{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:16:22Z","timestamp":1791393382964,"version":"4.3.3"},"reference-count":46,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Aging"],"abstract":"\n Background<\/jats:title>\n With the aging global population and the rising burden of Alzheimer disease and related dementias (ADRDs), there is a growing focus on identifying mild cognitive impairment (MCI) to enable timely interventions that could potentially slow down the onset of clinical dementia. The production of speech by an individual is a cognitively complex task that engages various cognitive domains. The ease of audio data collection highlights the potential cost-effectiveness and noninvasive nature of using human speech as a tool for cognitive assessment.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to construct a machine learning pipeline that incorporates speaker diarization, feature extraction, feature selection, and classification to identify a set of acoustic features derived from voice recordings that exhibit strong MCI detection capability.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n The study included 100 MCI cases and 100 cognitively normal controls matched for age, sex, and education from the Framingham Heart Study. Participants' spoken responses on neuropsychological tests were recorded, and the recorded audio was processed to identify segments of each participant's voice from recordings that included voices of both testers and participants. A comprehensive set of 6385 acoustic features was then extracted from these voice segments using OpenSMILE and Praat software. Subsequently, a random forest model was constructed to classify cognitive status using the features that exhibited significant differences between the MCI and cognitively normal groups. The MCI detection performance of various audio lengths was further examined.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n An optimal subset of 29 features was identified that resulted in an area under the receiver operating characteristic curve of 0.87, with a 95% CI of 0.81-0.94. The most important acoustic feature for MCI classification was the number of filled pauses (importance score=0.09, P=3.10E\u201308). There was no substantial difference in the performance of the model trained on the acoustic features derived from different lengths of voice recordings.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study showcases the potential of monitoring changes to nonsemantic and acoustic features of speech as a way of early ADRD detection and motivates future opportunities for using human speech as a measure of brain health.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/55126","type":"journal-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T23:01:46Z","timestamp":1721084506000},"page":"e55126","source":"Crossref","is-referenced-by-count":21,"title":["Detection of Mild Cognitive Impairment From Non-Semantic, Acoustic Voice Features: The Framingham Heart Study"],"prefix":"10.2196","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6495-3087","authenticated-orcid":false,"given":"Huitong","family":"Ding","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0908-9729","authenticated-orcid":false,"given":"Adrian","family":"Lister","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9199-8723","authenticated-orcid":false,"given":"Cody","family":"Karjadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7742-4491","authenticated-orcid":false,"given":"Rhoda","family":"Au","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3043-3942","authenticated-orcid":false,"given":"Honghuang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7512-0929","authenticated-orcid":false,"given":"Brian","family":"Bischoff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6780-6808","authenticated-orcid":false,"given":"Phillip H","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/alz.12328"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/alz.12694"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1212\/wnl.64.12_suppl_3.s34"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2011.03.003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1101\/cshperspect.a006148"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1046\/j.1532-5415.5153.x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2014.06.004"},{"issue":"2","key":"ref8","first-page":"45","volume":"21","author":"Robinson, P","year":"2003","journal-title":"Stud Second Lang Acquis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/S1355617707070609"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e3181c7198e"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2196\/42886"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3389\/frdem.2023.1214940"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2174\/1567205017666200213094513"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/slt48900.2021.9383491"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-021-00888-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/02699206.2020.1827043"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1212\/wnl.34.7.939"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMc1604823"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tasl.2011.2125954"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-560"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9052974"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref23","unstructured":"BoersmaPPraat: doing phonetics by computer20112024-07-19http:\/\/www.praat.org\/"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2013-56"},{"key":"ref25","unstructured":"DumpalaSHRodriguezSRempelSSajjadianMUherROoreSDetecting depression with a temporal context of speaker embeddings2022Proc AAAI SASJanuary 10, 2022Canada"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2021.780169"},{"key":"ref27","unstructured":"BeccariaFGagliardiGKokkinakisDExtraction and classification of acoustic features from Italian speaking children with autism spectrum disorders2022Proceedings of the LREC 2022 Workshop on Resources and Processing of Linguistic, Para-linguistic and Extra-linguistic Data from People with Various Forms of Cognitive\/Psychiatric\/Developmental Impairments (RaPID-4 2022)June 25, 2022ItalyELRA2230"},{"key":"ref28","author":"Beyan, C","year":"2021","journal-title":"arXiv:210502636"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2668024.2668028"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00292"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/0969594x.2021.1951162"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_695"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1001\/jamaneurol.2021.3404"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/trc2.12330"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.dadm.2014.11.012"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuropsychologia.2018.12.018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcomdis.2004.03.002"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1177\/1533317508328138"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2174\/1567205014666171120144343"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2018.00975"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.2174\/1567205014666171121114930"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/s130506730"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.bandc.2004.05.003"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e31826e26b7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2011.03.004"},{"key":"ref46","unstructured":"Framingham Heart Study For Researchers20242024-04-22https:\/\/www.framinghamheartstudy.org\/fhs-for-researchers\/"}],"container-title":["JMIR Aging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aging.jmir.org\/2024\/1\/e55126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:42:34Z","timestamp":1782841354000},"score":1,"resource":{"primary":{"URL":"https:\/\/aging.jmir.org\/2024\/1\/e55126"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,22]]},"references-count":46,"URL":"https:\/\/doi.org\/10.2196\/55126","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.55126","asserted-by":"object"}]},"ISSN":["2561-7605"],"issn-type":[{"value":"2561-7605","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,22]]}}}