{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:02:49Z","timestamp":1787022169579,"version":"build-2736575974"},"reference-count":56,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T00:00:00Z","timestamp":1744588800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004070","name":"Khalifa University of Science, Technology and Research","doi-asserted-by":"publisher","award":["FSU-2021-005"],"award-info":[{"award-number":["FSU-2021-005"]}],"id":[{"id":"10.13039\/501100004070","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Alzheimer\u2019s disease (AD) is a neurodegenerative disorder that requires early diagnosis for effective management. However, issues with currently available diagnostic biomarkers preclude early diagnosis, necessitating the development of alternative biomarkers and methods, such as blood-based diagnostics. We propose c-Triadem (constrained triple-input Alzheimer\u2019s disease model), a novel deep neural network to identify potential blood-based biomarkers for AD and predict mild cognitive impairment (MCI) and AD with high accuracy. The model utilizes genotyping data, gene expression data, and clinical information to predict the disease status of participants, i.e., cognitively normal (CN), MCI, or AD. The nodes of the neural network represent genes and their related pathways, and the edges represent known relationships among the genes and pathways. Simulated data validation further highlights the robustness of key features identified by SHapley Additive exPlanations (SHAP). We trained the model with blood genotyping data, microarray, and clinical features from the Alzheimer\u2019s Neuroimaging Disease Initiative (ADNI). We demonstrate that our model\u2019s performance is superior to previous models with an AUC of 97% and accuracy of 89%. We then identified the most influential genes and clinical features for prediction using SHapley Additive exPlanations (SHAP). Our SHAP analysis shows that CASP9, LCK, and SDC3 SNPs and PINK1, ATG5, and ubiquitin (UBB, UBC) expression have a higher impact on model performance. Our model has facilitated the identification of potential blood-based genetic markers of DNA damage response and mitophagy in affected regions of the brain. The model can be used for detection and biomarker identification in other related dementias.<\/jats:p>","DOI":"10.1371\/journal.pone.0320360","type":"journal-article","created":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T16:02:46Z","timestamp":1744646566000},"page":"e0320360","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["c-Triadem: A constrained, explainable deep learning model to identify novel biomarkers in Alzheimer\u2019s disease"],"prefix":"10.1371","volume":"20","author":[{"given":"Sherlyn","family":"Jemimah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ferial","family":"Abuhantash","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1868-1003","authenticated-orcid":true,"given":"Aamna","family":"AlShehhi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,4,14]]},"reference":[{"key":"pone.0320360.ref001","unstructured":"Gauthier S, Rosa-Neto P, Morais J, Webster C. World Alzheimer report 2021: journey through the diagnosis of dementia. Alzheimer\u2019s Disease International; 2021."},{"key":"pone.0320360.ref002","doi-asserted-by":"crossref","first-page":"984786","DOI":"10.5402\/2012\/984786","article-title":"Biomarkers in Alzheimer\u2019s disease: a review","volume":"2012","author":"M Chintamaneni","year":"2012","journal-title":"ISRN Pharmacol"},{"key":"pone.0320360.ref003","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1586\/14737159.2015.1002469","article-title":"Genetic diagnosis and prognosis of Alzheimer\u2019s disease: challenges and opportunities","volume":"15","author":"C Reitz","year":"2015","journal-title":"Expert Rev Mol Diagn"},{"key":"pone.0320360.ref004","first-page":"243","article-title":"Beta-protein amyloid is widely distributed in the central nervous system of patients with Alzheimer\u2019s disease","volume":"134","author":"K Ogomori","year":"1989","journal-title":"Am J