Linguistic Features Identify Alzheimer’s Disease in Narrative Speech
The DOI matches its Crossref record; 97 of the 98 references it cites were found in a registry or an index.
Abstract
Background: Although memory impairment is the main symptom of Alzheimer’s disease (AD), language impairment can be an important marker. Relatively few studies of language in AD quantify the impairments in connected speech using computational techniques. Objective: We aim to demonstrate state-of-the-art accuracy in automatically identifying Alzheimer’s disease from short narrative samples elicited with a picture description task, and to uncover the salient linguistic factors with a statistical factor analysis. Methods: Data are derived from the DementiaBank corpus, from which 167 patients diagnosed with “possible” or “probable” AD provide 240 narrative samples, and 97 controls provide an additional 233. We compute a number of linguistic variables from the transcripts, and acoustic variables from the associated audio files, and use these variables to train a machine learning classifier to distinguish between participants with AD and healthy controls. To examine the degree of heterogeneity of linguistic impairments in AD, we follow an exploratory factor analysis on these measures of speech and language with an oblique promax rotation, and provide interpretation for the resulting factors. Results: We obtain state-of-the-art classification accuracies of over 81% in distinguishing individuals with AD from those without based on short samples of their language on a picture description task. Four clear factors emerge: semantic impairment, acoustic abnormality, syntactic impairment, and information impairment. Conclusion: Modern machine learning and linguistic analysis will be increasingly useful in assessment and clustering of suspected AD.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Indeed, speech has been studied as an objective tool for automatically differentiating people with amnestic AD presentation from healthy controls (HC).”
From Automatic classification of AD pathology in FTD phenotypes using natural speech (2024) · cites this paper as [14]
In the citing paper
“For example, a large number of lexical, syntactic, and acoustic features was used to classify patients with the amnestic AD presentation versus HC in the DementiaBank corpus with 82% accuracy.”
From Automatic classification of AD pathology in FTD phenotypes using natural speech (2024) · cites this paper as [14]
In the citing paper
“Acoustic, syntactic, and semantic features, including grammatical complexity and information content, can correlate strongly with cognitive decline [11,32].”
From A Conversational Robot for Older Adults with Alzheimer's Disease (2020) · cites this paper as [11]
In the citing paper
“Our linguistic analysis for cognitive monitoring has followed the work of Fraser et al. [11] and Roark et al. [32] and is restricted to examining features that can be automatically extracted from transcriptions of conversations.”
From A Conversational Robot for Older Adults with Alzheimer's Disease (2020) · cites this paper as Fraser et al. [11]
In the citing paper
“Accuracy of 92% was obtained in distinguishing people suffering from AD and healthy control group using top 25 ranked features [134].”
From Recent Advancements in Pathogenesis, Diagnostics and Treatment of Alzheimer’s Disease (2020) · cites this paper as [134]
7 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336
Costello, A. B., & Osborne, J. (2005) · University of Massachusetts Amherst · doi:10.7275/jyj1-4868 · Cited by 10,297 · cited 1×
“To fairly examine the degree of heterogeneity of linguistic impairments in patients with AD, we chose promax, an oblique rotation which allows factors to be correlated with each other [71].”
Evaluating the use of exploratory factor analysis in psychological research.
Fabrigar, L. R., Wegener, D. T., MacCallum, R. C., & Strahan, E. J. (1999) · Psychological Methods · doi:10.1037/1082-989x.4.3.272 · Cited by 9,587
Brysbaert, M., & New, B. (2009) · Behavior Research Methods · doi:10.3758/brm.41.4.977 · Cited by 2,821 · cited 1×
“Specifically, we use the SUBTL frequency norms [53] and the combined Bristol and Gilhooly-Logie norms [54, 55] for familiarity, imageability, and age-ofacquisition.”
