{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T18:42:04Z","timestamp":1776710524837,"version":"3.51.2"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>As one of the most common neurodegenerative diseases, Alzheimer\u2019s accounts for serious health problems worldwide. Accurate detection and prediction of this disease contribute to the health system for better prevention and interventions in the treatment plans. However, traditional models designed for prediction and classification face several challenges, including handling complex data, which neglects many data points for the diagnosis. To overcome this challenge, we propose a novel model based on the integration of Neural Processes (NPs) and Normalizing Flows (NFs). The dataset used for this study is the Alzheimer\u2019s Disease Prediction of Longitudinal Evolution (TADPOLE). We selected various features to build an efficient model, including cognitive, neuroimaging, genetic, and demographic data. which contains three classes: Cognitively Normal (CN), Mild Cognitive Impairment (MCI), and AD. The proposed model is able to capture the temporal dependencies present in the complex distribution. The stochastic processes were modeled by NPs, while NF was able to transform the Gaussian distributions from simple to complex distributions, allowing them to model a wide range of data distributions. The prediction performance and robustness have been enhanced since this framework is able the adapt to every patient trajectory and generalizing across different populations. The model was compared with other models, such as SNP, deep geometric learning, Manifold DCNN, and other models. Our model (SNP-NF) made an improvement regarding mAUC, Precision, and Recall, approximately 3%,1%, and 0.7%, respectively from our previous model, which utilized only NP. These results demonstrate the capability of the proposed approach to provide early detection and personal treatment plans for patients suffering from this disease.<\/jats:p>","DOI":"10.1371\/journal.pone.0345958","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T17:47:12Z","timestamp":1776707232000},"page":"e0345958","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Normalizing flow based neural processes for Alzheimer\u2019s disease progression prediction"],"prefix":"10.1371","volume":"21","author":[{"given":"Emad","family":"Al-anbari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5607-4963","authenticated-orcid":true,"given":"Hossein","family":"Karshenas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1993-6370","authenticated-orcid":true,"given":"Bijan","family":"Shoushtarian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"pone.0345958.ref001","first-page":"1","article-title":"Deep learning approaches for early prediction of conversion from MCI to AD using MRI and clinical data: A systematic review","author":"G Valizadeh","year":"2024","journal-title":"Arch Comput Methods Eng"},{"key":"pone.0345958.ref002","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.compbiomed.2017.02.011","article-title":"Classification of Alzheimer\u2019s disease and prediction of mild cognitive impairment-to-Alzheimer\u2019s conversion from structural magnetic resource imaging using feature ranking and a genetic algorithm","volume":"83","author":"I Beheshti","year":"2017","journal-title":"Comput Biol Med"},{"key":"pone.0345958.ref003","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1016\/j.neuroimage.2014.10.002","article-title":"Machine learning framework for early MRI-based Alzheimer\u2019s conversion prediction in MCI subjects","volume":"104","author":"E Moradi","year":"2015","journal-title":"Neuroimage"},{"issue":"8","key":"pone.0345958.ref004","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1016\/j.jalz.2019.02.007","article-title":"A deep learning model for early prediction of Alzheimer\u2019s disease dementia based on hippocampal magnetic resonance imaging data","volume":"15","author":"H Li","year":"2019","journal-title":"Alzheimers