{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T20:41:42Z","timestamp":1793479302986,"version":"4.5.0"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T00:00:00Z","timestamp":1776902400000},"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. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Alzheimer\u2019s disease (AD) is increasingly recognized as a disorder involving not only amyloid and tau pathology but also glial activation and neuroinflammation. Biomarkers reflecting these processes may improve the classification of clinical cognitive impairment. This study evaluated the diagnostic value of glial biomarkers, alongside cerebrospinal fluid (CSF) biomarkers, for distinguishing cognitively normal individuals from those with clinical dementia rating scale (CDR)-defined very mild or mild dementia.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Data from 333 adults aged \u226560\u202fyears were obtained from the Knight Alzheimer\u2019s Disease Research Center\u2019s longitudinal, open-access dataset. Seven multimodal models integrating CSF biomarkers, glial biomarkers, and clinical features were developed using machine-learning approaches. A hybrid model incorporating feature selection was applied, and model interpretability was assessed. Classification performance was evaluated using AUC, accuracy, recall, precision, and F1-score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Incorporating all biomarkers, the model achieved the highest performance (AUC\u202f=\u202f0.959; accuracy\u202f=\u202f0.912), followed by a parsimonious hybrid model (clustering, cystatin C, age, tau, A\u03b242, sex) with comparable performance (AUC\u202f=\u202f0.951; accuracy\u202f=\u202f0.868;\n                      <jats:italic>p<\/jats:italic>\n                      =\u202f0.309). According to SHAP analysis, tau and cystatin C were the most influential features in both models for clinical impairment classification.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Glial biomarkers significantly enhance diagnostic classification of CDR-defined clinical cognitive impairment beyond core CSF biomarkers. Parsimonious and interpretable machine-learning models achieve performance comparable to more complex approaches, supporting their potential use in clinical stratification frameworks.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1787915","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T04:21:09Z","timestamp":1776918069000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Glial biomarkers improve classification of cognitive impairment: an explainable artificial intelligence study using CSF biomarkers"],"prefix":"10.3389","volume":"17","author":[{"given":"Merve","family":"T\u00fcrkeg\u00fcn \u015eeng\u00fcl","sequence":"first","affiliation":[{"name":"Department of Biostatistics and Medical Informatics, Faculty of Medicine, Alanya Alaaddin Keykubat University","place":["Antalya, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dilara","family":"Nemutlu Samur","sequence":"additional","affiliation":[{"name":"Department of Medical Pharmacology, Faculty of Medicine, Alanya Alaaddin Keykubat University","place":["Antalya, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,23]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"112834","DOI":"10.1016\/j.exger.2025.112834","article-title":"Mild cognitive impairment among older adults in outpatient clinics: awareness and knowledge needs survey","volume":"209","author":"Wang","year":"2025","journal-title":"Exp Gerontol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e0306270","DOI":"10.1371\/journal.pone.0306270","article-title":"Transition of mild cognitive impairment to Alzheimer's disease: medications as modifiable risk factors","volume":"19","author":"Wang","year":"2024","journal-title":"PLoS One"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1709","DOI":"10.1097\/CM9.0000000000001496","article-title":"Amyloid and tau positive mild cognitive impairment: clinical and biomarker characteristics of dementia progression","volume":"134","author":"Wei","year":"2021","journal-title":"Chin Med J"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1662151","DOI":"10.3389\/fpsyg.2025.1662151","article-title":"Mild cognitive impairment and neuropsychological examination","volume":"16","author":"Hessen","year":"2025","journal-title":"Front Psychol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1186\/s40035-024-00432-x","article-title":"Updates in Alzheimer's disease: from basic research to