{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T13:31:40Z","timestamp":1778679100353,"version":"3.51.4"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004561","name":"Ministry of Education and Science of the Republic of Kazakhstan","doi-asserted-by":"publisher","award":["No OP2025004"],"award-info":[{"award-number":["No OP2025004"]}],"id":[{"id":"10.13039\/501100004561","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012632","name":"Nazarbayev University","doi-asserted-by":"publisher","award":["SOM2024008"],"award-info":[{"award-number":["SOM2024008"]}],"id":[{"id":"10.13039\/501100012632","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["U19AG024904"],"award-info":[{"award-number":["U19AG024904"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neuroinform."],"abstract":"<jats:p>Reliable imaging biomarkers are essential for improving early detection of Alzheimer\u2019s disease (AD). We evaluated whether an automated MRI-based classifier provides diagnostic performance comparable to expert radiologists in differentiating cognitively normal (CN) individuals from patients with AD using standardized ADNI data. Thirty-eight structural MRI datasets (20 CN, 18 AD) were analyzed. An automated multi-class volumetric classifier and two board-certified radiologists independently assigned probability scores across seven diagnostic categories. Performance was evaluated using a partial-credit scoring rule to account for probabilistic ties. Diagnostic performance for CN-AD discrimination was assessed using accuracy, sensitivity, specificity, receiver operating characteristic (ROC) analysis, inter-observer agreement metrics, Brier scores for calibration, and decision curve analysis (DCA) for clinical utility. The automated classifier achieved an accuracy of 0.66, sensitivity of 0.56, and specificity of 0.75. Radiologists demonstrated comparable performance with inherent inter-observer variability. Agreement between automated and human assessments was fair at the categorical level, with low concordance for continuous probability estimates. ROC analysis based on continuous AD probabilities demonstrated high discrimination performance for the automated model (AUC = 0.90), exceeding that of radiologists (AUC = 0.71 and 0.62). DCA indicated that the automated pipeline provides a positive net benefit as a second-opinion tool. This exploratory study emphasizes the impact of evaluation frameworks on performance metrics and supports further validation using multi-modal data in larger cohorts.<\/jats:p>","DOI":"10.3389\/fninf.2026.1821249","type":"journal-article","created":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T12:48:28Z","timestamp":1778676508000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reliability and diagnostic performance of an automated MRI-based classifier compared with radiologists in Alzheimer\u2019s disease"],"prefix":"10.3389","volume":"20","author":[{"given":"Nurmakhan","family":"Zholshybek","sequence":"first","affiliation":[{"name":"Department of Medicine, School of Medicine, Nazarbayev University","place":["Astana, Kazakhstan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elnora","family":"Abdurakhmanova","sequence":"additional","affiliation":[{"name":"Department of Biomedical Sciences, School of Medicine, Nazarbayev University","place":["Astana, Kazakhstan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Almas","family":"Bimakhan","sequence":"additional","affiliation":[{"name":"Department of Biomedical Sciences, School of Medicine, Nazarbayev University","place":["Astana, Kazakhstan"]},{"name":"Clinical and Academic Department of Radiology and Nuclear Medicine, Corporate Fund \u201cUniversity Medical Center\u201d","place":["Astana, Kazakhstan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinara","family":"Jumadilova","sequence":"additional","affiliation":[{"name":"Department of Medicine, School of Medicine, Nazarbayev University","place":["Astana, Kazakhstan"]},{"name":"Clinical and Academic Department of Radiology and Nuclear Medicine, Corporate Fund \u201cUniversity Medical Center\u201d","place":["Astana, Kazakhstan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanibek","family":"Baiturlin","sequence":"additional","affiliation":[{"name":"Department of Radiology and Radiosurgery, National Center for Neurosurgery","place":["Astana, Kazakhstan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph","family":"Almazan","sequence":"additional","affiliation":[{"name":"Department of Medicine, School of Medicine, Nazarbayev University","place":["Astana, Kazakhstan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srinivasa Rao","family":"Bolla","sequence":"additional","affiliation":[{"name":"Department of Biomedical Sciences, School of Medicine, Nazarbayev University","place":["Astana, Kazakhstan"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,13]]},"reference":[{"key":"B1","article-title":"National Bureau of Economic Research, Working Paper, 31422.","author":"Agarwal","year":"2023"},{"key":"B2","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/s40708-025-00252-3","article-title":"Machine-learning models for Alzheimer\u2019s disease diagnosis using neuroimaging data: Survey, reproducibility, and generalizability evaluation.","volume":"12","author":"Aghdam","year":"2025","journal-title":"Brain Inform."