Learning Test, and Animal Fluency tests. Six machine learning algorithms were trained and evaluated using sensitivity (SN), specificity (SP), accuracy (ACC), Matthews correlation coefficient (MCC) and AUC.</p><p><strong>Results: </strong>The eXtreme gradient boosting (XGBoost) model demonstrated superior performance across all metrics (SN = 0.78, SP = 0.84, ACC = 0.81, MCC = 0.62, AUC = 0.90), and was selected for subsequent interpretation. SHAP analysis identified educational level, age, race/ethnicity, and creatinine as primary predictors. Elevated thallium and molybdenum levels and reduced barium levels also contributed to cognitive risk. Ultimately, a user-friendly webserver was deployed for the predictive model and is freely accessed at http://bio-medical.online/admxp/.</p><p><strong>Discussion: </strong>The associated webserver enables accessible risk screening and underpins precision prevention strategies in aging populations.</p>\",\"PeriodicalId\":12750,\"journal\":{\"name\":\"Frontiers in Genetics\",\"volume\":\"16 \",\"pages\":\"1631228\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2025-06-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12237647/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Genetics\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.3389/fgene.2025.1631228\",\"RegionNum\":3,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"GENETICS & HEREDITY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Genetics","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.3389/fgene.2025.1631228","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"GENETICS & HEREDITY","Score":null,"Total":0}
A machine learning framework for predicting cognitive impairment in aging populations using urinary metal and demographic data.
Introduction: Cognitive impairment in older adults poses a significant global public health concern, with environmental metal exposure emerging as a major risk factor. However, the combined effects of multiple metals and the modulatory roles of demographic variables remain insufficiently explored.
Methods: This study analyzed data from four NHANES cycles (1999-2000, 2001-2002, 2011-2012, 2013-2014), comprising 1,230 participants aged ≥ 60 years. Urinary concentrations of nine metals and creatinine were quantified in conjunction with demographic variables. Cognitive status was classified using data-driven quartile thresholds on the Digit Symbol Substitution Test, CERAD Word-Learning Test, and Animal Fluency tests. Six machine learning algorithms were trained and evaluated using sensitivity (SN), specificity (SP), accuracy (ACC), Matthews correlation coefficient (MCC) and AUC.
Results: The eXtreme gradient boosting (XGBoost) model demonstrated superior performance across all metrics (SN = 0.78, SP = 0.84, ACC = 0.81, MCC = 0.62, AUC = 0.90), and was selected for subsequent interpretation. SHAP analysis identified educational level, age, race/ethnicity, and creatinine as primary predictors. Elevated thallium and molybdenum levels and reduced barium levels also contributed to cognitive risk. Ultimately, a user-friendly webserver was deployed for the predictive model and is freely accessed at http://bio-medical.online/admxp/.
Discussion: The associated webserver enables accessible risk screening and underpins precision prevention strategies in aging populations.
Frontiers in GeneticsBiochemistry, Genetics and Molecular Biology-Molecular Medicine
CiteScore
5.50
自引率
8.10%
发文量
3491
审稿时长
14 weeks
期刊介绍:
Frontiers in Genetics publishes rigorously peer-reviewed research on genes and genomes relating to all the domains of life, from humans to plants to livestock and other model organisms. Led by an outstanding Editorial Board of the world’s leading experts, this multidisciplinary, open-access journal is at the forefront of communicating cutting-edge research to researchers, academics, clinicians, policy makers and the public.
The study of inheritance and the impact of the genome on various biological processes is well documented. However, the majority of discoveries are still to come. A new era is seeing major developments in the function and variability of the genome, the use of genetic and genomic tools and the analysis of the genetic basis of various biological phenomena.