The CHILDES Project: Tools for Analyzing Talk
Pye, C., & MacWhinney, B. (1994) · Language · doi:10.2307/416745 · Cited by 2,301
Cognition and anatomy in three variants of primary progressive aphasia
Gorno‐Tempini, M. L., Dronkers, N. F., Rankin, K. P., Ogar, J. M., Phengrasamy, L., Rosen, H. J., Johnson, J. K., Weiner, M. W., & Miller, B. L. (2004) · Annals of Neurology · doi:10.1002/ana.10825 · Cited by 1,625 · cited 2×
“All of the high loadings reflect characteristics of 629 semantically impoverished language, similar to that 630 seen in semantic dementia, a degenerative disorder 631 specifically affecting the temporal lobe [72].”
Using uh and um in spontaneous speaking
Clark, H. (2002) · Cognition · doi:10.1016/s0010-0277(02)00017-3 · Cited by 1,235 · cited 1×
“As described in the previous section , we remove the filled pauses uh, um, er, and ah, but we keep track of the frequency of occurrence of each type, as previous work has suggested that they may serve different purposes [49].”
Automatic analysis of syntactic complexity in second language writing
Lu, X. (2010) · International Journal of Corpus Linguistics · doi:10.1075/ijcl.15.4.02lu · Cited by 1,041
Age-of-acquisition, imagery, concreteness, familiarity, and ambiguity measures for 1,944 words
Gilhooly, K. J., & Logie, R. H. (1980) · Behavior Research Methods & Instrumentation · doi:10.3758/bf03201693 · Cited by 868 · cited 1×
“Specifically, we use the SUBTL frequency norms [53] and the combined Bristol and Gilhooly-Logie norms [54, 55] for familiarity, imageability, and age-ofacquisition.”
Verbal fluency performance in dementia of the Alzheimer’s type: a meta-analysis
Henry, J. D., Crawford, J. R., & Phillips, L. H. (2004) · Neuropsychologia · doi:10.1016/j.neuropsychologia.2004.02.001 · Cited by 847
Research works printed but not linked: 3
- Kempler, 1995, Dementia and Communication: Research and Clinical Implications, 98
- Brunét, 1978, Le Vocabulaire de Jean Giraudoux: Structure et Evolution
- Honoré, 1979, Some simple measures of richness of vocabulary, Assoc Lit Linguist Comput Bull, 7, 172
Cited by
Items 201–300 of 800
AI-Atroshi, C., Beulah, J. R., Singamaneni, K. K., Cyril, C. P. D., Neelakandan, S., & Velmurugan, S. (2022) · International Journal of Healthcare Management · doi:10.1080/20479700.2022.2097764 · Cited by 30
RetractedCognitive Digital Biomarkers from Automated Transcription of Spoken Language
Tavabi, N., Stück, D., Signorini, A., Karjadi, C., Alhanai, T., Sandoval, M., Lemke, C., Glass, J. R., Hardy, S., Lavallee, M., et al. (2022) · The Journal of Prevention of Alzheimer s Disease · doi:10.14283/jpad.2022.66 · Cited by 28
An Evaluation on Information Composition in Dementia Detection Based on Speech
Zheng, C., Bouazizi, M., & Ohtsuki, T. O. (2022) · IEEE Access · doi:10.1109/access.2022.3203068 · Cited by 28
“In the 105 past few years, using Natural Language Processing (NLP) 106 and machine learning techniques to detect dementia based 107 on speech and language data is receiving attention from 108 researchers around the world [9].”
