{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T16:06:29Z","timestamp":1772640389866,"version":"3.50.1"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T00:00:00Z","timestamp":1755475200000},"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>Background<\/jats:title><jats:p>Alzheimer's disease (AD) greatly affects the daily functioning and life quality of patients and is prevalent in the elderly population. Amyloid-\u03b2 (A\u03b2) accumulation in the brain is the main hallmark of AD pathophysiology. Positron Emission Tomography (PET) imaging is the most accurate method to identify A\u03b2 deposits in the brain, but it is expensive and not widely available. The development of a low-cost method to detect A\u03b2 deposition in the brain, as an alternative to PET, would therefore be of great value. This study aims to develop and validate machine learning algorithms for accurately predicting brain A\u03b2 positivity using plasma biomarkers, genetic information, and clinical data as a cost-effective alternative to PET imaging.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We analyzed 1,043 patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and validated our models on 127 patients from the Center for Neurodegeneration and Translational Neuroscience (CNTN) dataset. Brain A\u03b2 status was determined using plasma biomarkers [A\u03b242, A\u03b240, Phosphorylated tau (pTau) 181, Neurofilament light chain (NfL)], Apolipoprotein E (APOE) genotype, and clinical information [Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA), age, education year, and gender]. Decision tree, random forest, support vector machine, and multilayer perceptron machine learning methods were used to combine all this information. We introduced a feature selection method to balance the performance and the number of features. We conducted a feature matching technique to enable our model to be tested on the external dataset without retraining.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Our system achieved a value of 0.95 for the Area Under the ROC curve (AUC) using the ADNI dataset (<jats:italic>n<\/jats:italic> = 340) and the full set of 11 features. Our architecture was also tested on an external dataset (CNTN, <jats:italic>n<\/jats:italic> = 127) and achieved an AUC of 0.90. When using only five features (pTau 181, A\u03b242\/40, A\u03b242, APOE \u025b4 count, and MMSE) on 341 ADNI patients, we achieved an AUC of 0.87.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The random forest, support vector machine and multilayer perceptron methods can accurately predict brain A\u03b2 status using plasma biomarkers, genotype, and clinical information. The method generalizes well to an independent dataset and can be reduced to using only five features without losing much accuracy, thus providing an inexpensive alternative to PET imaging.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnagi.2025.1559459","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T13:42:14Z","timestamp":1755524534000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Accurate and robust prediction of Amyloid-\u03b2 brain deposition from plasma biomarkers and clinical information using machine learning"],"prefix":"10.3389","volume":"17","author":[{"given":"Jiayuan","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew J.","family":"Doig","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sofia","family":"Michopoulou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petroula","family":"Proitsi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fumie","family":"Costen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"name":"The Alzheimer's disease neuroimaging initiative","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,18]]},"reference":[{"key":"B1","unstructured":"Alzheimer's Disease Neuroimaging Initiative\n          \n          2004"},{"key":"B2","unstructured":"Australian Imaging, Biomarker and Lifestyle\n          \n          2006"},{"key":"B3","doi-asserted-by":"publisher","first-page":"198","DOI":"10.22266\/ijies2021.1231.19","article-title":"Performance comparison of grid search and random search methods for hyperparameter tuning in extreme gradient boosting algorithm to predict chronic kidney failure","volume":"14","author":"Anggoro","year":"2021","journal-title":"Int. J. Intell. Eng. Syst"},{"key":"B4","doi-asserted-by":"publisher","first-page":"7220","DOI":"10.1126\/sciadv.aau7220","article-title":"A plasma protein classifier for predicting amyloid burden for preclinical Alzheimer's disease","volume":"5","author":"Ashton","year":"2019","journal-title":"Sci. Adv"},{"key":"B5","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1136\/jnnp-2021-327864","article-title":"Plasma A\u03b2 as a biomarker for predicting A\u03b2-PET status in Alzheimer's disease: a systematic review with meta-analysis","volume":"93","author":"Cheng","year":"2022","journal-title":"J. Neurol. Neurosurg. Psychiat"},{"key":"B6","unstructured":"Center for neurodegeneration and translational neuroscience\n          \n          2015"},{"key":"B7","unstructured":"Amyloid and tau: the proteins involved in dementia\n          \n          2021"},{"key":"B8","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1016\/S1474-4422(18)30029-2","article-title":"Cognitive and neuroimaging features and brain \u03b2-amyloidosis in individuals at risk of Alzheimer's disease (INSIGHT-preAD): a longitudinal observational study","volume":"17","author":"Dubois","year":"2018","journal-title":"The Lancet Neurol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.neunet.2018.11.005","article-title":"A comparison of deep networks with ReLU activation function and linear spline-type methods","volume":"110","author":"Eckle","year":"2019","journal-title":"Neural Networks"},{"key":"B10","author":"G\u00e9ron","year":"2022","journal-title":"Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: concepts, tools, and techniques to build intelligent systems"},{"key":"B11","article-title":"\u201cAdam: a method for stochastic optimization,\u201d","author":"Kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015"},{"key":"B12","doi-asserted-by":"publisher","first-page":"95","DOI":"10.3389\/fnagi.2019.00095","article-title":"Cognitive profiling related to cerebral amyloid beta burden using machine learning approaches","volume":"11","author":"Ko","year":"2019","journal-title":"Front. Aging