Dement"},{"issue":"10","key":"pone.0345958.ref005","doi-asserted-by":"crossref","first-page":"1842","DOI":"10.3390\/healthcare10101842","article-title":"Deep Learning Techniques for the Effective Prediction of Alzheimer\u2019s Disease: A Comprehensive Review","volume":"10","author":"KA Shastry","year":"2022","journal-title":"Healthcare (Basel)"},{"key":"pone.0345958.ref006","doi-asserted-by":"crossref","first-page":"777","DOI":"10.3389\/fnins.2018.00777","article-title":"Convolutional Neural Networks-Based MRI Image Analysis for the Alzheimer\u2019s Disease Prediction From Mild Cognitive Impairment","volume":"12","author":"W Lin","year":"2018","journal-title":"Front Neurosci"},{"key":"pone.0345958.ref007","first-page":"1","article-title":"RNN-based longitudinal analysis for diagnosis of Alzheimer\u2019s disease","volume":"73","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2019","journal-title":"Comput Med Imaging Graph"},{"key":"pone.0345958.ref008","doi-asserted-by":"crossref","first-page":"222126","DOI":"10.1109\/ACCESS.2020.3043715","article-title":"An Ensemble-Learning Based Application to Predict the Earlier Stages of Alzheimer\u2019s Disease (AD)","volume":"8","author":"AH Syed","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0345958.ref009","unstructured":"Garnelo M, Schwarz J, Rosenbaum D, Viola F, Rezende DJ, Eslami S, et al. Neural processes. arXiv preprint arXiv:180701622. 2018."},{"issue":"5","key":"pone.0345958.ref010","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1016\/j.jalz.2017.11.004","article-title":"A prognostic model of Alzheimer\u2019s disease relying on multiple longitudinal measures and time-to-event data","volume":"14","author":"K Li","year":"2018","journal-title":"Alzheimers Dement"},{"issue":"2","key":"pone.0345958.ref011","doi-asserted-by":"crossref","first-page":"212","DOI":"10.14283\/jpad.2023.13","article-title":"Longitudinal Exposure-Response Modeling of Multiple Indicators of Alzheimer\u2019s Disease Progression","volume":"10","author":"DG Polhamus","year":"2023","journal-title":"J Prev Alzheimers Dis"},{"issue":"282","key":"pone.0345958.ref012","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1080\/01621459.1958.10501452","article-title":"Nonparametric Estimation from Incomplete Observations","volume":"53","author":"EL Kaplan","year":"1958","journal-title":"J Am Stat Assoc"},{"issue":"9","key":"pone.0345958.ref013","doi-asserted-by":"crossref","first-page":"3072","DOI":"10.1093\/brain\/awaf151","article-title":"Structural covariance analysis for neurodegenerative and neuroinflammatory brain disorders","volume":"148","author":"N Mongay-Ochoa","year":"2025","journal-title":"Brain"},{"issue":"5","key":"pone.0345958.ref014","doi-asserted-by":"crossref","first-page":"2231","DOI":"10.3390\/ijms26052231","article-title":"Molecular Biomarkers in Neurological Diseases: Advances in Diagnosis and Prognosis","volume":"26","author":"A Myrou","year":"2025","journal-title":"Int J Mol Sci"},{"issue":"1","key":"pone.0345958.ref015","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1186\/s12874-024-02198-2","article-title":"Methods of determining optimal cut-point of diagnostic biomarkers with application of clinical data in ROC analysis: an update review","volume":"24","author":"M Hassanzad","year":"2024","journal-title":"BMC Med Res Methodol"},{"key":"pone.0345958.ref016","doi-asserted-by":"crossref","first-page":"593898","DOI":"10.3389\/fnagi.2021.593898","article-title":"Gray Matter Deterioration Pattern During Alzheimer\u2019s Disease Progression: A Regions-of-Interest Based Surface Morphometry Study","volume":"13","author":"Z Wu","year":"2021","journal-title":"Front Aging Neurosci"},{"key":"pone.0345958.ref017","doi-asserted-by":"crossref","first-page":"102913","DOI":"10.1016\/j.media.2023.102913","article-title":"Gaussian Process-based prediction of memory performance and biomarker status in ageing and Alzheimer\u2019s disease-A systematic model evaluation","volume":"90","author":"A