{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T14:55:58Z","timestamp":1781362558862,"version":"3.54.1"},"posted":{"date-parts":[[2023,1,30]]},"group-title":"Bioinformatics","reference-count":31,"publisher":"openRxiv","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2023,1,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Alzheimer\u2019s disease (AD) is a neurodegenerative disease that affects millions of people worldwide. Mild cognitive impairment (MCI) is an intermediary stage between cognitively normal (CN) state and AD. Not all people who have MCI convert to AD. The diagnosis of AD is made after significant symptoms of dementia such as short-term memory loss are already present. Since AD is currently an irreversible disease, diagnosis at the onset of disease brings a huge burden on patients, their caregivers, and the healthcare sector. Thus, there is a crucial need to develop methods for the early prediction AD for patients who have MCI. Recurrent Neural Networks (RNN) have been successfully used to handle Electronic Health Records (EHR) for predicting conversion from MCI to AD. However, RNN ignores irregular time intervals between successive events which occurs common in EHR data. In this study, we propose two deep learning architectures based on RNN, namely Predicting Progression of Alzheimer\u2019s Disease (PPAD) and PPAD-Autoencoder (PPAD-AE). PPAD and PPAD-AE are designed for early predicting conversion from MCI to AD at the next visit and multiple visits ahead for patients, respectively. To minimize the effect of the irregular time intervals between visits, we propose using age in each visit as an indicator of time change between successive visits. Our experimental results conducted on Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI) and National Alzheimer\u2019s Coordinating Center (NACC) datasets showed that our proposed models outperformed all baseline models for most prediction scenarios in terms of F2 and sensitivity. We also observed that the age feature was one of top features and was able to address irregular time interval problem.<\/jats:p>","DOI":"10.1101\/2023.01.28.526045","type":"posted-content","created":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T21:55:21Z","timestamp":1675115721000},"source":"Crossref","is-referenced-by-count":5,"title":["PPAD: A deep learning architecture to predict progression of Alzheimer\u2019s disease"],"prefix":"10.64898","author":[{"given":"Mohammad","family":"Al Olaimat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jared","family":"Martinez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fahad","family":"Saeed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4813-4310","authenticated-orcid":false,"given":"Serdar","family":"Bozdag","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"Alzheimer's Disease Neuroimaging Initiative","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"issue":"3","key":"2023020309050776000_2023.01.28.526045v2.1","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/j.jalz.2010.03.006","article-title":"Clinical Core of the Alzheimer\u2019s Disease Neuroimaging Initiative: progress and plans","volume":"6","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2010","journal-title":"Alzheimer\u2019s & Dementia"},{"issue":"3","key":"2023020309050776000_2023.01.28.526045v2.2","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/j.jalz.2015.02.003","article-title":"2015 Alzheimer\u2019s disease facts and figures","volume":"11","author":"Alzheimer\u2019s Association","year":"2015","journal-title":"Alzhei-mer\u2019s & Dementia"},{"key":"2023020309050776000_2023.01.28.526045v2.3","doi-asserted-by":"crossref","unstructured":"Baytas, I. M. , Xiao, C. , Zhang, X. , Wang, F. , Jain, A. K. , & Zhou, J. (2017, August). Patient subtyping via time-aware LSTM networks. In Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data min-ing (pp. 65\u201374).","DOI":"10.1145\/3097983.3097997"},{"key":"2023020309050776000_2023.01.28.526045v2.4","doi-asserted-by":"crossref","unstructured":"Besser, L. , Kukull, W. , Knopman, D. S. , Chui, H. , Galasko, D. , Weintraub, S. , \u2026 & Morris, J. C. (2018). Version 3 of the National Alzheimer\u2019s Coordinating Cen-ter\u2019s uniform data set. Alzheimer disease and associated disorders.","DOI":"10.1097\/WAD.0000000000000279"},{"key":"2023020309050776000_2023.01.28.526045v2.5","doi-asserted-by":"publisher","DOI":"10.1046\/j.1365-2990.2003.00457.x"},{"key":"2023020309050776000_2023.01.28.526045v2.6","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2015.2404809.00036"},{"key":"2023020309050776000_2023.01.28.526045v2.7","unstructured":"Goodfellow, I. , Bengio, Y. , & Courville, A. (2016). Deep learning. MIT press."},{"issue":"10","key":"2023020309050776000_2023.01.28.526045v2.8","first-page":"2222","article-title":"LSTM: A search space odyssey","volume":"28","year":"2016","journal-title":"IEEE transactions on neural networks and learning systems"},{"key":"2023020309050776000_2023.01.28.526045v2.9","doi-asserted-by":"publisher","DOI":"10.3109\/00048679809113126"},{"issue":"7","key":"2023020309050776000_2023.01.28.526045v2.10","first-page":"679","article-title":"Risk factors for Alzheimer\u2019s disease","volume":"62","year":"2010","journal-title":"Brain and nerve= Shinkei kenkyu no shinpo"},{"issue":"3","key":"2023020309050776000_2023.01.28.526045v2.11","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.jalz.2010.03.004","article-title":"Update on the magnetic resonance imaging core of the Alzheimer\u2019s disease neuroimaging initi-ative","volume":"6","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2010","journal-title":"Alzheimer\u2019s & Dementia"},{"issue":"3","key":"2023020309050776000_2023.01.28.526045v2.12","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.jalz.2010.03.003","article-title":"The Alzheimer\u2019s Disease Neuroimaging Initiative positron emission tomography core","volume":"6","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2010","journal-title":"Alzheimer\u2019s & De-mentia"},{"issue":"1","key":"2023020309050776000_2023.01.28.526045v2.13","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.jalz.2012.09.017","article-title":"AD dementia risk in late MCI, in early MCI, and in subjective memory impairment","volume":"10","year":"2014","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2023020309050776000_2023.01.28.526045v2.14","doi-asserted-by":"crossref","first-page":"134824","DOI":"10.1016\/j.neulet.2020.134824","article-title":"Sex difference in the association of APOE4 with cerebral glucose metabolism in older adults reporting significant memory concern","volume":"722","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2020","journal-title":"Neuroscience Letters"},{"key":"2023020309050776000_2023.01.28.526045v2.15","doi-asserted-by":"crossref","unstructured":"Kim, D. , Kim, S. , Risacher, S. L. , Shen, L. , Ritchie, M. D. , Weiner, M. W. , \u2026 & Nho, K. (2013, September). A graph-based integration of multimodal brain im-aging data for the detection of early mild cognitive impairment (E-MCI). In In-ternational Workshop on Multimodal Brain Image Analysis (pp. 159\u2013169). Springer, Cham.","DOI":"10.1007\/978-3-319-02126-3_16"},{"issue":"1","key":"2023020309050776000_2023.01.28.526045v2.16","first-page":"1","article-title":"Predicting Alzheimer\u2019s disease progression using multi-modal deep learning approach","volume":"9","year":"2019","journal-title":"Scientific re-ports"},{"key":"2023020309050776000_2023.01.28.526045v2.17","doi-asserted-by":"crossref","unstructured":"Li, H. , & Fan, Y. (2019, April). Early prediction of Alzheimer\u2019s disease dementia based on baseline hippocampal MRI and 1-year follow-up cognitive measures using deep recurrent neural networks. In 2019 IEEE 16th International Sympo-sium on Biomedical Imaging (ISBI 2019) (pp. 368\u2013371). IEEE.","DOI":"10.1109\/ISBI.2019.8759397"},{"issue":"4","key":"2023020309050776000_2023.01.28.526045v2.18","doi-asserted-by":"crossref","first-page":"5923","DOI":"10.1364\/OE.416672","article-title":"Bi-directional gated recurrent unit neural network based nonlinear equalizer for coherent optical communication system","volume":"29","year":"2021","journal-title":"Optics Express"},{"key":"2023020309050776000_2023.01.28.526045v2.19","unstructured":"Luong, D. T. A. , & Chandola, V. (2018). An Empirical Evaluation of Time-Aware LSTM Autoencoder on Chronic Kidney Disease. CoRR."},{"key":"2023020309050776000_2023.01.28.526045v2.20","article-title":"Predicting feature imputability in the absence of ground truth","year":"2020","journal-title":"arXiv preprint"},{"key":"2023020309050776000_2023.01.28.526045v2.21","doi-asserted-by":"crossref","first-page":"117203","DOI":"10.1016\/j.neuroimage.2020.117203","article-title":"Predicting Alzheimer\u2019s disease pro-gression using deep recurrent neural networks","volume":"222","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2020","journal-title":"NeuroImage"},{"key":"2023020309050776000_2023.01.28.526045v2.22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurobiolaging.2010.04.029"},{"issue":"3","key":"2023020309050776000_2023.01.28.526045v2.23","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/j.jalz.2010.03.013","article-title":"Alzheimer\u2019s Disease Neu-roimaging Initiative biomarkers as quantitative phenotypes: Genetics core aims, progress, and plans","volume":"6","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2010","journal-title":"Alzheimer\u2019s & dementia"},{"issue":"2","key":"2023020309050776000_2023.01.28.526045v2.24","doi-asserted-by":"crossref","first-page":"11","DOI":"10.3390\/geriatrics1020011","article-title":"Prognosis of early-onset vs. late-onset mild cognitive impairment: comparison of conversion rates and its predictors","volume":"1","year":"2016","journal-title":"Geriatrics"},{"issue":"3","key":"2023020309050776000_2023.01.28.526045v2.25","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.jalz.2010.03.008","article-title":"Up-date on the biomarker core of the Alzheimer\u2019s Disease Neuroimaging Initiative subjects","volume":"6","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2010","journal-title":"Alzheimer\u2019s & dementia"},{"issue":"1","key":"2023020309050776000_2023.01.28.526045v2.26","first-page":"1","article-title":"Multimodal deep learning models for early detection of Alzheimer\u2019s disease stage","volume":"11","year":"2021","journal-title":"Scientific reports"},{"issue":"3","key":"2023020309050776000_2023.01.28.526045v2.27","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.jalz.2010.03.007","article-title":"The Alzheimer\u2019s disease neuroimaging initiative: progress report and future plans","volume":"6","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2010","journal-title":"Alzheimer\u2019s & Dementia"},{"issue":"5","key":"2023020309050776000_2023.01.28.526045v2.28","first-page":"e111","article-title":"The Alzheimer\u2019s Disease Neuroimaging Ini-tiative: a review of papers published since its inception","volume":"9","year":"2013","journal-title":"Alzheimer\u2019s & Demen-tia"},{"key":"2023020309050776000_2023.01.28.526045v2.29","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2796.2004.01380.x"},{"issue":"8 Suppl","key":"2023020309050776000_2023.01.28.526045v2.30","first-page":"S177","article-title":"Economic burden of Alzheimer disease and managed care con-siderations","volume":"26","year":"2020","journal-title":"The American journal of managed care"},{"key":"2023020309050776000_2023.01.28.526045v2.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.09.069"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2023.01.28.526045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T04:11:38Z","timestamp":1768450298000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2023.01.28.526045"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,30]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1101\/2023.01.28.526045","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1093\/bioinformatics\/btad249","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2023,1,30]]},"subtype":"preprint"}}