{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T22:24:35Z","timestamp":1787783075684,"version":"build-2784847793"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Aging Neurosci."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Conventional machine learning (ML) approaches for constructing biological age (BA) have predominantly relied on blood-based markers, limiting their scope. This study aims to develop and validate novel ML-based BA models using a comprehensive set of clinical, behavioral, and socioeconomic factors and evaluate their predictive performance for mortality.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We analyzed data from 24,985 participants in the National Health and Nutrition Examination Survey (NHANES) from 1999 to 2010, with follow-up extending to 31 December 2019, or until death or loss to follow-up. Thirty features, including blood and urine biochemistry, physical examination data, behavioral traits, and socioeconomic factors, were selected using the Least Absolute Shrinkage and Selection Operator (LASSO). These features were utilized to train deep neural networks (DNN) and ensemble learning models, specifically the Deep Biological Age (DBA) and Ensemble Biological Age (EnBA), with chronological age (CA) as the reference label. Model performance was assessed using mean absolute error (MAE), while interpretability was explored using Shapley Additive exPlanation (SHAP). Predictive accuracy of DBA and EnBA for mortality was compared with Phenotypic Age (PhenoAge) using the area under the curve (AUC) derived from Cox proportional hazards models and hazard ratios (HR), adjusted for demographics and lifestyle factors. Sensitivity analyses were performed to ensure robustness.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>DBA and EnBA accurately predicted actual age (MAE = 2.98 and 3.58 years, respectively) and demonstrated strong predictive capability for all-cause mortality, with AUCs of 0.896 (95% CI: 0.891\u20130.898) for DBA and 0.889 (95% CI: 0.884\u20130.894) for EnBA. Higher DBA and EnBA accelerations were significantly associated with increased mortality risk (HR = 1.059 and 1.039, respectively). SHAP analysis highlighted prescription medication usage, hepatitis B surface antibody status, and vigorous physical activity as the most influential features contributing to DBA predictions. Furthermore, BA acceleration was linked to elevated risk of death from specific chronic conditions, including cardiovascular and cerebrovascular diseases and cancer.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>Our study successfully developed and validated two ML-based BA models capable of accurately predicting both all-cause and cause-specific mortality. These findings suggest that the DBA and EnBA models hold promise for early identification of high-risk individuals, potentially facilitating timely preventive interventions and improving population health outcomes.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnagi.2025.1532884","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T05:36:15Z","timestamp":1752644175000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Development and validation of deep learning- and ensemble learning-based biological ages in the NHANES study"],"prefix":"10.3389","volume":"17","author":[{"given":"Yushu","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xifan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adila","family":"Abula","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"4801","DOI":"10.1093\/eurheartj\/ehac572","article-title":"Vigorous physical activity, incident heart disease, and cancer: How little is enough?","volume":"43","author":"Ahmadi","year":"2022","journal-title":"Eur. Heart J."},{"key":"B2","doi-asserted-by":"publisher","first-page":"1016","DOI":"10.1038\/s41591-024-03483-9","article-title":"Integrating the environmental and genetic architectures of aging and mortality.","volume":"31","author":"Argentieri","year":"2025","journal-title":"Nat. Med."},{"key":"B3","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1016\/0531-5565(88)90025-3","article-title":"Biomarkers of aging.","volume":"23","author":"Baker","year":"1988","journal-title":"Exp. Gerontol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"3249","DOI":"10.18632\/aging.101629","article-title":"PhotoAgeClock: Deep learning algorithms for development of non-invasive visual biomarkers of aging.","volume":"10","author":"Bobrov","year":"2018","journal-title":"Aging"},{"key":"B5","doi-asserted-by":"publisher","first-page":"103023","DOI":"10.1016\/j.autneu.2022.103023","article-title":"Exploring the interplay between mechanisms of neuroplasticity and cardiovascular health in aging adults: A multiple linear regression analysis study.","volume":"242","author":"Cabral","year":"2022","journal-title":"Auton Neurosci."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1016\/S0140-6736(09)61460-4","article-title":"Ageing populations: The challenges ahead.","volume":"374","author":"Christensen","year":"2009","journal-title":"Lancet"},{"key":"B7","doi-asserted-by":"publisher","first-page":"100379","DOI":"10.1016\/j.cosrev.2021.100379","article-title":"A survey on deep learning and its applications.","volume":"40","author":"Dong","year":"2021","journal-title":"Comput. Sci. Rev."},{"key":"B8","doi-asserted-by":"publisher","first-page":"101743","DOI":"10.1016\/j.arr.2022.101743","article-title":"Epigenetic clock: A promising biomarker and practical tool in aging.","volume":"81","author":"Duan","year":"2022","journal-title":"Ageing Res. Rev."