{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T15:47:33Z","timestamp":1792856853658,"version":"4.5.0"},"reference-count":70,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T00:00:00Z","timestamp":1723075200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Speech analysis has been expected to help as a screening tool for early detection of Alzheimer\u2019s disease (AD) and mild-cognitively impairment (MCI). Acoustic features and linguistic features are usually used in speech analysis. However, no studies have yet determined which type of features provides better screening effectiveness, especially in the large aging population of China.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objective<\/jats:title><jats:p>Firstly, to compare the screening effectiveness of acoustic features, linguistic features, and their combination using the same dataset. Secondly, to develop Chinese automated diagnosis model using self-collected natural discourse data obtained from native Chinese speakers.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A total of 92 participants from communities in Shanghai, completed MoCA-B and a picture description task based on the Cookie Theft under the guidance of trained operators, and were divided into three groups including AD, MCI, and heathy control (HC) based on their MoCA-B score. Acoustic features (Pitches, Jitter, Shimmer, MFCCs, Formants) and linguistic features (part-of-speech, type-token ratio, information words, information units) are extracted. The machine algorithms used in this study included logistic regression, random forest (RF), support vector machines (SVM), Gaussian Naive Bayesian (GNB), and k-Nearest neighbor (kNN). The validation accuracies of the same ML model using acoustic features, linguistic features, and their combination were compared.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The accuracy with linguistic features is generally higher than acoustic features in training. The highest accuracy to differentiate HC and AD is 80.77% achieved by SVM, based on all the features extracted from the speech data, while the highest accuracy to differentiate HC and AD or MCI is 80.43% achieved by RF, based only on linguistic features.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Our results suggest the utility and validity of linguistic features in the automated diagnosis of cognitive impairment, and validated the applicability of automated diagnosis for Chinese language data.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fpubh.2024.1417966","type":"journal-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T04:49:05Z","timestamp":1723092545000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":36,"title":["Automatic speech analysis for detecting cognitive decline of older adults"],"prefix":"10.3389","volume":"12","author":[{"given":"Lihe","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiran","family":"Che","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjing","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,8,8]]},"reference":[{"key":"ref1","volume-title":"World Alzheimer report 2023: reducing dementia risk: never too early, never too late","author":"Long","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1547","DOI":"10.3233\/JAD-200888","article-title":"Artificial intelligence, speech and language processing approaches to monitoring Alzheimer\u2019s disease: a systematic review","volume":"78","author":"Garcia","year":"2020","journal-title":"J Alzheimers Dis"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"101514","DOI":"10.1016\/j.csl.2023.101514","article-title":"A mobile application using automatic speech analysis for classifying Alzheimer\u2019s disease and mild cognitive impairment","volume":"81","author":"Yamada","year":"2023","journal-title":"Comput Speech Lang"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"102624","DOI":"10.1016\/j.artmed.2023.102624","article-title":"ADscreen: a speech processing-based screening system for automatic identification of patients with Alzheimer\u2019s disease and related dementia","volume":"143","author":"Zolnoori","year":"2023","journal-title":"Artif Intell Med"},{"key":"ref5","first-page":"2167","volume-title":"To BERT or not to BERT: comparing speech and language-based approaches for Alzheimer's disease detection","author":"Balagopalan","year":"2020"},{"key":"ref6","first-page":"3651","article-title":"What does BERT learn about the structure of language?","author":"Jawahar","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2015\/916356","article-title":"Automatic prosodic analysis to identify mild dementia","volume":"2015","author":"Gonzalez-Moreira","year":"2015","journal-title":"Biomed Res Int"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1186\/s12911-021-01456-3","article-title":"Transformer-based deep neural network language models for Alzheimer\u2019s disease risk assessment from targeted speech","volume":"21","author":"Roshanzamir","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref9","first-page":"580","article-title":"Prosodic speech analysis to identify mild cognitive impairment","volume-title":"VI Latin American Congress on Biomedical Engineering CLAIB 2014, Paran\u00e1, Argentina 29, 30 and 