{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:50:14Z","timestamp":1787010614986,"version":"build-2736575974"},"posted":{"date-parts":[[2025,8,27]]},"group-title":"Neuroscience","reference-count":39,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"id":[{"id":"https:\/\/ror.org\/03tq10v65","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,8,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Alzheimer\u2019s disease shows significantly variable progressions between patients, making early diagnosis, disease monitoring, and care planning difficult. Existing data-driven Disease Progression Models try to tackle this issue, but they usually require sufficiently large datasets of specific diagnostic modalities, which are rarely available in clinical practice. Here, we introduce a new modeling framework capable of predicting individual disease trajectories from sparse, irregularly sampled, multi-modal clinical data. Our method uses (recurrent) Neural Ordinary Differential Equations to determine the current hidden state of a patient from sparse past exams and to forecast future disease progression, illustrating how biomarkers evolve over time. When applied to the ADNI clinical cohort, the model detected early signs of disease more accurately than common data-driven alternatives and effectively tracked changes in biomarker trajectories that align with established clinical knowledge. This provides a versatile tool for accurate diagnosis and monitoring of neurodegenerative diseases.<\/jats:p>","DOI":"10.1101\/2025.08.26.672412","type":"posted-content","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T11:25:11Z","timestamp":1756293911000},"source":"Crossref","is-referenced-by-count":1,"title":["Predicting Alzheimer\u2019s Disease Progression from Sparse Multimodal Data by NeuralODE Models"],"prefix":"10.64898","author":[{"given":"Andrea","family":"Zanin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6662-3433","authenticated-orcid":false,"given":"Stefano","family":"Pagani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7014-972X","authenticated-orcid":false,"given":"Mattia","family":"Corti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0953-5513","authenticated-orcid":false,"given":"Valeria","family":"Crepaldi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3537-6713","authenticated-orcid":false,"given":"Giuseppe","family":"Di Fede","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2138-3878","authenticated-orcid":false,"given":"Paola F.","family":"Antonietti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"the Alzheimer\u2019s Disease Neuroimaging Initiative ADNI","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025082923200823000_2025.08.26.672412v1.1","doi-asserted-by":"publisher","DOI":"10.1111\/ene.13439"},{"key":"2025082923200823000_2025.08.26.672412v1.2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-1331.2010.03040.x"},{"key":"2025082923200823000_2025.08.26.672412v1.3","doi-asserted-by":"crossref","first-page":"e213603","DOI":"10.1212\/WNL.0000000000213603","article-title":"Survival Differences Between Individuals With Typical and Atypical Phenotypes of Alzheimer Disease","volume":"104","year":"2025","journal-title":"Neurology"},{"key":"2025082923200823000_2025.08.26.672412v1.4","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(09)70299-6"},{"key":"2025082923200823000_2025.08.26.672412v1.5","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(20)32205-4"},{"key":"2025082923200823000_2025.08.26.672412v1.6","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","year":"2018","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2025082923200823000_2025.08.26.672412v1.7","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000002923"},{"key":"2025082923200823000_2025.08.26.672412v1.8","doi-asserted-by":"crossref","first-page":"e209219","DOI":"10.1212\/WNL.0000000000209219","article-title":"Explaining the Variability of Alzheimer Disease Fluid Biomarker Concentrations in Memory Clinic Patients Without Dementia","volume":"102","year":"2024","journal-title":"Neurology"},{"key":"2025082923200823000_2025.08.26.672412v1.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cortex.2005.11.002"},{"key":"2025082923200823000_2025.08.26.672412v1.10","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-023-00779-6"},{"key":"2025082923200823000_2025.08.26.672412v1.11","doi-asserted-by":"publisher","DOI":"10.1007\/S13311-022-01185-Z"},{"key":"2025082923200823000_2025.08.26.672412v1.12","doi-asserted-by":"crossref","first-page":"3162","DOI":"10.1038\/s41598-023-29383-5","article-title":"A multidimensional ODE-based model of Alzheimer\u2019s disease progression","volume":"13","year":"2023","journal-title":"Scientific Reports"},{"key":"2025082923200823000_2025.08.26.672412v1.13","first-page":"1711","article-title":"Deep learning approach for early detection of Alzheimer\u2019s disease","volume":"14","year":"2021","journal-title":"Cognitive Computation"},{"key":"2025082923200823000_2025.08.26.672412v1.14","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1109\/JBHI.2019.2914970","article-title":"Studying the manifold structure of Alzheimer\u2019s disease: a deep