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1252","DOI":"10.14336\/AD.2020.1202","article-title":"DeepMAge: A methylation aging clock developed with deep learning.","volume":"12","author":"Galkin","year":"2021","journal-title":"Aging Dis."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1118","DOI":"10.1056\/NEJMra031087","article-title":"Hepatitis B virus infection\u2013natural history and clinical consequences.","volume":"350","author":"Ganem","year":"2004","journal-title":"N. Engl. J. Med."},{"key":"B11","doi-asserted-by":"publisher","first-page":"2277","DOI":"10.1038\/s41467-023-38013-7","article-title":"Accelerated biological aging and risk of depression and anxiety: Evidence from 424,299 UK Biobank participants.","volume":"14","author":"Gao","year":"2023","journal-title":"Nat. Commun."},{"key":"B12","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s10654-021-00797-7","article-title":"Exploring domains, clinical implications and environmental associations of a deep learning marker of biological ageing.","volume":"37","author":"Gialluisi","year":"2022","journal-title":"Eur. J. Epidemiol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1007\/s40121-023-00766-5","article-title":"Effect of Anti-HBs on mortality among resolved HBV infection: A population-based prospective cohort study.","volume":"12","author":"Huang","year":"2023","journal-title":"Infect. Dis. Ther."},{"key":"B14","doi-asserted-by":"publisher","first-page":"4241","DOI":"10.1007\/s11357-025-01577-x","article-title":"Construction and validation of a DNN-based biological age and its influencing factors in the China Kadoorie Biobank.","volume":"47","author":"Huang","year":"2025","journal-title":"Geroscience"},{"key":"B15","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1016\/j.cgh.2007.06.015","article-title":"Risk and predictors of mortality associated with chronic hepatitis B infection.","volume":"5","author":"Iloeje","year":"2007","journal-title":"Clin. Gastroenterol. Hepatol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"108891","DOI":"10.1016\/j.isci.2024.108891","article-title":"A biological age model based on physical examination data to predict mortality in a Chinese population.","volume":"27","author":"Jia","year":"2024","journal-title":"iScience"},{"key":"B17","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1038\/s44161-024-00438-8","article-title":"Accelerated biological aging elevates the risk of cardiometabolic multimorbidity and mortality.","volume":"3","author":"Jiang","year":"2024","journal-title":"Nat. Cardiovasc. Res."},{"key":"B18","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1016\/j.mad.2005.10.004","article-title":"A new approach to the concept and computation of biological age.","volume":"127","author":"Klemera","year":"2006","journal-title":"Mech. Ageing Dev."},{"key":"B19","doi-asserted-by":"publisher","first-page":"2795","DOI":"10.1007\/s11357-021-00480-5","article-title":"A toolkit for quantification of biological age from blood chemistry and organ function test data: Bioage.","volume":"43","author":"Kwon","year":"2021","journal-title":"Geroscience"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e2024329","DOI":"10.1001\/jamanetworkopen.2020.24329","article-title":"Association of neighborhood deprivation with epigenetic aging using 4 clock metrics.","volume":"3","author":"Lawrence","year":"2020","journal-title":"JAMA Netw. Open"},{"key":"B21","doi-asserted-by":"publisher","first-page":"573","DOI":"10.18632\/aging.101414","article-title":"An epigenetic biomarker of aging for lifespan and healthspan.","volume":"10","author":"Levine","year":"2018","journal-title":"Aging"},{"key":"B22","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.cell.2022.11.001","article-title":"Hallmarks of aging: An expanding universe.","volume":"186","author":"L\u00f3pez-Ot\u00edn","year":"2023","journal-title":"Cell"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.07874","article-title":"A unified approach to interpreting model predictions.","author":"Lundberg","year":"2017","journal-title":"arXiv [Preprint]"},{"key":"B24","doi-asserted-by":"publisher","first-page":"6115","DOI":"10.1007\/s11357-024-01186-0","article-title":"Clinical biomarker-based biological age predicts deaths in Brazilian adults: The ELSA-Brasil study.","volume":"46","author":"Machado","year":"2024","journal-title":"Geroscience"},{"key":"B25","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1038\/s41416-023-02288-w","article-title":"Clinical biomarker-based biological aging and risk of cancer in the UK Biobank.","volume":"129","author":"Mak","year":"2023","journal-title":"Br. J. Cancer"},{"key":"B26","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1038\/s41598-018-35704-w","article-title":"Blood biochemistry analysis to detect smoking status and quantify accelerated aging in smokers.","volume":"9","author":"Mamoshina","year":"2019","journal-title":"Sci. Rep."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1482","DOI":"10.1093\/gerona\/gly005","article-title":"Population specific biomarkers of human aging: A big data study using South Korean, Canadian, and Eastern European patient populations.","volume":"73","author":"Mamoshina","year":"2018","journal-title":"J. Gerontol. A Biol. Sci. Med. Sci."},{"key":"B28","doi-asserted-by":"publisher","first-page":"3758","DOI":"10.1016\/j.cell.2023.08.003","article-title":"Biomarkers of aging for the identification and evaluation of longevity interventions.","volume":"186","author":"Moqri","year":"2023","journal-title":"Cell"},{"key":"B29","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1038\/s41591-023-02784-9","article-title":"Validation of biomarkers of aging.","volume":"30","author":"Moqri","year":"2024","journal-title":"Nat. Med."