31 October 2014","author":"Gonzalez-Moreira","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.dadm.2014.11.012","article-title":"Automatic speech analysis for the assessment of patients with predementia and Alzheimer\u2019s disease","volume":"1","author":"K\u00f6nig","year":"2015","journal-title":"Alzheimer\u2019s & Dementia: Diagnosis, Assessment & Disease Monitoring"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"29","DOI":"10.3109\/17549500903137256","article-title":"Temporal parameters of spontaneous speech in Alzheimer\u2019s disease","volume":"12","author":"Hoffmann","year":"2010","journal-title":"Int J Speech Lang Pathol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.csl.2018.07.007","article-title":"Identifying mild cognitive impairment and mild Alzheimer\u2019s disease based on spontaneous speech using ASR and linguistic features","volume":"53","author":"Gosztolya","year":"2019","journal-title":"Comput Speech Lang"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1016\/j.nrl.2012.07.012","article-title":"Oral reading fluency analysis in patients with Alzheimer disease and asymptomatic control subjects","volume":"28","author":"Mart\u00ednez-S\u00e1nchez","year":"2013","journal-title":"Neurologia"},{"key":"ref14","first-page":"891","volume-title":"Evaluating the vulnerability of end-to-end automatic speech recognition models to membership inference attacksin Interspeech","author":"Shah","year":"2021"},{"key":"ref15","first-page":"2157","article-title":"Tackling the ADReSS challenge: a multimodal approach to the automated recognition of Alzheimer\u2019s dementia","volume-title":"Interspeech","author":"Martinc","year":"2020"},{"key":"ref16","first-page":"670","article-title":"An exploration of log-mel spectrogram and MFCC features for Alzheimer\u2019s dementia recognition from spontaneous speech","author":"Meghanani","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1829","DOI":"10.18517\/ijaseit.8.5.6503","article-title":"Classification of Alzheimer\u2019s disease in PET scans using MFCC and SVM","volume":"8","author":"Panyavaraporn","year":"2018","journal-title":"Int J Adv Sci Eng Inf Technol"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1177\/1533317515603957","article-title":"Computer-aided diagnosis system for Alzheimer\u2019s disease using different discrete transform techniques","volume":"31","author":"Dessouky","year":"2016","journal-title":"Am J Alzheimers Dis Other Dement"},{"key":"ref19","first-page":"1162","article-title":"Detecting depression in Alzheimer\u2019s disease and MCI by speech analysis","volume":"99","author":"Abdallah-Qasaimeh","year":"2021","journal-title":"J Theor Appl Inf Technol"},{"key":"ref20","first-page":"91","article-title":"Dementia classification using acoustic descriptors derived from subsampled signals","author":"Triapthi","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"635945","DOI":"10.3389\/fnagi.2021.635945","article-title":"Comparing pre-trained and feature-based models for prediction of Alzheimer\u2019s disease based on speech","volume":"13","author":"Balagopalan","year":"2021","journal-title":"Front Aging Neurosci"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/s12559-013-9229-9","article-title":"On automatic diagnosis of Alzheimer\u2019s disease based on spontaneous speech analysis and emotional temperature","volume":"7","author":"Lopez-de-Ipi\u00f1a","year":"2015","journal-title":"Cogn Comput"},{"key":"ref23","first-page":"347","article-title":"A study for detecting mild cognitive impairment by analyzing conversations with humanoid robots","author":"Yoshii","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1159\/000356726","article-title":"Speech in Alzheimer\u2019s disease: can temporal and acoustic parameters discriminate dementia?","volume":"37","author":"Meil\u00e1n","year":"2014","journal-title":"Dement Geriatr Cogn Disord"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"78","DOI":"10.3115\/v1\/W14-3210","article-title":"Learning predictive linguistic features for Alzheimer\u2019s disease and related dementias using verbal utterances","volume-title":"Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality","author":"Orimaye","year":"2014"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1016\/j.procs.2020.09.071","article-title":"Language-related features for early detection of Alzheimer disease","volume":"176","author":"Ammar","year":"2020","journal-title":"Procedia Comput Sci"},{"key":"ref27","first-page":"2538","article-title":"Speech-based automatic and robust detection of very early dementia","author":"Satt","year":"2014"},{"key":"ref28","first-page":"2187","article-title":"Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer\u2019s dementia recognition from spontaneous speech","author":"Rohanian","year":"2020"},{"key":"ref29","first-page":"835","article-title":"Recent developments in opensmile, the Munich open-source multimedia feature extractor","author":"Eyben","year":"2013"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","article-title":"The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing","volume":"7","author":"Eyben","year":"2015","journal-title":"IEEE Trans Affect