Nemali","year":"2023","journal-title":"Med Image Anal"},{"issue":"1","key":"pone.0345958.ref018","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1186\/s13195-024-01517-5","article-title":"Predicting progression from subjective cognitive decline to mild cognitive impairment or dementia based on brain atrophy patterns","volume":"16","author":"O Lerch","year":"2024","journal-title":"Alzheimers Res Ther"},{"key":"pone.0345958.ref019","doi-asserted-by":"crossref","first-page":"107782","DOI":"10.1016\/j.engappai.2023.107782","article-title":"Multi-modal imaging genetics data fusion by deep auto-encoder and self-representation network for Alzheimer\u2019s disease diagnosis and biomarkers extraction","volume":"130","author":"C-N Jiao","year":"2024","journal-title":"Eng Appl Artif Intell"},{"issue":"2","key":"pone.0345958.ref020","doi-asserted-by":"crossref","first-page":"759","DOI":"10.11591\/eei.v10i2.2714","article-title":"A new model for early diagnosis of alzheimer\u2019s disease based on BAT-SVM classifier","volume":"10","author":"SA Taie","year":"2021","journal-title":"Bulletin EEI"},{"issue":"8","key":"pone.0345958.ref021","doi-asserted-by":"crossref","first-page":"4508","DOI":"10.3390\/ijerph19084508","article-title":"Temporal and Spatial Analysis of Alzheimer\u2019s Disease Based on an Improved Convolutional Neural Network and a Resting-State FMRI Brain Functional Network","volume":"19","author":"H Sun","year":"2022","journal-title":"Int J Environ Res Public Health"},{"issue":"12","key":"pone.0345958.ref022","doi-asserted-by":"crossref","first-page":"791","DOI":"10.3390\/info15120791","article-title":"UniFlow: Unified Normalizing Flow for Unsupervised Multi-Class Anomaly Detection","volume":"15","author":"J Zhong","year":"2024","journal-title":"Information"},{"key":"pone.0345958.ref023","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1182\/blood-2024-205413","article-title":"Enhancing Personalized Prognostic Assessment of Myelodysplastic Syndromes through a Multimodal and Explainable Deep Data Fusion Approach (MAGAERA)","volume":"144","author":"E Sauta","year":"2024","journal-title":"Blood"},{"key":"pone.0345958.ref024","doi-asserted-by":"crossref","first-page":"3198066","DOI":"10.1155\/2023\/3198066","article-title":"Using CNN Saliency Maps and EEG Modulation Spectra for Improved and More Interpretable Machine Learning-Based Alzheimer\u2019s Disease Diagnosis","volume":"2023","author":"M Lopes","year":"2023","journal-title":"Comput Intell Neurosci"},{"issue":"4","key":"pone.0345958.ref025","article-title":"Federated learning with multi-cohort real-world data for predicting the progression from mild cognitive impairment to Alzheimer\u2019s disease","volume":"21","author":"J Pan","year":"2025","journal-title":"Alzheimers Dement"},{"key":"pone.0345958.ref026","doi-asserted-by":"crossref","unstructured":"Selvan R, Faye F, Middleton J, Pai A. Uncertainty quantification in medical image segmentation with Normalizing Flows. In: MLMI@MICCAI. 2020. Available from: https:\/\/api.semanticscholar.org\/CorpusID:219305718","DOI":"10.1007\/978-3-030-59861-7_9"},{"key":"pone.0345958.ref027","unstructured":"Kim H, Mnih A, Schwarz J, Garnelo M, Eslami A, Rosenbaum D, et al. Attentive neural processes. arXiv preprint arXiv:190105761. 2019."},{"key":"pone.0345958.ref028","unstructured":"Nguyen T, Grover A. Transformer neural processes: Uncertainty-aware meta learning via sequence modeling. arXiv preprint arXiv:220704179. 2022."},{"key":"pone.0345958.ref029","doi-asserted-by":"crossref","first-page":"44607","DOI":"10.1109\/ACCESS.2025.3548173","article-title":"A Novel Approach to the Prediction of Alzheimer\u2019s Disease Progression by Leveraging Neural Processes and a Transformer Encoder Model","volume":"13","author":"E Al-Anbari","year":"2025","journal-title":"IEEE Access"},{"key":"pone.0345958.ref030","unstructured":"Smith A, et al. Conditional normalizing flows for high-dimensional classification tasks. IEEE Trans Neural Netw Learn Syst. 2023."