Pathol"},{"key":"pone.0320360.ref005","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1046\/j.1440-1819.2000.00747.x","article-title":"Neuronal loss and neurofibrillary degeneration in the hippocampal cortex in late-onset sporadic Alzheimer\u2019s disease","volume":"54","author":"Y Fukutani","year":"2000","journal-title":"Psychiatry Clin Neurosci"},{"key":"pone.0320360.ref006","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1016\/j.neuron.2020.06.010","article-title":"Selective neuronal vulnerability in Alzheimer\u2019s disease: a network-based analysis","volume":"107","author":"J-P Roussarie","year":"2020","journal-title":"Neuron"},{"key":"pone.0320360.ref007","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1212\/WNL.42.3.631","article-title":"Neurofibrillary tangles but not senile plaques parallel duration and severity of Alzheimer\u2019s disease","volume":"42","author":"P Arriagada","year":"1992","journal-title":"Neurology"},{"key":"pone.0320360.ref008","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.jalz.2018.02.018","article-title":"NIA-AA research framework: toward a biological definition of Alzheimer\u2019s disease","volume":"14","author":"CR Jack","year":"2018","journal-title":"Alzheimers Dement"},{"key":"pone.0320360.ref009","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/s11011-022-01114-1","article-title":"Blood-based biomarkers in Alzheimer\u2019s disease: a mini-review","volume":"38","author":"SP Padala","year":"2023","journal-title":"Metab Brain Dis"},{"key":"pone.0320360.ref010","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1016\/j.jalz.2017.06.2266","article-title":"Amyloid \u03b2 concentrations and stable isotope labeling kinetics of human plasma specific to central nervous system amyloidosis","volume":"13","author":"V Ovod","year":"2017","journal-title":"Alzheimers Dement"},{"key":"pone.0320360.ref011","first-page":"249","article-title":"et al","volume":"554","author":"A Nakamura","year":"2018","journal-title":"High performance plasma amyloid-\u03b2 biomarkers for Alzheimer\u2019s disease. Nature"},{"key":"pone.0320360.ref012","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1186\/s13041-019-0448-1","article-title":"Blood-based molecular biomarkers for Alzheimer\u2019s disease","volume":"12","author":"H Zetterberg","year":"2019","journal-title":"Mol Brain"},{"key":"pone.0320360.ref013","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/S1474-4422(21)00361-6","article-title":"Blood-based biomarkers for Alzheimer\u2019s disease: towards clinical implementation","volume":"21","author":"CE Teunissen","year":"2022","journal-title":"Lancet Neurol"},{"key":"pone.0320360.ref014","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1111\/joim.12816","article-title":"Biomarkers for Alzheimer\u2019s disease: current status and prospects for the future","volume":"284","author":"K Blennow","year":"2018","journal-title":"J Intern Med"},{"key":"pone.0320360.ref015","doi-asserted-by":"crossref","unstructured":"Lashley T, et al. Molecular biomarkers of Alzheimer\u2019s disease: progress and prospects. Dis Model Mech. 2018;11:dmm031781. doi: 10.1242\/dmm.031781","DOI":"10.1242\/dmm.031781"},{"key":"pone.0320360.ref016","doi-asserted-by":"crossref","first-page":"895398","DOI":"10.3389\/fnagi.2022.895398","article-title":"Commentary: Diagnostic accuracy of blood-based biomarker panels: a systematic review","volume":"14","author":"S Bhagavati","year":"2022","journal-title":"Front Aging Neurosci"},{"key":"pone.0320360.ref017","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1109\/JBHI.2020.2984355","article-title":"Early detection of Alzheimer\u2019s disease with blood plasma proteins using support vector machines","volume":"25","author":"CS Eke","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0320360.ref018","doi-asserted-by":"crossref","first-page":"9387","DOI":"10.3390\/ijms23169387","article-title":"Senescence markers in peripheral blood mononuclear cells in amnestic mild cognitive impairment and Alzheimer\u2019s disease","volume":"23","author":"F Salech","year":"2022","journal-title":"Int J Mol