{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T01:10:36Z","timestamp":1792804236231,"version":"4.5.0"},"reference-count":34,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T00:00:00Z","timestamp":1753401600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Delft University of Technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background: Mild Cognitive Impairment (MCI) represents an intermediate stage between normal cognitive aging and Alzheimer\u2019s Disease (AD). Early and accurate identification of MCI is crucial for implementing interventions that may delay or prevent further cognitive decline. This study aims to develop a machine learning-based model for differentiating between Cognitively Normal (CN) individuals and MCI patients using data from the Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI). Methods: An ensemble classification approach was designed by integrating Extra Trees, Random Forest, and Light Gradient Boosting Machine (LightGBM) algorithms. Feature selection emphasized clinically relevant biomarkers, including Amyloid-\u03b2 42, phosphorylated tau, diastolic blood pressure, age, and gender. The dataset was split into training and held-out test sets. A probability thresholding strategy was employed to flag uncertain predictions for potential deferral, enhancing model reliability in borderline cases. Results: The final ensemble model achieved an accuracy of 83.2%, a recall of 80.2%, and a precision of 86.3% on the independent test set. The probability thresholding mechanism flagged 23.3% of cases as uncertain, allowing the system to abstain from low-confidence predictions. This strategy improved clinical interpretability and minimized the risk of misclassification in ambiguous cases. Conclusions: The proposed AI-driven ensemble model demonstrates strong performance in classifying MCI versus CN individuals using multimodal ADNI data. Incorporating a deferral mechanism through uncertainty estimation further enhances the model\u2019s clinical utility. These findings support the integration of machine learning tools into early screening workflows for cognitive impairment.<\/jats:p>","DOI":"10.3390\/jcm14155261","type":"journal-article","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T09:35:11Z","timestamp":1753436111000},"page":"5261","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["AI-Based Classification of Mild Cognitive Impairment and Cognitively Normal Patients"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6857-3927","authenticated-orcid":false,"given":"Rafail","family":"Christodoulou","sequence":"first","affiliation":[{"name":"Department of Radiology, Stanford University School of Medicine, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5100-5802","authenticated-orcid":false,"given":"Giorgos","family":"Christofi","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, 2628 Delft, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rafael","family":"Pitsillos","sequence":"additional","affiliation":[{"name":"Department of Neurophysiology, The Cyprus Institute of Neurology and Genetics, Nicosia 2371, Cyprus"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reina","family":"Ibrahim","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, University of Balamand, Balamand 2807, Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6102-3344","authenticated-orcid":false,"given":"Platon","family":"Papageorgiou","sequence":"additional","affiliation":[{"name":"2nd Department of Orthopaedic Surgery and Traumatology, Aghia Sophia Pediatric General Hospital, Thivon 3 Street, 15772 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8863-3635","authenticated-orcid":false,"given":"Sokratis G.","family":"Papageorgiou","sequence":"additional","affiliation":[{"name":"1st Department of Neurology, Medical School, National and Kapodistrian University of Athens, Eginition Hospital, 15772 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evros","family":"Vassiliou","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Union, NJ 07083, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michalis F.","family":"Georgiou","sequence":"additional","affiliation":[{"name":"Department of Radiology, Division of Nuclear Medicine, University of Miami, Miami, FL 33136, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1017\/S1092852918001347","article-title":"State of the science on mild cognitive impairment (MCI)","volume":"24","author":"Anderson","year":"2019","journal-title":"CNS Spectr."},{"key":"ref_2","unstructured":"World Health Organization (WHO) (2025, April 30). Dementia. Available online: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/dementia."