},{"key":"pone.0345958.ref031","unstructured":"John D, et al. Uncertainty quantification in classification using normalizing flows. J Mach Learn Res. 2023."},{"key":"pone.0345958.ref032","unstructured":"Zhang Y. Interpretable machine learning for Alzheimer\u2019s disease diagnosis. J Biomed Inform. 2022."},{"key":"pone.0345958.ref033","unstructured":"Li W. Augmented normalizing flows for imbalanced multi-class classification. IEEE Access. 2023."},{"issue":"3","key":"pone.0345958.ref034","first-page":"1142","article-title":"Institute of Mathematical Statistics is collaborating with JSTOR to digitize, preserve, and extend access the annals of mathematical statistics","volume":"42","author":"J Wals","year":"1971","journal-title":"Ann Math Stat"},{"key":"pone.0345958.ref035","unstructured":"Kingma DP. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980. 2014."},{"key":"pone.0345958.ref036","unstructured":"Dataset Website. https:\/\/tadpole.grand-challenge.org\/"},{"key":"pone.0345958.ref037","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/j.media.2019.01.004","article-title":"Training recurrent neural networks robust to incomplete data: Application to Alzheimer\u2019s disease progression modeling","volume":"53","author":"M Mehdipour Ghazi","year":"2019","journal-title":"Med Image Anal"},{"key":"pone.0345958.ref038","unstructured":"Marinescu RV, Oxtoby NP, Young AL, Bron EE, Toga AW, Weiner MW, et al. TADPOLE challenge: prediction of longitudinal evolution in Alzheimer\u2019s disease. arXiv preprint arXiv:180503909. 2018."},{"key":"pone.0345958.ref039","unstructured":"Grandini M, Bagli E, Visani G. Metrics for multi-class classification: an overview. arXiv preprint arXiv:200805756. 2020."},{"issue":"5","key":"pone.0345958.ref040","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.1109\/TBME.2018.2874712","article-title":"Estimating Missing Data in Temporal Data Streams Using Multi-Directional Recurrent Neural Networks","volume":"66","author":"J Yoon","year":"2019","journal-title":"IEEE Trans Biomed Eng"},{"key":"pone.0345958.ref041","doi-asserted-by":"crossref","first-page":"117203","DOI":"10.1016\/j.neuroimage.2020.117203","article-title":"Predicting Alzheimer\u2019s disease progression using deep recurrent neural networks","volume":"222","author":"M Nguyen","year":"2020","journal-title":"Neuroimage"},{"key":"pone.0345958.ref042","doi-asserted-by":"crossref","unstructured":"Almubark I, Alsegehy S, Jiang X, Chang LC. Classification of Alzheimer\u2019s disease, mild cognitive impairment, and normal controls with multilayer perceptron neural network and neuropsychological test data. In: IJCCI. 2020. p. 439\u201346.","DOI":"10.5220\/0010143304390446"},{"key":"pone.0345958.ref043","unstructured":"Chakraborty R, Yang CH, Zhen X, Banerjee M, Archer D, Vaillancourt D, et al. A statistical recurrent model on the manifold of symmetric positive definite matrices. In: Advances in neural information processing systems. 2018;31."},{"key":"pone.0345958.ref044","first-page":"10620","article-title":"Dilated Convolutional Neural Networks for Sequential Manifold-valued Data","volume":"2019","author":"X Zhen","year":"2019","journal-title":"Proc IEEE Int Conf Comput Vis"},{"issue":"4","key":"pone.0345958.ref045","doi-asserted-by":"crossref","first-page":"7090","DOI":"10.1109\/TNNLS.2024.3394598","article-title":"Deep Geometric Learning With Monotonicity Constraints for Alzheimer\u2019s Disease Progression","volume":"36","author":"S Jeong","year":"2025","journal-title":"IEEE Trans Neural Netw Learn Syst"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0345958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T17:47:20Z","timestamp":1776707240000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0345958"}},"subtitle":[],"editor":[{"given":"Jose Gerardo","family":"Tamez-Pe\u00f1a","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":45,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0345958","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,20]]}}}