Sci"},{"key":"pone.0320360.ref019","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1186\/s13195-020-00754-8","article-title":"Association between polygenic risk score of Alzheimer\u2019s disease and plasma phosphorylated tau in individuals from the Alzheimer\u2019s disease neuroimaging initiative","volume":"13","author":"A Zettergren","year":"2021","journal-title":"Alzheimers Res Ther"},{"key":"pone.0320360.ref020","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1093\/brain\/awac128","article-title":"Plasma biomarkers and genetics in the diagnosis and prediction of Alzheimer\u2019s disease","volume":"146","author":"J Stevenson-Hoare","year":"2023","journal-title":"Brain"},{"key":"pone.0320360.ref021","doi-asserted-by":"crossref","first-page":"103929","DOI":"10.1016\/j.ebiom.2022.103929","article-title":"Transcript levels in plasma contribute substantial predictive value as potential Alzheimer\u2019s disease biomarkers in African Americans","volume":"78","author":"JS Reddy","year":"2022","journal-title":"EBioMedicine"},{"key":"pone.0320360.ref022","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1186\/s41065-022-00252-x","article-title":"Bioinformatics analysis of diagnostic biomarkers for Alzheimer\u2019s disease in peripheral blood based on sex differences and support vector machine algorithm","volume":"159","author":"W Ji","year":"2022","journal-title":"Hereditas"},{"key":"pone.0320360.ref023","doi-asserted-by":"crossref","unstructured":"Stamate D, et al. A metabolite-based machine learning approach to diagnose Alzheimer-type dementia in blood: results from the European Medical information framework for Alzheimer disease biomarker discovery cohort. Alzheimers Dement. (N.Y.) 2019;5:933\u20138. doi: 10.1016\/j.trci.2019.11.001","DOI":"10.1016\/j.trci.2019.11.001"},{"key":"pone.0320360.ref024","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1016\/j.jalz.2019.03.007","article-title":"Inflammatory biomarkers in Alzheimer\u2019s disease plasma","volume":"15","author":"AR Morgan","year":"2019","journal-title":"Alzheimers Dement"},{"key":"pone.0320360.ref025","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1159\/000330750","article-title":"A blood-based algorithm for the detection of Alzheimer\u2019s disease","volume":"32","author":"SE O\u2019Bryant","year":"2011","journal-title":"Dement Geriatr Cogn Disord"},{"key":"pone.0320360.ref026","doi-asserted-by":"crossref","first-page":"1920","DOI":"10.1093\/brain\/awaa137","article-title":"Development and validation of an interpretable deep learning framework for Alzheimer\u2019s disease classification","volume":"143","author":"S Qiu","year":"2020","journal-title":"Brain"},{"key":"pone.0320360.ref027","unstructured":"Lundberg S, Lee S-I. A unified approach to interpreting model predictions. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS\u201917. Red Hook, NY: Curran Associates Inc.; 2017, pp. 4768\u2013-77."},{"key":"pone.0320360.ref028","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1007\/s41666-022-00114-1","article-title":"Explainable artificial intelligence for predictive modeling in healthcare","volume":"6","author":"CC Yang","year":"2022","journal-title":"J Healthc Inform Res"},{"key":"pone.0320360.ref029","doi-asserted-by":"crossref","first-page":"792","DOI":"10.1016\/j.jalz.2015.05.009","article-title":"Genetic studies of quantitative MCI and AD phenotypes in ADNI: progress, opportunities, and plans","volume":"11","author":"AJ Saykin","year":"2015","journal-title":"Alzheimers Dement"},{"key":"pone.0320360.ref030","doi-asserted-by":"crossref","first-page":"3254","DOI":"10.1038\/s41598-020-74399-w","article-title":"Multimodal deep learning models for early detection of Alzheimer\u2019s disease stage","volume":"11","author":"J Venugopalan","year":"2021","journal-title":"Sci Rep"},{"key":"pone.0320360.ref031","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1002\/hbm.24428","article-title":"Effective feature learning and fusion of multimodality data using stage-wise deep neural network for dementia diagnosis","volume":"40","author":"T Zhou","year":"2019","journal-title":"Hum. Brain