},{"key":"B3","doi-asserted-by":"publisher","first-page":"6","DOI":"10.38094\/jastt62453","article-title":"Alzheimer\u2019s classification with a MaxViT-based deep learning model using magnetic resonance imaging","author":"Aslan","year":"2025","journal-title":"JASTT"},{"key":"B4","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1097\/JCMA.0000000000001188","article-title":"Comparison of machine learning algorithms for automatic prediction of Alzheimer disease.","volume":"88","author":"Aslan","year":"2025","journal-title":"J. Chin. Med. Assoc."},{"key":"B5","doi-asserted-by":"publisher","first-page":"e0142756","DOI":"10.1371\/journal.pone.0142756","article-title":"Heterogeneity of regional brain atrophy patterns associated with distinct progression rates in Alzheimer\u2019s disease.","volume":"10","author":"Byun","year":"2015","journal-title":"PLoS One"},{"key":"B6","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1002\/jmrs.424","article-title":"The effect of clinical information on radiology reporting: A systematic review.","volume":"68","author":"Castillo","year":"2021","journal-title":"J. Med. Radiat. Sci."},{"key":"B7","doi-asserted-by":"publisher","first-page":"18137","DOI":"10.1038\/s41598-022-22979-3","article-title":"The development of an automated machine learning pipeline for the detection of Alzheimer\u2019s Disease.","volume":"12","author":"Chedid","year":"2022","journal-title":"Sci. Rep."},{"key":"B8","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1037\/h0026256","article-title":"Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit.","volume":"70","author":"Cohen","year":"1968","journal-title":"Psychol. Bull."},{"key":"B9","doi-asserted-by":"publisher","first-page":"117026","DOI":"10.1016\/j.neuroimage.2020.117026","article-title":"AssemblyNet: A large ensemble of CNNs for 3D whole-brain MRI segmentation.","volume":"219","author":"Coup\u00e9","year":"2020","journal-title":"Neuroimage"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e70336","DOI":"10.1002\/hbm.70336","article-title":"Lifespan tree of brain anatomy: Diagnostic values for motor and cognitive neurodegenerative diseases.","volume":"46","author":"Coup\u00e9","year":"2025","journal-title":"Hum. Brain Mapp."},{"key":"B11","doi-asserted-by":"publisher","first-page":"225022","DOI":"10.1088\/1361-6560\/abb6be","article-title":"RegQCNET: Deep quality control for image-to-template brain MRI affine registration.","volume":"65","author":"de Senneville","year":"2020","journal-title":"Phys. Med. Biol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1017\/S109285291600047X","article-title":"Approach to atypical Alzheimer\u2019s disease and case studies of the major subtypes.","volume":"22","author":"Dickerson","year":"2017","journal-title":"CNS Spectr."},{"key":"B13","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1186\/s13195-023-01314-6","article-title":"Biomarkers in Alzheimer\u2019s disease: Role in early and differential diagnosis and recognition of atypical variants.","volume":"15","author":"Dubois","year":"2023","journal-title":"Alzheimers Res. Ther."},{"key":"B14","doi-asserted-by":"publisher","first-page":"555","DOI":"10.21605\/cukurovaumfd.1514656","article-title":"MR g\u00f6r\u00fcnt\u00fclerinden Alzheimer hastal\u0131\u011f\u0131n\u0131n s\u0131n\u0131fland\u0131r\u0131lmasx0131; i\u00e7in inception ve s\u0131kma-uyarma a\u011f\u0131 tabanl\u0131 derin \u00f6\u011frenme modeli.","volume":"39","author":"F\u0131rat","year":"2024","journal-title":"Cukurova Univ. Muhendislik Fak Derg."},{"key":"B15","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1212\/01.wnl.0000287091.57376.6","article-title":"Volumetric MRI vs clinical predictors of Alzheimer disease in mild cognitive impairment.","volume":"70","author":"Fleisher","year":"2008","journal-title":"Neurology"},{"key":"B16","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/j.jalz.2009.04.1235","article-title":"Markers of Alzheimer\u2019s disease in a population attending a memory clinic.","volume":"5","author":"Frisoni","year":"2009","journal-title":"Alzheimer\u2019s Dement."