},{"key":"ref_3","first-page":"afac173","article-title":"Worldwide prevalence of mild cognitive impairment among community dwellers aged 50 years and older: A meta-analysis and systematic review of epidemiology studies","volume":"51","author":"Bai","year":"2022","journal-title":"Age Ageing"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1001\/archneur.56.3.303","article-title":"Mild cognitive impairment: Clinical characterization and outcome","volume":"56","author":"Petersen","year":"1999","journal-title":"Arch. Neurol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1016\/j.cger.2014.04.001","article-title":"Dementia and cognitive impairment: Epidemiology, diagnosis, and treatment","volume":"30","author":"Hugo","year":"2014","journal-title":"Clin. Geriatr. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.neurobiolaging.2012.03.010","article-title":"Visual ratings of atrophy in MCI: Prediction of conversion and relationship with CSF biomarkers","volume":"34","author":"Lehmann","year":"2013","journal-title":"Neurobiol. Aging"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1186\/s13024-020-00395-3","article-title":"Neuroimaging advances regarding subjective cognitive decline in preclinical Alzheimer\u2019s disease","volume":"15","author":"Wang","year":"2020","journal-title":"Mol. Neurodegener."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"5885","DOI":"10.1002\/alz.13412","article-title":"Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review","volume":"19","author":"Borchert","year":"2023","journal-title":"Alzheimer\u2019s Dement. J. Alzheimer\u2019s Assoc."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1016\/j.beth.2020.05.002","article-title":"Supervised Machine Learning: A Brief Primer","volume":"51","author":"Jiang","year":"2020","journal-title":"Behav. Ther."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Lama, R.K., and Kwon, G.R. (2021). Diagnosis of Alzheimer\u2019s Disease Using Brain Network. Front. Neurosci., 15.","DOI":"10.3389\/fnins.2021.605115"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Battineni, G., Hossain, M.A., Chintalapudi, N., Traini, E., Dhulipalla, V.R., Ramasamy, M., and Amenta, F. (2021). Improved Alzheimer\u2019s Disease Detection by MRI Using Multimodal Machine Learning Algorithms. Diagnostics, 11.","DOI":"10.3390\/diagnostics11112103"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"5154","DOI":"10.1016\/j.acra.2024.06.040","article-title":"Combined Quantitative amyloid-\u03b2 PET and Structural MRI Features Improve Alzheimer\u2019s Disease Classification in Random Forest Model\u2014A Multicenter Study","volume":"31","author":"Bao","year":"2024","journal-title":"Acad. Radiol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"El-Latif, A.A.A., Chelloug, S.A., Alabdulhafith, M., and Hammad, M. (2023). Accurate Detection of Alzheimer\u2019s Disease Using Lightweight Deep Learning Model on MRI Data. Diagnostics, 13.","DOI":"10.3390\/diagnostics13071216"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"65055","DOI":"10.1109\/ACCESS.2022.3180073","article-title":"Automated Detection of Alzheimer\u2019s Disease and Mild Cognitive Impairment Using Whole Brain MRI","volume":"10","author":"Faisal","year":"2022","journal-title":"IEEE Access"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"29870","DOI":"10.1109\/ACCESS.2021.3059658","article-title":"Volumetric Feature-Based Alzheimer\u2019s Disease Diagnosis from sMRI Data Using a Convolutional Neural Network and a Deep Neural Network","volume":"9","author":"Basher","year":"2021","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"102444","DOI":"10.1016\/j.media.2022.102444","article-title":"Recent advances and clinical applications of deep learning in medical image analysis","volume":"79","author":"Chen","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"100083","DOI":"10.1016\/j.tjpad.2025.100083","article-title":"Joint ensemble learning-based risk prediction of Alzheimer\u2019s disease among mild cognitive impairment patients","volume":"12","author":"Guan","year":"2025","journal-title":"J. Prev. Alzheimer\u2019s Dis."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Mujahid, M., Rehman, A., Alam, T., Alamri, F.S., Fati, S.M., and Saba, T. (2023). An Efficient Ensemble Approach for Alzheimer\u2019s Disease Detection Using an Adaptive Synthetic Technique and Deep Learning. Diagnostics, 13.","DOI":"10.3390\/diagnostics13152489"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, P., Lin, S., Qiao, J., and Tu, Y. (2021). Diagnosis of Alzheimer\u2019s Disease with Ensemble Learning Classifier and 3D Convolutional Neural Network. Sensors, 21.","DOI":"10.3390\/s21227634"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Khan, Y.F., Kaushik, B., Chowdhary, C.L., and Srivastava, G. (2022). Ensemble Model for Diagnostic Classification of Alzheimer\u2019s Disease Based on Brain Anatomical Magnetic Resonance Imaging. Diagnostics, 12.","DOI":"10.3390\/diagnostics12123193"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1126\/science.8346443","article-title":"Gene dose of apolipoprotein E type 4 allele and the risk of Alzheimer\u2019s disease in late onset families","volume":"261","author":"Corder","year":"1993","journal-title":"Science"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1016\/j.mayocp.2017.02.011","article-title":"Alzheimer Disease: Scientific Breakthroughs and Translational Challenges","volume":"92","author":"Caselli","year":"2017","journal-title":"Mayo Clin. Proc."