Mapp"},{"key":"pone.0320360.ref032","doi-asserted-by":"crossref","first-page":"109582","DOI":"10.1016\/j.jneumeth.2022.109582","article-title":"Addressing the missing data challenge in multi-modal datasets for the diagnosis of Alzheimer\u2019s disease","volume":"375","author":"M Aghili","year":"2022","journal-title":"J Neurosci Methods"},{"key":"pone.0320360.ref033","doi-asserted-by":"crossref","first-page":"701301","DOI":"10.3389\/fphar.2021.701301","article-title":"Caspase-9: a multimodal therapeutic target with diverse cellular expression in human disease","volume":"12","author":"MI Avrutsky","year":"2021","journal-title":"Front Pharmacol"},{"key":"pone.0320360.ref034","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1006\/nbdi.2002.0549","article-title":"Caspase-9 activation and caspase cleavage of tau in the Alzheimer\u2019s disease brain","volume":"11","author":"TT Rohn","year":"2002","journal-title":"Neurobiol Dis"},{"key":"pone.0320360.ref035","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.clineuro.2016.02.015","article-title":"Increased apoptosis in the platelets of patients with Alzheimer\u2019s disease and amnestic mild cognitive impairment","volume":"143","author":"S Zhao","year":"2016","journal-title":"Clin Neurol Neurosurg"},{"key":"pone.0320360.ref036","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1093\/hmg\/ddg007","article-title":"Results of a high-resolution genome screen of 437 Alzheimer\u2019s disease families","volume":"12","author":"D Blacker","year":"2003","journal-title":"Hum Mol Genet"},{"key":"pone.0320360.ref037","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.jns.2005.06.017","article-title":"Lymphocyte-specific protein tyrosine kinase is a novel risk gene for alzheimer disease","volume":"238","author":"W Zhong","year":"2005","journal-title":"J Neurol Sci"},{"key":"pone.0320360.ref038","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1007\/s00018-012-1168-1","article-title":"Alzheimer\u2019s disease risk factor lymphocyte-specific protein tyrosine kinase regulates long-term synaptic strengthening, spatial learning and memory","volume":"70","author":"E-J Kim","year":"2013","journal-title":"Cell Mol Life Sci"},{"key":"pone.0320360.ref039","first-page":"23","article-title":"Syndecan-3 as a novel biomarker in Alzheimer\u2019s disease","author":"A Hud\u00e1k","year":"2022","journal-title":"Int J Mol Sci"},{"key":"pone.0320360.ref040","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/s40035-022-00305-1","article-title":"Defective mitophagy and the etiopathogenesis of Alzheimer\u2019s disease","volume":"11","author":"K Zeng","year":"2022","journal-title":"Transl Neurodegener"},{"key":"pone.0320360.ref041","doi-asserted-by":"crossref","first-page":"20009","DOI":"10.1038\/s41598-019-56614-5","article-title":"Autophagy and mitophagy biomarkers are reduced in sera of patients with Alzheimer\u2019s disease and mild cognitive impairment","volume":"9","author":"M Castellazzi","year":"2019","journal-title":"Sci Rep"},{"key":"pone.0320360.ref042","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1016\/j.nicl.2016.12.011","article-title":"Rey\u2019s auditory verbal learning test scores can be predicted from whole brain MRI in Alzheimer\u2019s disease","volume":"13","author":"E Moradi","year":"2017","journal-title":"NeuroImage Clin"},{"key":"pone.0320360.ref043","doi-asserted-by":"crossref","unstructured":"Phongpreecha T, et al. Single-cell peripheral immunoprofiling of Alzheimer\u2019s and Parkinson\u2019s diseases. Sci Adv. 2020;6:eabd5575. doi: 10.1126\/sciadv.abd5575","DOI":"10.1126\/sciadv.abd5575"},{"key":"pone.0320360.ref044","doi-asserted-by":"crossref","unstructured":"Josephy-Hernandez S, et al. Pharmacological interrogation of TrkA-mediated mechanisms in hippocampal-dependent memory consolidation. PLoS One. 2019;14:e0218036, doi: 10.1371\/journal.pone.0218036","DOI":"10.1371\/journal.pone.0218036"},{"key":"pone.0320360.ref045","doi-asserted-by":"crossref","unstructured":"Garfias S, et al. Peripheral blood lymphocyte phenotypes in Alzheimer and Parkinson\u2019s diseases. Neurol. (Engl. Ed.) 