BackgroundBattista, P., Catricalà, E., Piccininni, M., Copetti, M., Esposito, V., Polito, C., Miozzo, A., Gobbi, E., Cuoco, S., Boschi, V., et al. (2018) · Dementia and Geriatric Cognitive Disorders · doi:10.1159/000492632 · Cited by 30
Diagnosing People with Dementia Using Automatic Conversation Analysis
Mirheidari, B., Blackburn, D., Reuber, M., Walker, T., & Christensen, H. (2016) · Interspeech 2016 · doi:10.21437/interspeech.2016-857 · Cited by 25
Automated free speech analysis reveals distinct markers of Alzheimer’s and frontotemporal dementia
da Cunha, P. L., Ruiz, F., Ferrante, F. J., Sterpin, L., Ibáñez, A. M., Slachevsky, A., Matallana, D., Martínez, Á., Hesse, E., & García, A. M. (2024) · PLoS ONE · doi:10.1371/journal.pone.0304272 · Cited by 31
“Similar classification outcomes were obtained in previous machine learning studies, although these varied in the clinical grounding of their target features [8,52,74].”
BackgroundResultScreening for early Alzheimer’s disease: enhancing diagnosis with linguistic features and biomarkers
Chou, C., Chang, C.-T., Chang, Y., Lee, C., Chuang, Y., Chiu, Y., Liang, W.-L., Fan, Y.-M., & Liu, Y. (2024) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2024.1451326 · Cited by 34
Deep ensemble learning with transformer models for enhanced Alzheimer’s disease detection
Latif, S., Islam, N. U., Uddin, Z., Cheema, K. M., Ahmed, S. S., & Khan, M. F. (2025) · Scientific Reports · doi:10.1038/s41598-025-08362-y · Cited by 32
Transforming mental health research and care through artificial intelligence
Opel, N., & Breakspear, M. J. (2026) · Science · doi:10.1126/science.adz9193 · Cited by 37
Detecting cognitive impairments by agreeing on interpretations of linguistic features
Zhu, Z., Novikova, J., & Rudzicz, F. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1146 · Cited by 32
“In GANs, a “discriminator” network is trained to tell whether a vector is drawn from the real world or produced synthetically by a “generator” neural network, while the generator is trained to synthesize images as close to real data as possible.”
BackgroundMethodInfluentialSelf-citationVaccaro, M. G., Sarica, A., Quattrone, A., Chiriaco, C., Salsone, M., Morelli, M., & Quattrone, A. (2020) · Journal of Neuropsychology · doi:10.1111/jnp.12232 · Cited by 26
Soroski, T., Vasco, T. D. C., Newton‐Mason, S. M., Granby, S., Lewis, C., Harisinghani, A., Rizzo, M., Conati, C., Murray, G., Carenini, G., et al. (2022) · JMIR Aging · doi:10.2196/33460 · Cited by 29
“The Cookie Theft picture description task is a validated spontaneous speech task used extensively in prior work for AD/MCI classification [6,24-26].”
BackgroundMethodTelephone-based Dementia Screening I: Automated Semantic Verbal Fluency Assessment
Tröger, J., Linz, N., König, A., Robert, P. H., & Alexandersson, J. (2018) · International Conference on Pervasive Computing Technologies for Healthcare · doi:10.1145/3240925.3240943 · Cited by 38
“Tasks, eliciting spontaneous speech, are slightly more restricted and therefore easier to process; descriptions of the Cookie Theft Picture or comparable visual material, allows for extracting a wide variety of features and yields very good results [2, 18, 32, 41].”
BackgroundShankar, R., Goh, Z., Devi, F., & Xu, Q. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02105-z · Cited by 28
“These changes encompass multiple dimensions: reduced lexical diversity, increased use of pronouns and fi ller words, simpli fi ed syntactic structures, altered speech fl uency, and changes in acoustic properties such as pause patterns and articulation rate 6,7 .”
Predicting Dementia Screening and Staging Scores from Semantic Verbal Fluency Performance
Linz, N., Tröger, J., Alexandersson, J., Wolters, M. K., König, A., & Robert, P. H. (2017) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2017.100 · Cited by 34
“[14] worked on recordings of picture descriptions of the Cookie Theft Picture Description Task , extracted from the DementiaBank corpus [15].”
