{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T18:26:16Z","timestamp":1790792776427,"version":"4.1.0"},"reference-count":43,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"content-version":"vor","delay-in-days":7,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000065","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["1RF1NS115141\u201001A1"],"award-info":[{"award-number":["1RF1NS115141\u201001A1"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ascpt.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Clinical Translational Sci"],"published-print":{"date-parts":[[2024,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Cognitive decline in Parkinson's disease (PD) varies widely. While models to predict cognitive progression exist, comparing traditional probabilistic models to deep learning methods remains understudied. This study compares sequential modeling techniques to identify cognitive progression in individuals with and without PD. Using data from the Parkinson's Progression Marker Initiative, shallow Markov, deep recurrent (long short\u2010term memory [LSTM]), and nonrecurrent (temporal fusion transformer [TFT]) models were compared to predict cognitive status over time. Cognitive status was categorized into normal cognition (NC), mild cognitive impairment (MCI), and dementia. Predictions were made annually for up to 3\u2009years using clinical data, including demographics, cognitive assessments, PD severity, and medical history. Each approach was evaluated using inverse probability weighted (IPW\u2010) F1 scores. An ensemble method combined outputs from the Markov, LSTM, and TFT models. The dataset included 917 individuals (53% PD; 30% at risk for PD; 17% Healthy Controls). The TFT model outperformed others across all annual periods (IPW\u2010F1\u2009=\u20090.468) compared to the Markov (IPW\u2010F1\u2009=\u20090.349) and LSTM (IPW\u2010F1\u2009=\u20090.414) models, with improved performance using an ensemble approach (IPW\u2010F1\u2009=\u20090.502). For MCI and dementia predictions, which were rarer occurrences compared to NC status (ratios: 50:8:1), the TFT model consistently outperformed competing models, achieving IPW\u2010F1 scores of 0.496 and 0.533 for MCI and dementia, respectively. In conclusion, sequential deep learning models like TFT, which mitigate long\u2010term memory loss and can interpret complex, high\u2010dimensional data, perform best overall in predicting clinically important cognitive transitions. These methods should be further explored for predicting degenerative conditions.<\/jats:p>","DOI":"10.1111\/cts.70066","type":"journal-article","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T13:40:04Z","timestamp":1731073204000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Comparing machine learning and deep learning models to predict cognition progression in Parkinson's disease"],"prefix":"10.1111","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5732-065X","authenticated-orcid":false,"given":"Edgar A.","family":"Bernal","sequence":"first","affiliation":[{"name":"FLX AI  Rochester New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3438-4252","authenticated-orcid":false,"given":"Shu","family":"Yang","sequence":"additional","affiliation":[{"name":"Center for Health + Technology University of Rochester  Rochester New York USA"},{"name":"Hajim School of Engineering &amp; Applied Sciences University of Rochester  Rochester New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3629-9337","authenticated-orcid":false,"given":"Konnor","family":"Herbst","sequence":"additional","affiliation":[{"name":"Center for Health + Technology University of Rochester  Rochester New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2394-9513","authenticated-orcid":false,"given":"Charles S.","family":"Venuto","sequence":"additional","affiliation":[{"name":"Center for Health + Technology University of Rochester  Rochester New York USA"},{"name":"Department of Neurology University of Rochester  Rochester New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,11,8]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(12)70152-7"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41572-021-00280-3"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parkreldis.2016.04.009"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1177\/0891988712464823"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.24893"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.21507"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.21844"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parkreldis.2019.04.020"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000000066"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.27902"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.29918"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0303644"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(16)30328-3"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/acn3.51022"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0175674"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41531-022-00409-5"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/brainsci12081048"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-37644-6"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.27528"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41531-020-00121-2"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-023-02866-6"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-019-04538-7"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-023-02643-7"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0286506"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13101691"},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","unstructured":"IsmailNH KamarudinNS NasirAFA.The neuropsychology assessment for identifying dementia in parkinson's disease patients using a deep neural network. International Conference on Software Engineering & Computer Systems and 4th International Conference on Computational Science and Information Management (ICSECS\u2010ICOCSIM) Pekan Malaysia. 238\u20132432021.","DOI":"10.1109\/ICSECS52883.2021.00050"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84800-007-0_10"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_2_10_30_1","unstructured":"VaswaniA ShazeerN ParmarN et\u00a0al.Attention is all you need.2017. In Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc. Red Hook NY USA: 6000\u20136010."},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2726187"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.actpsy.2015.10.009"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2022.982289"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1136\/jnnp.2005.081711"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(18)30127-3"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-24271-9"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1177\/0962280210395740"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1972.223477"},{"key":"e_1_2_10_40_1","doi-asserted-by":"crossref","unstructured":"LeP ZuidemaW.Quantifying the vanishing gradient and long distance dependency problem in recursive neural networks and recursive LSTMs. Proceedings of the 1st Workshop on Representation Learning for NLP 2016; Berlin Germany. Association for Computational Linguistics: 87\u201393.","DOI":"10.18653\/v1\/W16-1610"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2021.03.012"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-024-05025-w"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooae087"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000209699"}],"container-title":["Clinical and Translational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cts.70066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T07:18:15Z","timestamp":1732605495000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/10.1111\/cts.70066"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":43,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["10.1111\/cts.70066"],"URL":"https:\/\/doi.org\/10.1111\/cts.70066","archive":["Portico"],"relation":{},"ISSN":["1752-8054","1752-8062"],"issn-type":[{"value":"1752-8054","type":"print"},{"value":"1752-8062","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]},"assertion":[{"value":"2024-07-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70066"}}