{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T18:28:32Z","timestamp":1774895312973,"version":"3.50.1"},"reference-count":23,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"First People's Hospital of Yunnan Province","award":["2024nmkfkt-09"],"award-info":[{"award-number":["2024nmkfkt-09"]}]},{"name":"Fuwai Cardiovascular Hospital","award":["2025yfkt-zl-08"],"award-info":[{"award-number":["2025yfkt-zl-08"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Alzheimer\u2019s disease (AD) is a neurodegenerative disorder and the leading cause of dementia. Early diagnosis and monitoring of disease progression are crucial for effective intervention. This study presents a novel disease progression model based on Variational Probabilistic Principal Component Analysis (VPPCA), which uses a Bayesian framework for dimensionality reduction and uncertainty quantification. By analyzing 1,021 amyloid-positive patients from the Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI) database, we extracted 25 features, including CSF (ABETA, TAU, PTAU), PET (FDG, AV45), and MRI volumetrics, along with cognitive and functional assessments. VPPCA compresses these multi-modal biomarkers into a single first principal component score (VPPCA1), which serves as a measure of disease progression. To ensure biological grounding and avoid circularity, we demonstrated that a VPPCA1 model using only non-cognitive features (CSF, PET, MRI, demographics) correlates strongly with cognitive decline (r\u2009=\u20090.658 with ADAS-Cog13), confirming that it captures genuine pathological progression rather than simply reflecting cognitive assessments. Block-wise feature ablation revealed that multi-modal integration is essential, with cognitive features showing the highest importance (0.1064), though all modalities contribute complementarily. In classification tasks, VPPCA exhibited strong performance with ROC-AUC values of 0.990 (CN vs Dementia), 0.774 (CN vs MCI), and 0.785 (MCI vs Dementia). A Bayesian hierarchical longitudinal model effectively captured patient-specific progression trajectories, offering personalized predictions of future disease states. VPPCA outperforms Probabilistic PCA (PPCA) by providing uncertainty quantification, with patient-specific confidence levels (\u03c3\u2009=\u20090.086\u20130.136), which correlate with data quality, enabling automatic risk stratification. This work demonstrates that VPPCA offers a robust, biologically-grounded framework for modeling AD progression, providing actionable uncertainty quantification that improves clinical decision support and facilitates personalized care.<\/jats:p>","DOI":"10.1371\/journal.pone.0342549","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:36:15Z","timestamp":1774892175000},"page":"e0342549","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Disease progression modeling of Alzheimer\u2019s disease based on variational probability principal component analysis"],"prefix":"10.1371","volume":"21","author":[{"given":"Xin","family":"Xiong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6391-5392","authenticated-orcid":true,"given":"Ximin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"name":"for the Alzheimer\u2019s Disease Neuroimaging Initiative","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,3,30]]},"reference":[{"issue":"10284","key":"pone.0342549.ref001","doi-asserted-by":"crossref","first-page":"1577","DOI":"10.1016\/S0140-6736(20)32205-4","volume":"397","author":"P Scheltens","year":"2021","journal-title":"Lancet"},{"issue":"3","key":"pone.0342549.ref002","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.jalz.2007.04.381","article-title":"Forecasting the global burden of Alzheimer\u2019s disease","volume":"3","author":"R Brookmeyer","year":"2007","journal-title":"Alzheimers Dement"},{"issue":"3","key":"pone.0342549.ref003","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1016\/j.jalz.2011.03.003","article-title":"Toward defining the preclinical stages of Alzheimer\u2019s disease: recommendations from the National Institute on Aging-Alzheimer\u2019s Association workgroups on diagnostic guidelines for Alzheimer\u2019s disease","volume":"7","author":"RA Sperling","year":"2011","journal-title":"Alzheimers Dement"},{"key":"pone.0342549.ref004","volume-title":"Machine learning for modeling the progression of Alzheimer disease dementia using clinical data: a systematic literature review. arXiv e-prints","author":"S Kumar","year":"2021"},{"issue":"1","key":"pone.0342549.ref005","doi-asserted-by":"crossref","first-page":"13622","DOI":"10.1038\/s41598-019-49656-2","article-title":"Machine learning for comprehensive forecasting of Alzheimer\u2019s Disease progression","volume":"9","author":"Coalition Against Major Diseases, Abbott, Alliance for Aging Research, Alzheimer\u2019s Association","year":"2019","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0342549.ref006","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/S1474-4422(09)70299-6","article-title":"Hypothetical model of dynamic biomarkers of the Alzheimer\u2019s pathological cascade","volume":"9","author":"CR Jack","year":"2010","journal-title":"Lancet Neurol"},{"key":"pone.0342549.ref007","doi-asserted-by":"crossref","first-page":"120279","DOI":"10.1016\/j.neuroimage.2023.120279","article-title":"Disease progression modelling of Alzheimer\u2019s disease using probabilistic principal components analysis","volume":"278","author":"M Saint-Jalmes","year":"2023","journal-title":"Neuroimage"},{"key":"pone.0342549.ref008","unstructured":"Ayvaz DS, Baytas IM. Investigating conversion from mild cognitive impairment to Alzheimer\u2019s disease using latent space manipulation. 