Natural Language Analysis to Detect Parkinson’s Disease
Pérez-Toro, P. A., Vásquez-Correa, J. C., Strauss, M., Orozco‐Arroyave, J. R., & Nöth, E. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-27947-9_7 · Cited by 24
Identification of Mild Cognitive Impairment Among Chinese Based on Multiple Spoken Tasks
Wang, T., Hong, Y., Wang, Q., Su, R., Ng, M. L., Xu, J. L., Wang, L., & Yan, N. (2021) · Journal of Alzheimer s Disease · doi:10.3233/jad-201387 · Cited by 29
“The impairments have been qualitatively associated with the widespread atrophies distributed in the anterior temporal lobes, left temporoparietal junction, and frontal premotor circuits of the MCI brains, which are actively engaged during speech production [14].”
Chen, M., Chu, X., & Subbalakshmi, K. P. (2021) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1145/3487351.3488346 · Cited by 24
“We extract the following handcrafted features: 37 PoS tags and one sentiment feature (average value of words’ sentiment polarity) using NLTK [34], four psycho-linguistic features (‘FamiliarityScore’, ‘ConcretenessScore’, ‘ImagabilityScore’ and ‘AgeofAcquisitionScore’), four vocabulary richness features (Honore’s Stati…”
MethodParsapoor, M., Alam, M. R., & Mihailidis, A. (2023) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-023-02122-6 · Cited by 34
“Previous research identified the MFCCs as one of the most relevant acoustic features to distinguish patients with different types of dementia [45, 63, 64].”
BackgroundLuz, S. F., Haider, F., Fromm, D., Lazarou, I., Kompatsiaris, I. Y., & MacWhinney, B. (2024) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2024.3378595 · Cited by 46
“This dataset has been used in several studies [26], [30], [31].”
Challenges with real-world smartwatch based audio monitoring
Liaqat, D., Wu, R. C., Gershon, A. S., Alshaer, H., Rudzicz, F., & de Lara, E. (2018) · doi:10.1145/3211960.3211977 · Cited by 28
Self-citationde la Fuente Garcia, S., Ritchie, C. W., & Luz, S. (2019) · BMJ Open · doi:10.1136/bmjopen-2018-026254 · Cited by 25
Grammaticalization and the linguistic individual: new avenues in lifespan research
Anthonissen, L., & Petré, P. (2019) · Linguistics Vanguard · doi:10.1515/lingvan-2018-0037 · Cited by 28
Cohen, T., & Pakhomov, S. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.176 · Cited by 38
Exploring MMSE Score Prediction Using Verbal and Non-Verbal Cues
Farzana, S., & Parde, N. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-3085 · Cited by 26
“…in automated dementia detection, although most work to date has focused on the binary task of dementia classification (wherein an individual is predicted to either have or not have dementia) [10, 11, 12, 13, 4] rather than the more nuanced problem of assigning continuous MMSE scores [14, 4].”
BackgroundInfluentialOn the importance of normative data in speech-based assessmentPreprint
Noorian, Z., Pou-Prom, C., & Rudzicz, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.00069 · Cited by 29
“Interestingly, many lexical features (indicative of previous work that only used the DB data set [6]) ceased to be important when including the normative data.”
BackgroundSelf-citationTalk2Me: Automated linguistic data collection for personal assessment
Komeili, M., Pou-Prom, C., Liaqat, D., Fraser, K. C., Yancheva, M., & Rudzicz, F. (2019) · PLOS ONE · doi:10.1371/journal.pone.0212342 · Cited by 23
“Fraser et al used over 370 automatically extracted acoustic, lexical, and syntactic features to detect AD [2] based on acoustics and speech transcripts.”