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/S1550-8579(07)80026-X","article-title":"Gender differences in dementia risk factors","volume":"4","author":"Azad","year":"2007","journal-title":"Gend. Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1002\/ana.410140502","article-title":"Senile dementia of the Alzheimer type","volume":"14","author":"Terry","year":"1983","journal-title":"Ann. Neurol."},{"key":"ref_25","first-page":"CD010945","article-title":"Plasma and cerebrospinal fluid ABeta42 for the differential diagnosis of Alzheimer\u2019s disease dementia in participants diagnosed with any dementia subtype in a specialist care setting","volume":"2","author":"Kokkinou","year":"2021","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1001\/archneurol.2008.596","article-title":"Cerebrospinal fluid {beta}-amyloid 42 and tau proteins as biomarkers of Alzheimer-type pathologic changes in the brain","volume":"66","author":"Tapiola","year":"2009","journal-title":"Arch. Neurol."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ruiz, A., Pesini, P., Espinosa, A., P\u00e9rez-Grijalba, V., Valero, S., Sotolongo-Grau, O., Alegret, M., Monle\u00f3n, I., Lafuente, A., and Buend\u00eda, M. (2013). Blood amyloid beta levels in healthy, mild cognitive impairment and Alzheimer\u2019s disease individuals: Replication of diastolic blood pressure correlations and analysis of critical covariates. PLoS ONE, 8.","DOI":"10.1371\/journal.pone.0081334"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"96981","DOI":"10.1109\/ACCESS.2020.2997736","article-title":"Optimized one vs one approach in multiclass classification for early alzheimer\u2019s disease and mild cognitive impairment diagnosis","volume":"8","author":"Illan","year":"2020","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"115974","DOI":"10.1109\/ACCESS.2022.3218621","article-title":"Automatic Early Diagnosis of Alzheimer\u2019s Disease Using 3D Deep Ensemble Approach","volume":"10","author":"Gamal","year":"2022","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e59370","DOI":"10.2196\/59370","article-title":"Machine learning driven by magnetic resonance imaging for the classification of Alzheimer disease progression: Systematic review and meta-analysis","volume":"7","author":"Battineni","year":"2024","journal-title":"JMIR Aging"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e70802","DOI":"10.1002\/hsr2.70802","article-title":"Recent advancements in neuroimaging-based Alzheimer\u2019s disease prediction using deep learning approaches in e-health: A systematic review","volume":"8","author":"Awang","year":"2025","journal-title":"Health Sci. Rep."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1016\/j.jalz.2015.04.005","article-title":"Impact of the Alzheimer\u2019s Disease Neuroimaging Initiative, 2004 to 2014","volume":"11","author":"Weiner","year":"2015","journal-title":"Alzheimer\u2019s Dement. J. Alzheimer\u2019s Assoc."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Gupta, Y., Kim, J.I., Kim, B.C., and Kwon, G.R. (2020). Classification and Graphical Analysis of Alzheimer\u2019s Disease and Its Prodromal Stage Using Multimodal Features From Structural, Diffusion, and Functional Neuroimaging Data and the APOE Genotype. Front. Aging Neurosci., 12.","DOI":"10.3389\/fnagi.2020.00238"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Wu, J., Dong, Q., Zhang, J., Su, Y., Wu, T., Caselli, R.J., Reiman, E.M., Ye, J., Lepore, N., and Chen, K. (2021). Federated Morphometry Feature Selection for Hippocampal Morphometry Associated Beta-Amyloid and Tau Pathology. Front. Neurosci., 15.","DOI":"10.3389\/fnins.2021.762458"}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/15\/5261\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:15:51Z","timestamp":1760033751000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/15\/5261"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,25]]},"references-count":34,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["jcm14155261"],"URL":"https:\/\/doi.org\/10.3390\/jcm14155261","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,25]]}}}