2022;37:110\u201321. doi: 10.1016\/j.nrleng.2018.10.022","DOI":"10.1016\/j.nrleng.2018.10.022"},{"key":"pone.0320360.ref046","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1111\/j.1749-6632.2009.05064.x","article-title":"AddNeuroMed\u2014the European collaboration for the discovery of novel biomarkers for Alzheimer\u2019s disease","volume":"1180","author":"S Lovestone","year":"2009","journal-title":"Ann N Y Acad Sci"},{"key":"pone.0320360.ref047","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1186\/s13059-015-0750-x","article-title":"A novel multi-tissue RNA diagnostic of healthy ageing relates to cognitive health status","volume":"16","author":"S Sood","year":"2015","journal-title":"Genome Biol"},{"key":"pone.0320360.ref048","doi-asserted-by":"crossref","first-page":"14645","DOI":"10.1523\/JNEUROSCI.1327-13.2013","article-title":"MiR-26b, upregulated in Alzheimer\u2019s disease, activates cell cycle entry, tau-phosphorylation, and apoptosis in postmitotic neurons","volume":"33","author":"S Absalon","year":"2013","journal-title":"J. Neurosci"},{"key":"pone.0320360.ref049","doi-asserted-by":"crossref","first-page":"3500","DOI":"10.3390\/ijms20143500","article-title":"Beyond TCR signaling: emerging functions of LCK in cancer and immunotherapy","volume":"20","author":"U Bommhardt","year":"2019","journal-title":"Int J Mol Sci"},{"key":"pone.0320360.ref050","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1212\/WNL.0b013e3181cb3e25","article-title":"Alzheimer\u2019s disease neuroimaging initiative (ADNI): clinical characterization","volume":"74","author":"RC Petersen","year":"2010","journal-title":"Neurology"},{"key":"pone.0320360.ref051","doi-asserted-by":"crossref","first-page":"3461","DOI":"10.1093\/bioinformatics\/btx441","article-title":"Reactome enhanced pathway visualization","volume":"33","author":"K Sidiropoulos","year":"2017","journal-title":"Bioinformatics"},{"key":"pone.0320360.ref052","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1038\/s41586-021-03922-4","article-title":"Biologically informed deep neural network for prostate cancer discovery","volume":"598","author":"HA Elmarakeby","year":"2021","journal-title":"Nature"},{"key":"pone.0320360.ref053","doi-asserted-by":"crossref","first-page":"D605","DOI":"10.1093\/nar\/gkaa1074","article-title":"The STRING database in 2021: customizable protein-protein networks, and functional characterization of user-uploaded gene\/measurement sets","volume":"49","author":"D Szklarczyk","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"pone.0320360.ref054","doi-asserted-by":"crossref","first-page":"10483","DOI":"10.1038\/s41598-023-37569-0","article-title":"An Alzheimer\u2019s disease category progression sub-grouping analysis using manifold learning on ADNI","volume":"13","author":"D van der Haar","year":"2023","journal-title":"Sci Rep"},{"key":"pone.0320360.ref055","doi-asserted-by":"crossref","first-page":"23788","DOI":"10.1038\/s41598-021-02827-6","article-title":"Using imputation to provide harmonized longitudinal measures of cognition across AIBL and ADNI","volume":"11","author":"R Shishegar","year":"2021","journal-title":"Sci Rep"},{"key":"pone.0320360.ref056","doi-asserted-by":"crossref","first-page":"111403","DOI":"10.1016\/j.ejrad.2024.111403","article-title":"Explainable AI-based Deep-SHAP for mapping the multivariate relationships between regional neuroimaging biomarkers and cognition","volume":"174","author":"P Bhattarai","year":"2024","journal-title":"Eur J Radiol"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0320360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T16:02:59Z","timestamp":1744646579000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0320360"}},"subtitle":[],"editor":[{"given":"Jose Gerardo","family":"Tamez-Pe\u00f1a","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,4,14]]},"references-count":56,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0320360","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.11.19.24317595","asserted-by":"object"}]},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,14]]}}}