diagnosis and therapies","volume":"13","author":"Liu","year":"2024","journal-title":"Translational Neurodegeneration"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"479","DOI":"10.3390\/brainsci10080479","article-title":"The neuropathological diagnosis of Alzheimer's disease-the challenges of pathological mimics and concomitant pathology","volume":"10","author":"King","year":"2020","journal-title":"Brain Sci"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"371","DOI":"10.14283\/jpad.2021.23","article-title":"Diagnosis of early Alzheimer's disease: clinical practice in 2021","volume":"8","author":"Porsteinsson","year":"2021","journal-title":"J Prev Alzheimers Dis"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/j.jalz.2018.02.018","article-title":"NIA-AA research framework: toward a biological definition of Alzheimer's disease","volume":"14","author":"Jack","year":"2018","journal-title":"Alzheimers Dement"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e2519919","DOI":"10.1001\/jamanetworkopen.2025.19919","article-title":"Cerebrospinal fluid amyloid and tau biomarker changes across the Alzheimer disease clinical spectrum","volume":"8","author":"De Leeuw","year":"2025","journal-title":"JAMA Netw Open"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"8976","DOI":"10.3390\/ijms24108976","article-title":"CSF biomarkers in the early diagnosis of mild cognitive impairment and Alzheimer's disease","volume":"24","author":"Papaliagkas","year":"2023","journal-title":"Int J Mol Sci"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1488494","DOI":"10.3389\/fpsyt.2024.1488494","article-title":"Using cerebrospinal fluid biomarkers to diagnose Alzheimer's disease: an Australian perspective","volume":"15","author":"Eratne","year":"2024","journal-title":"Front Psychol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"10572","DOI":"10.3390\/ijms231810572","article-title":"Glial cell-mediated neuroinflammation in Alzheimer's disease","volume":"23","author":"Al-Ghraiybah","year":"2022","journal-title":"Int J Mol Sci"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"824888","DOI":"10.3389\/fnins.2022.824888","article-title":"Microglia and astrocyte function and communication: what do we know in humans?","volume":"16","author":"Garland","year":"2022","journal-title":"Front Neurosci"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e23015","DOI":"10.1002\/dneu.23015","article-title":"Astrocytes and microglia in Alzheimer's disease: friends, foes, or both?","volume":"86","author":"Sharma","year":"2026","journal-title":"Dev Neurobiol"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1186\/s12974-024-03163-y","article-title":"Tracking neuroinflammatory biomarkers in Alzheimer\u2019s disease: a strategy for individualized therapeutic approaches?","volume":"21","author":"Lista","year":"2024","journal-title":"J Neuroinflammation"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.molmed.2018.11.006","article-title":"Astrocyte biomarkers in Alzheimer\u2019s disease","volume":"25","author":"Carter","year":"2019","journal-title":"Trends Mol Med"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"eaav6221","DOI":"10.1126\/scitranslmed.aav6221","article-title":"Increased soluble TREM2 in cerebrospinal fluid is associated with reduced cognitive and clinical decline in Alzheimer's disease","volume":"11","author":"Ewers","year":"2019","journal-title":"Sci Transl Med"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"705782","DOI":"10.3389\/fnagi.2021.705782","article-title":"Operational determination of subjective cognitive decline, mild cognitive impairment, and dementia using sum of boxes of the clinical dementia rating scale","volume":"13","author":"Yang","year":"2021","journal-title":"Front Aging Neurosci"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/s40846-024-00918-z","article-title":"Machine learning approaches for predicting progression to Alzheimer's disease in patients with mild cognitive impairment","volume":"45","author":"Gelir","year":"2025","journal-title":"J Med Biol Eng"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1016\/j.dadm.2018.07.004","article-title":"Machine learning of neuroimaging for assisted diagnosis of cognitive impairment and dementia: a systematic review","volume":"10","author":"Pellegrini","year":"2018","journal-title":"Alzheimers Dement (Amst)"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1016\/j.bbe.2025.05.011","article-title":"Integrative and interpretable framework to unveil the neurophysiological