Comput"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"780169","DOI":"10.3389\/fcomp.2021.780169","article-title":"Alzheimer\u2019s dementia recognition through spontaneous speech: the ADReSS challenge","volume":"3","author":"Luz","year":"2020","journal-title":"Front Comput Sci"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1109\/TASLP.2014.2359159","article-title":"A feature study for classification-based speech separation at low signal-to-noise ratios","volume":"22","author":"Chen","year":"2014","journal-title":"IEEE\/ACM Trans Audio Speech Lang Proc"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.1044\/2023_AJSLP-22-00403","article-title":"Automated classification of cognitive decline and probable Alzheimer\u2019s dementia across multiple speech and language domains","volume":"32","author":"He","year":"2023","journal-title":"Am J Speech Lang Pathol"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"195","DOI":"10.3389\/fnagi.2015.00195","article-title":"Speaking in Alzheimer\u2019s disease, is that an early sign? Importance of changes in language abilities in Alzheimer\u2019s disease","volume":"7","author":"Szatloczki","year":"2015","journal-title":"Front Aging Neurosci"},{"key":"ref35","first-page":"1","article-title":"ANN-based Alzheimer\u2019s disease classification from bag of words","author":"Klumpp","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/j.trci.2017.01.006","article-title":"Predicting mild cognitive impairment from spontaneous spoken utterances","volume":"3","author":"Asgari","year":"2017","journal-title":"Alzheimer\u2019s Dementia Transl Res Clin Interv"},{"key":"ref37","first-page":"27","article-title":"Aided diagnosis of dementia type through computer-based analysis of spontaneous speech","author":"Jarrold","year":"2014"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"407","DOI":"10.3233\/JAD-150520","article-title":"Linguistic features identify Alzheimer\u2019s disease in narrative speech","volume":"49","author":"Fraser","year":"2016","journal-title":"J Alzheimers Dis"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"806","DOI":"10.5220\/0011779000003393","article-title":"Measures of lexical diversity and detection of Alzheimer\u2019s using speech","volume":"3","author":"Kothari","year":"2023","journal-title":"ICAART"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1080\/026870300401603","article-title":"Analysis of spontaneous, conversational speech in dementia of Alzheimer type: evaluation of an objective technique for analysing lexical performance","volume":"14","author":"Bucks","year":"2000","journal-title":"Aphasiology"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1080\/01690960500258528","article-title":"Speeded naming, frequency and the development of the lexicon in Williams syndrome","volume":"21","author":"Thomas","year":"2006","journal-title":"Lang Cognit Proc"},{"key":"ref42","first-page":"98","article-title":"A comparison of syntax, semantics, and pragmatics in spoken language among residents with Alzheimer\u2019s disease in managed-care facilities","volume-title":"IEEE Symposium on Computational Intelligence in Healthcare and e-health (CICARE)","author":"Guinn","year":"2014"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"322","DOI":"10.18653\/v1\/K17-1033","article-title":"Idea density for predicting Alzheimer\u2019s disease from transcribed speech","volume-title":"Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)","author":"Sirts","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"2705","DOI":"10.21437\/Interspeech.2017-1712","article-title":"Speech processing approach for diagnosing dementia in an early stage","volume":"2017","author":"Sadeghian","year":"2017","journal-title":"Proc Interspeech"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.3233\/JAD-190452","article-title":"Detecting Alzheimer\u2019s disease from continuous speech using language models","volume":"70","author":"Guo","year":"2019","journal-title":"J Alzheimers Dis"},{"key":"ref46","first-page":"3289","article-title":"An assessment system for Alzheimer's disease based on speech using a novel feature sequence design and recurrent neural network","author":"Chien","year":"2018"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.cortex.2012.12.006","article-title":"Automated classification of primary progressive aphasia subtypes from narrative speech transcripts","volume":"55","author":"Fraser","year":"2014","journal-title":"Cortex"},{"key":"ref48","volume-title":"Exploring neural models for predicting dementia from language","author":"Kong","year":"2019"},{"key":"ref49","volume-title":"BDAE: the Boston diagnostic aphasia examination","author":"Goodglass","year":"2001"},{"key":"ref50","volume-title":"Feishu (version 7.6)","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.wocn.2018.07.001","article-title":"Introducing Parselmouth: a Python interface to Praat","volume":"71","author":"Jadoul","year":"2018","journal-title":"J Phon"},{"key":"ref52","first-page":"181","article-title":"Detecting mild cognitive impairment by exploiting linguistic information from transcripts","author":"Vincze","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","first-page":"3727","DOI":"10.1093\/brain\/awt269","article-title":"Connected speech as a marker of disease progression in