2021."},{"key":"pone.0342549.ref009","author":"ME Tipping","year":"1999"},{"issue":"4","key":"pone.0342549.ref010","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.jalz.2018.02.018","article-title":"NIA-AA Research Framework: Toward a biological definition of Alzheimer\u2019s disease","volume":"14","author":"CR Jack","year":"2018","journal-title":"Alzheimers Dement"},{"key":"pone.0342549.ref011","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1016\/j.dadm.2018.07.002","article-title":"Derivation of cutoffs for the Elecsys\u00ae amyloid \u03b2 (1-42) assay in Alzheimer\u2019s disease","volume":"10","author":"LM Shaw","year":"2018","journal-title":"Alzheimers Dement (Amst)"},{"issue":"4","key":"pone.0342549.ref012","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1002\/ana.21610","article-title":"Cerebrospinal fluid biomarker signature in Alzheimer\u2019s disease neuroimaging initiative subjects","volume":"65","author":"LM Shaw","year":"2009","journal-title":"Ann Neurol"},{"issue":"9","key":"pone.0342549.ref013","doi-asserted-by":"crossref","DOI":"10.1101\/cshperspect.a006221","article-title":"Fluid biomarkers in Alzheimer disease","volume":"2","author":"K Blennow","year":"2012","journal-title":"Cold Spring Harb Perspect Med"},{"issue":"1","key":"pone.0342549.ref014","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1002\/ana.22248","article-title":"Longitudinal assessment of A\u03b2 and cognition in aging and Alzheimer disease","volume":"69","author":"VL Villemagne","year":"2011","journal-title":"Ann Neurol"},{"issue":"6","key":"pone.0342549.ref015","doi-asserted-by":"crossref","DOI":"10.1016\/j.jalz.2014.11.001","article-title":"2014 Update of the Alzheimer\u2019s Disease Neuroimaging Initiative: A review of papers published since its inception","volume":"11","author":"MW Weiner","year":"2015","journal-title":"Alzheimers Dement"},{"issue":"7","key":"pone.0342549.ref016","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1016\/j.jalz.2015.05.001","article-title":"The Alzheimer\u2019s Disease Neuroimaging Initiative 2 PET Core: 2015","volume":"11","author":"W Jagust","year":"2015","journal-title":"Alzheimers Dement"},{"issue":"4","key":"pone.0342549.ref017","doi-asserted-by":"crossref","first-page":"1244","DOI":"10.1016\/j.neuroimage.2010.06.025","article-title":"Head size, age and gender adjustment in MRI studies: a necessary nuisance?","volume":"53","author":"J Barnes","year":"2010","journal-title":"Neuroimage"},{"key":"pone.0342549.ref018","first-page":"509","author":"CM Bishop","year":"1999","journal-title":"Variational principal components"},{"issue":"4","key":"pone.0342549.ref019","doi-asserted-by":"crossref","first-page":"421","DOI":"10.2174\/156720511795745339","article-title":"How should we deal with missing data in clinical trials involving Alzheimer\u2019s disease patients?","volume":"8","author":"N Coley","year":"2011","journal-title":"Curr Alzheimer Res"},{"key":"pone.0342549.ref020","article-title":"Orthogonal sparse linear discriminant analysis","author":"Z Liu","year":"2018","journal-title":"Int J Sys Sci"},{"issue":"3","key":"pone.0342549.ref021","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1177\/0962280217737566","article-title":"Bayesian latent time joint mixed effect models for multicohort longitudinal data","volume":"28","author":"D Li","year":"2019","journal-title":"Stat Methods Med Res"},{"key":"pone.0342549.ref022","doi-asserted-by":"crossref","first-page":"24","DOI":"10.3389\/fdata.2020.00024","article-title":"Statistical Disease Progression Modeling in Alzheimer Disease","volume":"3","author":"LL Raket","year":"2020","journal-title":"Front Big Data"},{"key":"pone.0342549.ref023","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.neuroimage.2017.08.059","article-title":"Probabilistic disease progression modeling to characterize diagnostic uncertainty: Application to staging and prediction in Alzheimer\u2019s disease","volume":"190","author":"M Lorenzi","year":"2019","journal-title":"Neuroimage"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0342549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:36:27Z","timestamp":1774892187000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0342549"}},"subtitle":[],"editor":[{"given":"Yong","family":"Fan","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,30]]},"references-count":23,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,30]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0342549","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,30]]}}}