fingerprint of Alzheimer\u2019s disease and mild cognitive impairment: a machine learning-SHAP approach","volume":"45","author":"de Guti\u00e9rrez- Pablo","year":"2025","journal-title":"Biocybern Biomed Eng"},{"key":"ref22","author":"Chen","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"5860","DOI":"10.1002\/alz.13390","article-title":"Artificial intelligence for biomarker discovery in Alzheimer's disease and dementia","volume":"19","author":"Winchester","year":"2023","journal-title":"Alzheimers Dement"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"2761","DOI":"10.3390\/ijms22052761","article-title":"Machine learning and novel biomarkers for the diagnosis of Alzheimer\u2019s disease","volume":"22","author":"Chang","year":"2021","journal-title":"Int J Mol Sci"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"e18850","DOI":"10.1371\/journal.pone.0018850","article-title":"Multiplexed immunoassay panel identifies novel CSF biomarkers for Alzheimer's disease diagnosis and prognosis","volume":"6","author":"Craig-Schapiro","year":"2011","journal-title":"PLoS One"},{"key":"ref26","author":"Max Kuhn","year":"2018"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1212\/WNL.34.7.939","article-title":"Clinical diagnosis of Alzheimer's disease: report of the NINCDS-ADRDA work group under the auspices of Department of Health and Human Services Task Force on Alzheimer's disease","volume":"34","author":"McKhann","year":"1984","journal-title":"Neurology"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"2412","DOI":"10.1212\/WNL.43.11.2412-a","article-title":"The clinical dementia rating (CDR): current version and scoring rules","volume":"43","author":"Morris","year":"1993","journal-title":"Neurology"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J Royal Statistical Society Series B: Statistical Methodol"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"ref31","author":"Scott M Lundberg","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"11941","DOI":"10.3390\/ijms252211941","article-title":"Neuroinflammatory biomarkers in Alzheimer's disease: from pathophysiology to clinical implications","volume":"25","author":"Roveta","year":"2024","journal-title":"Int J Mol Sci"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"79","DOI":"10.3389\/fnmol.2012.00079","article-title":"Cystatin C in Alzheimer's disease","volume":"5","author":"Kaur","year":"2012","journal-title":"Front Mol Neurosci"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"e55328","DOI":"10.1371\/journal.pone.0055328","article-title":"Alterations of CSF cystatin C levels and their correlations with CSF \u0391\u03b240 and \u0391\u03b242 levels in patients with Alzheimer's disease, dementia with lewy bodies and the atrophic form of general paresis","volume":"8","author":"Zhong","year":"2013","journal-title":"PLoS One"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"e952","DOI":"10.1038\/tp.2016.194","article-title":"A targeted proteomic multiplex CSF assay identifies increased malate dehydrogenase and other neurodegenerative biomarkers in individuals with Alzheimer's disease pathology","volume":"6","author":"Paterson","year":"2016","journal-title":"Transl Psychiatry"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"e13281","DOI":"10.1111\/bpa.13281","article-title":"Brain and plasmatic CLUSTERIN are translational markers of Alzheimer's disease","volume":"35","author":"Tournier","year":"2025","journal-title":"Brain Pathol"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1001\/jama.2011.381","article-title":"Plasma clusterin and the risk of Alzheimer disease","volume":"305","author":"Schrijvers","year":"2011","journal-title":"JAMA"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.3233\/jad-150036","article-title":"Clusterin levels in plasma predict cognitive decline and progression to Alzheimer's disease","volume":"46","author":"Jongbloed","year":"2015","journal-title":"J Alzheimer's Dis"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2017\/1879437","article-title":"The effect of Osteopontin on microglia","volume":"2017","author":"Yu","year":"2017","journal-title":"Biomed Res Int"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"4010","DOI":"10.1038\/s41598-021-83601-6","article-title":"Plasma osteopontin as a biomarker of Alzheimer\u2019s disease and vascular cognitive impairment","volume":"11","author":"Chai","year":"2021","journal-title":"Sci Rep"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.3233\/jad-2010-1309","article-title":"Osteopontin