},{"key":"B17","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-72938-1_2","article-title":"Diagnosis of Alzheimer\u2019s disease typical and atypical forms","volume-title":"Neurodegenerative Diseases","author":"Ghezzi","year":"2018"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1262","DOI":"10.1016\/j.jagp.2013.04.015","article-title":"change in sleep pattern may predict Alzheimer disease.","volume":"22","author":"Hahn","year":"2014","journal-title":"Am. J. Geriatr. Psychiatry"},{"key":"B19","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1148\/radiol.2261011712","article-title":"Probability in radiology.","volume":"226","author":"Halpern","year":"2003","journal-title":"Radiology"},{"key":"B20","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nrneurol.2013.269","article-title":"Sleep and Alzheimer disease pathology: A bidirectional relationship.","volume":"10","author":"Ju","year":"2014","journal-title":"Nat. Rev. Neurol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1427","DOI":"10.1016\/j.radi.2024.06.016","article-title":"Radiomics evaluation for the early detection of Alzheimer\u2019s dementia using T1-weighted MRI.","volume":"30","author":"Jytzler","year":"2024","journal-title":"Radiography"},{"key":"B22","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data.","volume":"33","author":"Landis","year":"1977","journal-title":"Biometrics"},{"key":"B23","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1109\/RBME.2018.2796598","article-title":"Quantitative MRI brain studies in mild cognitive impairment and Alzheimer\u2019s disease: A methodological review.","volume":"11","author":"Leandrou","year":"2018","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"B24","doi-asserted-by":"publisher","first-page":"e0316019","DOI":"10.1371\/journal.pone.0316019","article-title":"Area under the ROC curve has the most consistent evaluation for binary classification.","volume":"19","author":"Li","year":"2024","journal-title":"PLoS One"},{"key":"B25","doi-asserted-by":"publisher","first-page":"161305","DOI":"10.1007\/s11704-020-0016-y","article-title":"Understanding the role of human-inspired heuristics for retrieval models.","volume":"16","author":"Li","year":"2022","journal-title":"Front. Comput. Sci."},{"key":"B26","doi-asserted-by":"publisher","first-page":"30","DOI":"10.3389\/fninf.2016.00030","article-title":"volBrain: An online MRI brain volumetry system.","volume":"10","author":"Manj\u00f3n","year":"2016","journal-title":"Front. Neuroinform."},{"key":"B27","doi-asserted-by":"publisher","first-page":"e299","DOI":"10.5114\/pjr\/203781","article-title":"Quantitative brain volumetry in neurological disorders: From disease mechanisms to software solutions.","volume":"90","author":"Marek","year":"2025","journal-title":"Pol. J. Radiol."},{"key":"B28","doi-asserted-by":"publisher","first-page":"e69237","DOI":"10.1371\/journal.pone.0069237","article-title":"Automated, high accuracy classification of parkinsonian disorders: A pattern recognition approach.","volume":"8","author":"Marquand","year":"2013","journal-title":"PLoS One"},{"key":"B29","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1038\/s41746-025-02226-5","article-title":"Distinct visual biases affect humans and artificial intelligence in medical imaging diagnoses.","volume":"9","author":"McLeod","year":"2026","journal-title":"NPJ Digit. Med."},{"key":"B30","doi-asserted-by":"publisher","first-page":"617","DOI":"10.2214\/AJR.16.16894","article-title":"Diagnostic efficacy of structural MRI in patients with mild-to-moderate Alzheimer disease: Automated volumetric assessment versus visual assessment.","volume":"208","author":"Min","year":"2017","journal-title":"AJR Am. J. Roentgenol."},{"key":"B31","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1016\/j.jacr.2022.02.027","article-title":"The role of intuitive cognition in radiologic decision making.","volume":"19","author":"Patel","year":"2022","journal-title":"J. Am. Coll. Radiol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.neurobiolaging.2018.01.009","article-title":"Heterogeneous patterns of brain atrophy in Alzheimer\u2019s disease.","volume":"65","author":"Poulakis","year":"2018","journal-title":"Neurobiol. Aging"},{"key":"B33","doi-asserted-by":"publisher","first-page":"W365","DOI":"10.2214\/AJR.13.11657","article-title":"Biostatistics primer for the radiologist.","volume":"202","author":"Psoter","year":"2014","journal-title":"AJR Am. J. Roentgenol."},{"key":"B34","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1016\/j.rcl.2021.06.006","article-title":"Optimization of radiology workflow with artificial intelligence.","volume":"59","author":"Ranschaert","year":"2021","journal-title":"Radiol. Clin. North Am."