autopsy-proven Alzheimer\u2019s disease","volume":"136","author":"Ahmed","year":"2013","journal-title":"Brain"},{"key":"ref54","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1590\/S1980-57642014DN83000010","article-title":"Analysis of word number and content in discourse of patients with mild to moderate Alzheimer's disease","volume":"8","author":"Lira","year":"2014","journal-title":"Dementia Neuropsychol"},{"key":"ref55","first-page":"55","article-title":"The Stanford CoreNLP natural language processing toolkit","author":"Manning","year":"2014"},{"key":"ref56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/brln.1996.0033","article-title":"Comparative study of oral and written picture description in patients with Alzheimer's disease","volume":"53","author":"Croisile","year":"1996","journal-title":"Brain Lang"},{"key":"ref57","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/j.neuroimage.2014.09.060","article-title":"Data-driven HRF estimation for encoding and decoding models","volume":"104","author":"Pedregosa","year":"2015","journal-title":"NeuroImage"},{"key":"ref58","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/0093-934X(85)90124-5","article-title":"Language disintegration in dementia: effects of etiology and severity","volume":"25","author":"Hier","year":"1985","journal-title":"Brain Lang"},{"key":"ref59","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.laheal.2023.06.004","article-title":"Pragmatic impairment and multimodal compensation in older adults with dementia","volume":"176","author":"Lihe","year":"2023","journal-title":"Language and Health 1.1"},{"key":"ref60","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1080\/01690961003589484","article-title":"Lexical knowledge and lexical retrieval in ageing: insights from a tip-of-the-tongue (TOT) study","volume":"25","author":"Juncos-Rabad\u00e1n","year":"2010","journal-title":"Lang Cognit Proc"},{"key":"ref61","doi-asserted-by":"publisher","first-page":"25584","DOI":"10.1007\/s12144-022-03669-9","article-title":"Comparison of language and narrative features of individuals among amnestic mild cognitive impairment and healthy adults","volume":"42","author":"Karal\u0131","year":"2023","journal-title":"Curr Psychol"},{"key":"ref62","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1080\/02687038.2012.654933","article-title":"Abnormalities of connected speech in semantic dementia vs. Alzheimer\u2019s disease","volume":"26","author":"Sajjadi","year":"2012","journal-title":"Aphasiology"},{"key":"ref63","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1044\/jshd.4702.210","article-title":"The potential of language tasks for identifying senile dementia","volume":"47","author":"Bayles","year":"1982","journal-title":"J Speech Hear Disord"},{"key":"ref64","first-page":"192","article-title":"An Analysis of Oral Non-Fluency of Chinese DAT Patients","author":"Huang","year":"2022","journal-title":"Contemporary Linguistics"},{"key":"ref65","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1080\/13803390701550128","article-title":"Language performance in Alzheimer\u2019s disease and mild cognitive impairment: a comparative review","volume":"30","author":"Taler","year":"2008","journal-title":"J Clin Exp Neuropsychol"},{"key":"ref66","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511627774","volume-title":"Conversations with an Alzheimer\u2019s patient: an interactional sociolinguistic study","author":"Hamilton","year":"1994"},{"key":"ref67","doi-asserted-by":"publisher","first-page":"519","DOI":"10.3233\/JAD-170881","article-title":"Connected speech features from picture description in Alzheimer\u2019s disease: a systematic review","volume":"65","author":"Slegers","year":"2018","journal-title":"J Alzheimers Dis"},{"key":"ref68","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2019\/3637954","article-title":"Physician perceptions about the barriers to prompt diagnosis of mild cognitive impairment and Alzheimer\u2019s disease","volume":"2019","author":"Judge","year":"2019","journal-title":"Int J Alzheimers Dis"},{"key":"ref69","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1080\/13607863.2019.1577799","article-title":"Do people with dementia and mild cognitive impairments experience stigma? A cross-cultural investigation between Italy, Poland and the UK","volume":"24","author":"Lion","year":"2020","journal-title":"Aging Ment Health"},{"key":"ref70","doi-asserted-by":"publisher","first-page":"437","DOI":"10.3389\/fnagi.2017.00437","article-title":"Declines in connected language are associated with very early mild cognitive impairment: results from the Wisconsin registry for Alzheimer\u2019s prevention","volume":"9","author":"Mueller","year":"2018","journal-title":"Front Aging Neurosci"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2024.1417966\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T04:49:18Z","timestamp":1723092558000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2024.1417966\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,8]]},"references-count":70,"alternative-id":["10.3389\/fpubh.2024.1417966"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2024.1417966","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,8]]},"article-number":"1417966"}}