},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.1109\/SACI58269.2023.10158652","article-title":"Machine learning and mathematical models for prediction of structural aging process","author":"Mudabbiruddin","year":"2023","journal-title":"Proceedings of the 2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)"},{"key":"B31","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1093\/gerona\/glx144","article-title":"Measures of biologic age in a community sample predict mortality and age-related disease: The framingham offspring study.","volume":"73","author":"Murabito","year":"2018","journal-title":"J. Gerontol. A Biol. Sci. Med. Sci."},{"key":"B32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0047-6374(88)90109-1","article-title":"Assessment of biological age by principal component analysis.","volume":"46","author":"Nakamura","year":"1988","journal-title":"Mech. Ageing Dev."},{"key":"B33","doi-asserted-by":"publisher","first-page":"1776","DOI":"10.1002\/ijc.31204","article-title":"Medication use and kidney cancer survival: A population-based study.","volume":"142","author":"Nayan","year":"2018","journal-title":"Int. J. Cancer"},{"key":"B34","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1038\/s41586-018-0457-8","article-title":"Facing up to the global challenges of ageing.","volume":"561","author":"Partridge","year":"2018","journal-title":"Nature"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1021","DOI":"10.18632\/aging.100968","article-title":"Deep biomarkers of human aging: Application of deep neural networks to biomarker development.","volume":"8","author":"Putin","year":"2016","journal-title":"Aging"},{"key":"B36","first-page":"1135","article-title":"\u201cWhy should I trust you?\u201d: Explaining the predictions of any classifier","author":"Ribeiro","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1161\/CIRCULATIONAHA.121.056456","article-title":"Epigenetic age and the risk of incident atrial fibrillation.","volume":"144","author":"Roberts","year":"2021","journal-title":"Circulation"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1002\/ana.26624","article-title":"Biological age acceleration and motoric cognitive risk syndrome.","volume":"93","author":"Sathyan","year":"2023","journal-title":"Ann. Neurol."},{"key":"B39","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature13458","article-title":"Dynamic and static maintenance of epigenetic memory in pluripotent and somatic cells.","volume":"513","author":"Shipony","year":"2014","journal-title":"Nature"},{"key":"B40","doi-asserted-by":"publisher","first-page":"2521","DOI":"10.1038\/s41591-022-02100-x","article-title":"Association of wearable device-measured vigorous intermittent lifestyle physical activity with mortality.","volume":"28","author":"Stamatakis","year":"2022","journal-title":"Nat. Med."},{"key":"B41","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1186\/s13054-020-03179-9","article-title":"Prediction of the development of acute kidney injury following cardiac surgery by machine learning.","volume":"24","author":"Tseng","year":"2020","journal-title":"Crit. Care"},{"key":"B42","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1038\/s41398-022-02181-9","article-title":"Epigenetic aging and perceived psychological stress in old age.","volume":"12","author":"Vetter","year":"2022","journal-title":"Transl. Psychiatry"},{"key":"B43","doi-asserted-by":"publisher","first-page":"113690","DOI":"10.1016\/j.envpol.2019.113690","article-title":"Associations of annual ambient PM2.5 components with DNAm PhenoAge acceleration in elderly men: The normative aging study.","volume":"258","author":"Wang","year":"2020","journal-title":"Environ. Pollut."},{"key":"B44","doi-asserted-by":"publisher","first-page":"998","DOI":"10.1111\/jgs.14090","article-title":"Herpesvirus infections and risk of frailty and mortality in older women: Women\u2019s health and aging studies.","volume":"64","author":"Wang","year":"2016","journal-title":"J. Am. Geriatr. Soc."},{"key":"B45","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1093\/gerona\/glac161","article-title":"Development of a novel multidimensional measure of aging to predict mortality and morbidity in the prospective MJ Cohort.","volume":"78","author":"Wang","year":"2023","journal-title":"J. Gerontol. A Biol. Sci. Med. Sci."},{"key":"B46","doi-asserted-by":"publisher","first-page":"e212240","DOI":"10.1001\/jamanetworkopen.2021.2240","article-title":"Use of machine learning to develop and evaluate models using preoperative and intraoperative data to identify risks of postoperative complications.","volume":"4","author":"Xue","year":"2021","journal-title":"JAMA Netw. Open"},{"key":"B47","doi-asserted-by":"publisher","first-page":"n604","DOI":"10.1136\/bmj.n604","article-title":"Associations of healthy lifestyle and socioeconomic status with mortality and incident cardiovascular disease: Two prospective cohort studies.","volume":"373","author":"Zhang","year":"2021","journal-title":"BMJ"},{"key":"B48","doi-asserted-by":"publisher","first-page":"8110","DOI":"10.1109\/TPAMI.2022.3227370","article-title":"BoostTree and boostforest for ensemble learning.","volume":"45","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Pattern. Anal. Mach. Intell."}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1532884\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T05:36:16Z","timestamp":1752644176000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1532884\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":48,"alternative-id":["10.3389\/fnagi.2025.1532884"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2025.1532884","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,16]]},"article-number":"1532884"}}