},{"key":"B35","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1148\/radiol.2020190283","article-title":"Artificial intelligence system approaching neuroradiologist-level differential diagnosis accuracy at brain MRI.","volume":"295","author":"Rauschecker","year":"2020","journal-title":"Radiology"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1613","DOI":"10.1038\/s41592-025-02763-7","article-title":"MRIcroGL: Voxel-based visualization for neuroimaging.","volume":"22","author":"Rorden","year":"2025","journal-title":"Nat. Methods"},{"key":"B37","doi-asserted-by":"publisher","first-page":"e190146","DOI":"10.1148\/ryai.2020190146","article-title":"Subspecialty-level deep gray matter differential diagnoses with deep learning and Bayesian networks on clinical brain MRI: A pilot study.","volume":"2","author":"Rudie","year":"2020","journal-title":"Radiol. Art. Intell."},{"key":"B38","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.pscychresns.2015.08.014","article-title":"Neuroimaging of hippocampal atrophy in early recognition of Alzheimer\u2019s disease\u2013a critical appraisal after two decades of research.","volume":"247","author":"Schr\u00f6der","year":"2016","journal-title":"Psychiatry Res. Neuroimag."},{"key":"B39","doi-asserted-by":"publisher","first-page":"13","DOI":"10.3390\/sci5010013","article-title":"Review on alzheimer disease detection methods: Automatic pipelines and machine learning techniques.","volume":"5","author":"Shukla","year":"2023","journal-title":"Science"},{"key":"B40","doi-asserted-by":"publisher","first-page":"2074","DOI":"10.1007\/s00247-021-05177-7","article-title":"The augmented radiologist: Artificial intelligence in the practice of radiology.","volume":"52","author":"Sorantin","year":"2022","journal-title":"Pediatr. Radiol."},{"key":"B41","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1016\/S1474-4422(24)00038-3","article-title":"Global, regional, and national burden of disorders affecting the nervous system, 1990\u20132021: A systematic analysis for the Global Burden of Disease Study 2021.","volume":"23","author":"Steinmetz","year":"2024","journal-title":"Lancet Neurol."},{"key":"B42","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1016\/j.mcna.2012.12.013","article-title":"Relevance of magnetic resonance imaging for early detection and diagnosis of Alzheimer disease.","volume":"97","author":"Teipel","year":"2013","journal-title":"Med. Clin. North Am."},{"key":"B43","doi-asserted-by":"publisher","first-page":"1067","DOI":"10.1136\/amiajnl-2012-001503","article-title":"Investigating the link between radiologists\u2019 gaze, diagnostic decision, and image content.","volume":"20","author":"Tourassi","year":"2013","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"B44","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1136\/jnnp.2005.075341","article-title":"Hippocampal atrophy on MRI in frontotemporal lobar degeneration and Alzheimer\u2019s disease.","volume":"77","author":"van de Pol","year":"2006","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12559-023-10192-x","article-title":"Explainable artificial intelligence in Alzheimer\u2019s disease classification: A systematic review.","volume":"16","author":"Viswan","year":"2024","journal-title":"Cogn. Comput."},{"key":"B46","doi-asserted-by":"publisher","first-page":"2937","DOI":"10.14336\/AD.2024.1071","article-title":"The expanding burden of neurodegenerative diseases: An unmet medical and social need.","volume":"16","author":"Wang","year":"2024","journal-title":"Aging Dis."},{"key":"B47","doi-asserted-by":"publisher","first-page":"110934","DOI":"10.1016\/j.ejrad.2023.110934","article-title":"Artificial intelligence-based diagnosis of Alzheimer\u2019s disease with brain MRI images.","volume":"165","author":"Yao","year":"2023","journal-title":"Eur. J. Radiol."},{"key":"B48","doi-asserted-by":"publisher","first-page":"e95755","DOI":"10.1371\/journal.pone.0095755","article-title":"Cognitive decline in patients with Alzheimer\u2019s disease and its related factors in a memory clinic setting. Shanghai, China.","volume":"9","author":"Zhao","year":"2014","journal-title":"PLoS One"}],"container-title":["Frontiers in Neuroinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2026.1821249\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T12:48:30Z","timestamp":1778676510000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2026.1821249\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,13]]},"references-count":48,"alternative-id":["10.3389\/fninf.2026.1821249"],"URL":"https:\/\/doi.org\/10.3389\/fninf.2026.1821249","relation":{},"ISSN":["1662-5196"],"issn-type":[{"value":"1662-5196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,13]]},"article-number":"1821249"}}