Neurosci"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e14022","DOI":"10.15252\/emmm.202114022","article-title":"Soluble P'tau217 reflects amyloid and tau pathology and mediates the association of amyloid with tau","volume":"13","author":"Mattsson-Carlgren","year":"2021","journal-title":"EMBO Mol. Med"},{"key":"B14","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1186\/s13195-024-01415-w","article-title":"Machine learning prediction of future amyloid beta positivity in amyloid-negative individuals","volume":"16","author":"Moradi","year":"2024","journal-title":"Alzheimer's Res. Ther"},{"key":"B15","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1038\/nature25456","article-title":"High performance plasma amyloid-\u03b2 biomarkers for alzheimer's disease","volume":"554","author":"Nakamura","year":"2018","journal-title":"Nature"},{"key":"B16","unstructured":"2023"},{"key":"B17","unstructured":"Neurogrid\n          \n          2015"},{"key":"B18","doi-asserted-by":"publisher","first-page":"355","DOI":"10.3233\/ADR-230029","article-title":"Plasma biomarkers of Alzheimer's disease: a review of available assays, recent developments, and implications for clinical practice","volume":"7","author":"Pais","year":"2023","journal-title":"J. Alzheimer's Dis. Rep"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1001\/jamaneurol.2019.1632","article-title":"Performance of fully automated plasma assays as screening tests for Alzheimer disease-related \u03b2-amyloid status","volume":"76","author":"Palmqvist","year":"2019","journal-title":"JAMA Neurol."},{"key":"B20","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s43856-023-00295-9","article-title":"Integrated algorithm combining plasma biomarkers and cognitive assessments accurately predicts brain \u03b2-amyloid pathology","volume":"3","author":"Pan","year":"2023","journal-title":"Commun. Med"},{"key":"B21","unstructured":"Radiologists must monitor novel Alzheimer's treatment side effect, says study\n          \n          2023"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1136\/jnnp-2020-325537","article-title":"Associations of longitudinal plasma p-tau181 and NfL with tau-PET, A\u03b2-PET and cognition","volume":"92","author":"Rauchmann","year":"2021","journal-title":"J. Neurol. Neurosurg. Psychiat"},{"key":"B23","unstructured":"Polynomial kernel\n          \n          2023"},{"key":"B24","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1038\/s41398-021-01476-7","article-title":"Plasma phosphorylated-tau181 as a predictive biomarker for Alzheimer's amyloid, tau and FDG PET status","volume":"11","author":"Shen","year":"2021","journal-title":"Transl. Psychiat"},{"key":"B25","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1186\/s13195-018-0428-1","article-title":"MRI predictors of amyloid pathology: results from the EMIF-AD Multimodal Biomarker Discovery study","volume":"10","author":"Ten Kate","year":"2018","journal-title":"Alzheimer's Res. Ther"},{"key":"B26","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1001\/jamaneurol.2022.4485","article-title":"Association of phosphorylated tau biomarkers with amyloid positron emission tomography vs tau positron emission tomography","volume":"80","author":"Therriault","year":"2023","journal-title":"JAMA Neurol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1016\/j.jalz.2019.03.009","article-title":"Plasma amyloid \u03b2 40\/42 ratio predicts cerebral amyloidosis in cognitively normal individuals at risk for Alzheimer's disease","volume":"15","author":"Vergallo","year":"2019","journal-title":"Alzheimer's Dem"},{"key":"B28","doi-asserted-by":"publisher","first-page":"12173","DOI":"10.1002\/alz.12173","article-title":"APOE interacts with tau PET to influence memory independently of amyloid PET in older adults without dementia","volume":"17","author":"Weigand","year":"2021","journal-title":"Alzheimer's Dem"},{"key":"B29","doi-asserted-by":"publisher","first-page":"e12405","DOI":"10.1002\/dad2.12405","article-title":"Predicting continuous amyloid PET values with CSF and plasma A\u03b242\/A\u03b240","volume":"15","author":"Wisch","year":"2023","journal-title":"Alzheimer's Dem"},{"key":"B30","unstructured":"Dementia\n          \n          2023"},{"key":"B31","doi-asserted-by":"publisher","first-page":"119585","DOI":"10.1016\/j.saa.2021.119585","article-title":"Hyperspectral prediction of sugarbeet seed germination based on gauss kernel SVM","volume":"253","author":"Yang","year":"2021","journal-title":"Spectrochim. Acta Part A"},{"key":"B32","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1186\/s13195-023-01340-4","article-title":"Clinical and biological relevance of glial fibrillary acidic protein in Alzheimer's disease","volume":"15","author":"Yang","year":"2023","journal-title":"Alzheimer's Res. Ther"},{"key":"B33","unstructured":"Youn\n              Y. C.\n            \n            \n              Kim\n              H. R.\n            \n            \n              Shin\n              H.-W.\n            \n            \n              Jeong\n              H.-B.\n            \n            \n              Han\n              S.-W.\n            \n            \n              Pyun\n              J.-M.\n            \n          \n          Alzheimer's disease all markers study"},{"key":"B34","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1186\/s12911-022-02024-z","article-title":"Prediction of amyloid PET positivity via machine learning algorithms trained with EDTA-based blood amyloid-\u03b2 oligomerization data","volume":"22","author":"Youn","year":"","journal-title":"BMC Med. Inform. Decis. Mak"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS.2018.8624183","article-title":"\u201cImproved adam optimizer for deep neural networks,\u201d","author":"Zhang","year":"2018","journal-title":"2018 IEEE\/ACM 26th International Symposium on Quality of Service (IWQoS)"}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1559459\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T13:42:16Z","timestamp":1755524536000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1559459\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,18]]},"references-count":35,"alternative-id":["10.3389\/fnagi.2025.1559459"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2025.1559459","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,18]]},"article-number":"1559459"}}