{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:00:50Z","timestamp":1771610450321,"version":"3.50.1"},"reference-count":13,"publisher":"S. Karger AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Digit Biomark"],"abstract":"<jats:p>Introduction: Huntington\u2019s disease (HD) is a progressive neurodegenerative disorder characterized by motor, cognitive, and psychiatric decline. The Unified Huntington\u2019s Disease Rating Scale Total Motor Score (UHDRS-TMS) is standard for staging manifest disease, but is relatively insensitive to subtle premanifest changes. Speech abnormalities are emerging as candidate digital biomarkers; however, reliably separating premanifest HD (preHD) from healthy controls remains challenging. Here, we assess the feasibility of a speech-only approach by training and comparing multiple classifiers across diverse feature sets and structured tasks to determine whether speech alone can discriminate preHD from controls. Methods: Speech samples were collected from 94 individuals with HD (38 premanifest, 56 manifest) and 36 controls using a standardized six-task protocol administered via tablet. From these recordings, 188 lexical and prosodic features were automatically extracted. We trained 4 machine learning classifiers: random forest, support vector machine, XGBoost, and deep neural networks (DNNs), within 10-fold cross-validation using three feature configurations: (1) all tasks (188 features), (2) the top 30 ANOVA-ranked features, and (3) 22 features from the Caterpillar passage alone. Results: Traditional classifiers showed limited accuracy. A DNN using only the Caterpillar task achieved 81% unweighted accuracy for classifying preHD versus controls. Accuracy increased to 83% for prodromal HD and 87% when all HD participants were compared to controls. Adding features from additional tasks did not improve performance. Conclusion: A brief, structured speech task combined with deep learning enabled accurate classification of preHD. These findings support speech analysis as a scalable, objective tool for early disease detection and monitoring.<\/jats:p>","DOI":"10.1159\/000549327","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T17:01:16Z","timestamp":1768842076000},"page":"53-62","source":"Crossref","is-referenced-by-count":0,"title":["Toward a Speech-Based Model of Premanifest Huntington\u2019s Disease Progression Using Deep Neural Networks"],"prefix":"10.1159","volume":"10","author":[{"given":"Luis A.","family":"Sierra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Japleen","family":"Kaur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Namhee","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vinod","family":"Subramanian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raymond","family":"Brueckner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nate","family":"Blaylock","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henry","family":"O&apos;Connell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1866-162X","authenticated-orcid":false,"given":"Samuel A.","family":"Frank","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jody","family":"Corey-Bloom","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Laganiere","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"127","published-online":{"date-parts":[[2026,1,19]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2019.08.009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000002550"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/ene.15726"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1212\/wnl.0000000000008541"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/02687039608248419"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s00702-014-1229-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3233\/jhd-240044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2025.1494816"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2023.1191718"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1044\/1092-4388(2011\/11-0158)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5195\/jmla.2018.262"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/ajmg.b.31232"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1538\/1\/012024"}],"container-title":["Digital Biomarkers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/karger.com\/article-pdf\/doi\/10.1159\/000549327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T17:00:58Z","timestamp":1771606858000},"score":1,"resource":{"primary":{"URL":"https:\/\/karger.com\/article\/doi\/10.1159\/000549327"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":13,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,1]]}},"URL":"https:\/\/doi.org\/10.1159\/000549327","archive":["Portico"],"relation":{"is-supplemented-by":[{"id-type":"doi","id":"10.6084\/m9.figshare.31079230","asserted-by":"subject"}]},"ISSN":["2504-110X"],"issn-type":[{"value":"2504-110X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,19]]}}}