is increased in the cerebrospinal fluid of patients with Alzheimer's disease and its levels correlate with cognitive decline","volume":"19","author":"Comi","year":"2010","journal-title":"J Alzheimer's Dis"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"615745","DOI":"10.1155\/2013\/615745","article-title":"Elevated osteopontin levels in mild cognitive impairment and Alzheimer's disease","volume":"2013","author":"Sun","year":"2013","journal-title":"Mediat Inflamm"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"12276","DOI":"10.1038\/s41598-024-60134-2","article-title":"A multimodal machine learning model for predicting dementia conversion in Alzheimer's disease","volume":"14","author":"Lee","year":"2024","journal-title":"Sci Rep"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1186\/s12911-023-02238-9","article-title":"XGBoost-SHAP-based interpretable diagnostic framework for alzheimer's disease","volume":"23","author":"Yi","year":"2023","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.neuroscience.2023.01.029","article-title":"Comparison of machine learning-based approaches to predict the conversion to Alzheimer's disease from mild cognitive impairment","volume":"514","author":"Franciotti","year":"2023","journal-title":"Neuroscience"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"103142","DOI":"10.1016\/j.eclinm.2025.103142","article-title":"Development and validation of machine learning models with blood-based digital biomarkers for Alzheimer's disease diagnosis: a multicohort diagnostic study","volume":"81","author":"Jiao","year":"2025","journal-title":"EClinicalMedicine"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1186\/s13195-025-01851-2","article-title":"Optimizing timing and cost-effective use of plasma biomarkers in Alzheimer's disease","volume":"17","author":"Chang","year":"2025","journal-title":"Alzheimer's Res Ther"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"945274","DOI":"10.3389\/fnagi.2022.945274","article-title":"Develop a diagnostic tool for dementia using machine learning and non-imaging features","volume":"14","author":"Wang","year":"2022","journal-title":"Front Aging Neurosci"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"683689","DOI":"10.3389\/fnagi.2022.683689","article-title":"Diagnostic accuracy of blood-based biomarker panels: a systematic review","volume":"14","author":"Hardy-Sosa","year":"2022","journal-title":"Front Aging Neurosci"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"e79881","DOI":"10.7759\/cureus.79881","article-title":"Blood-based \u03b2-amyloid and phosphorylated tau (p-tau) biomarkers in Alzheimer's disease: a systematic review of their diagnostic potential","volume":"17","author":"Dasari","year":"2025","journal-title":"Cureus"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.3390\/cells10081930","article-title":"Neuroinflammation and Alzheimer's disease: a machine learning approach to CSF proteomics","volume":"10","author":"Gaetani","year":"2021","journal-title":"Cells"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/s12974-022-02383-4","article-title":"Cyclic multiplex fluorescent immunohistochemistry and machine learning reveal distinct states of astrocytes and microglia in normal aging and Alzheimer's disease","volume":"19","author":"Mu\u00f1oz-Castro","year":"2022","journal-title":"J Neuroinflammation"},{"key":"ref53","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1186\/s40478-024-01898-6","article-title":"3-dimensional morphological characterization of neuroretinal microglia in Alzheimer's disease via machine learning","volume":"12","author":"Nassrallah","year":"2024","journal-title":"Acta Neuropathol Commun"},{"key":"ref54","doi-asserted-by":"publisher","first-page":"17271","DOI":"10.1038\/s41598-024-67537-1","article-title":"Elucidating microglial heterogeneity and functions in Alzheimer\u2019s disease using single-cell analysis and convolutional neural network disease model construction","volume":"14","author":"Wu","year":"2024","journal-title":"Sci Rep"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1787915\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T04:21:10Z","timestamp":1776918070000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1787915\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,23]]},"references-count":54,"alternative-id":["10.3389\/fneur.2026.1787915"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1787915","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,23]]},"article-number":"1787915"}}