learning approach using convolutional autoencoders","volume":"24","year":"2020","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"2025082923200823000_2025.08.26.672412v1.15","doi-asserted-by":"crossref","first-page":"853294","DOI":"10.3389\/fpubh.2022.853294","article-title":"Early-stage Alzheimer\u2019s disease prediction using machine learning models","volume":"10","year":"2022","journal-title":"Frontiers in Public Health"},{"key":"2025082923200823000_2025.08.26.672412v1.16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16431-6_1"},{"key":"2025082923200823000_2025.08.26.672412v1.17","doi-asserted-by":"crossref","first-page":"7065","DOI":"10.1038\/s41467-021-26703-z","article-title":"A deep learning framework identifies dimensional representations of Alzheimer\u2019s disease from brain structure","volume":"12","year":"2021","journal-title":"Nature Communications"},{"key":"2025082923200823000_2025.08.26.672412v1.18","doi-asserted-by":"crossref","first-page":"119892","DOI":"10.1016\/j.neuroimage.2023.119892","article-title":"MC-RVAE: Multi-channel recurrent variational autoencoder for multimodal Alzheimer\u2019s disease progression modelling","volume":"268","year":"2023","journal-title":"NeuroImage"},{"key":"2025082923200823000_2025.08.26.672412v1.19","unstructured":"Rubanova, Y. , Chen, R. T. Q. & Duvenaud, D. Latent ODEs for irregularly-sampled time series. in Proceedings of the 33rd International Conference on Neural Information Processing Systems 5320\u20135330 (Curran Associates Inc., 2019)."},{"key":"2025082923200823000_2025.08.26.672412v1.20","first-page":"6572","volume-title":"in Proceedings of the 32nd International Conference on Neural Information Processing Systems","volume":"1","year":"2018"},{"key":"2025082923200823000_2025.08.26.672412v1.21","doi-asserted-by":"publisher","DOI":"10.2147\/DNND.S228939"},{"key":"2025082923200823000_2025.08.26.672412v1.22","doi-asserted-by":"publisher","DOI":"10.1001\/archneur.1990.00530010061020"},{"key":"2025082923200823000_2025.08.26.672412v1.23","doi-asserted-by":"crossref","unstructured":"Johnson, R. A. & Wichern, D. W. Applied Multivariate Statistical Analysis. (Prentice-Hall, Inc., 1988).","DOI":"10.2307\/2531616"},{"key":"2025082923200823000_2025.08.26.672412v1.24","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e3181e8e8b8"},{"key":"2025082923200823000_2025.08.26.672412v1.25","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1186\/s40035-023-00365-x","article-title":"Head-to-head Comparison of Plasma and PET Imaging ATN Markers in Subjects with Cognitive Complaints","volume":"12","year":"2023","journal-title":"Translational Neurodegeneration"},{"key":"2025082923200823000_2025.08.26.672412v1.26","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-018-0453-0"},{"key":"2025082923200823000_2025.08.26.672412v1.27","doi-asserted-by":"publisher","DOI":"10.1126\/science.1566067"},{"key":"2025082923200823000_2025.08.26.672412v1.28","doi-asserted-by":"publisher","DOI":"10.3390\/ijms22042110"},{"key":"2025082923200823000_2025.08.26.672412v1.29","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-021-01249-0)"},{"key":"2025082923200823000_2025.08.26.672412v1.30","doi-asserted-by":"publisher","DOI":"10.1016\/J.CAMWA.2011.06.002"},{"key":"2025082923200823000_2025.08.26.672412v1.31","unstructured":"Bradbury, J. , Frostig, R. , & others. JAX: Composable Transformations of Python+NumPy Programs. (2018)."},{"key":"2025082923200823000_2025.08.26.672412v1.32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"2025082923200823000_2025.08.26.672412v1.33","unstructured":"Kidger, P. On Neural Differential Equations. (University of Oxford, 2021)."},{"key":"2025082923200823000_2025.08.26.672412v1.34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980"},{"key":"2025082923200823000_2025.08.26.672412v1.35","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"2025082923200823000_2025.08.26.672412v1.36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"2025082923200823000_2025.08.26.672412v1.37","doi-asserted-by":"crossref","first-page":"1475","DOI":"10.3390\/s22041475","article-title":"A long short-term memory biomarker-based prediction framework for Alzheimer\u2019s disease","volume":"22","year":"2022","journal-title":"Sensors"},{"key":"2025082923200823000_2025.08.26.672412v1.38","doi-asserted-by":"crossref","first-page":"950","DOI":"10.3390\/bioengineering10080950","article-title":"An approach to binary classification of Alzheimer\u2019s disease using LSTM","volume":"10","year":"2023","journal-title":"Bioengineering"},{"key":"2025082923200823000_2025.08.26.672412v1.39","doi-asserted-by":"crossref","first-page":"80893","DOI":"10.1109\/ACCESS.2019.2919385","article-title":"Predicting Alzheimer\u2019s disease using LSTM","volume":"7","year":"2019","journal-title":"IEEE Access"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.08.26.672412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T09:25:23Z","timestamp":1768469123000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.08.26.672412"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1101\/2025.08.26.672412","relation":{},"subject":[],"published":{"date-parts":[[2025,8,27]]},"subtype":"preprint"}}