MethodSelf-citationvan den Berg, R. L., de Boer, C., Zwan, M. D., Jutten, R. J., van Liere, M. N., van de Glind, M.-C. A. B. J., Dubbelman, M. A., Schlüter, L., van Harten, A. C., Teunissen, C. E., et al. (2024) · Alzheimer s Research & Therapy · doi:10.1186/s13195-024-01543-3 · Cited by 29
Digital detection of Alzheimer’s disease using smiles and conversations with a chatbot
Takeshige‐Amano, H., Oyama, G., Ogawa, M., Fusegi, K., Kambe, T., Shiina, K., Ueno, S., Okuzumi, A., Hatano, T., Motoi, Y., et al. (2024) · Scientific Reports · doi:10.1038/s41598-024-77220-0 · Cited by 30
“Previous studies performed to detect AD using machine learning are detailed in Supplementary Table 2 13,15,19–31 (adapted from reference 3 ).”
MethodDetecting Dementia from Face in Human-Agent Interaction
Tanaka, H., Adachi, H., Kazui, H., Ikeda, M., Kudo, T., & Nakamura, S. (2019) · doi:10.1145/3351529.3360654 · Cited by 25
“These features are thus potentially useful for the detection of dementia [7, 9, 15, 16, 22].”
Backgroundde Almeida, R. G., Mobayyen, F., Antal, C., Kehayia, E., Nair, V. P., & Schwartz, G. J. (2021) · Cognitive Neuropsychology · doi:10.1080/02643294.2020.1858772 · Cited by 25
“…for this article can be accessed https://doi.org/10.1080/02643294.2020.1858772 memory and language impairments can be instrumental in AD early diagnosis and remediation (Ahmed et al., 2013; Fraser et al., 2016), with verb knowledge breakdown being one more important piece of this complex puzzle.”
BackgroundInfluentialLavoie, M., Black, S. E., Tang‐Wai, D. F., Graham, N. L., Stewart, S., Léonard, C., & Rochon, E. A. (2021) · International Journal of Language & Communication Disorders · doi:10.1111/1460-6984.12660 · Cited by 23
Treviso, M., Shulby, C., & Aluísio, S. M. (2017) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/e17-1030 · Cited by 23
Detecting Alzheimer’s Disease Using Interactional and Acoustic Features from Spontaneous Speech
Nasreen, S., Hough, J., & Purver, M. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-1526 · Cited by 22
“Linguistic variables are used to describe the quantitative and qualitative aspects of language production, for example via the decline in lexical-semantic abilities, word comprehension, verbal fluency, and syntactic processing for particular kinds of tasks such as picture description [7, 8].”
MethodPan, Y., Mirheidari, B., Reuber, M., Venneri, A., Blackburn, D. J., & Christensen, H. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2698 · Cited by 29
“Though better results were reported in [8, 33], those systems were not fully automatic.”
BackgroundResultLi, C., Knopman, D. S., Xu, W., Cohen, T., & Pakhomov, S. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.131 · Cited by 43
Language Analytics for Assessment of Mental Health Status and Functional Competency
Voleti, R., Woolridge, S. M., Liss, J., Milanovic, M., Stegmann, G., Hahn, S., Harvey, P. D., Patterson, T. L., Bowie, C. R., & Berisha, V. (2023) · Schizophrenia Bulletin · doi:10.1093/schbul/sbac176 · Cited by 26
Zhang, M., Tang, E., Ding, H., & Zhang, Y. (2024) · Journal of Speech, Language, and Hearing Research · doi:10.1044/2024_jslhr-24-00157 · Cited by 22
Pragmatic Aspects of Discourse Production for the Automatic Identification of Alzheimer's Disease
Pompili, A., Abad, A., de Matos, D. M., & Martins, I. P. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2967879 · Cited by 35
“problems aiming at identifying AD and related dementias [10], [49].”
BackgroundMethodA 5-min Cognitive Task With Deep Learning Accurately Detects Early Alzheimer's Disease
Almubark, I., Chang, L., Shattuck, K. F., Nguyen, T., Turner, R. S., & Jiang, X. (2020) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2020.603179 · Cited by 24
“Behavioral data from speech (Fraser et al., 2016; Nagumo et al., 2020), body movement (Khan and Jacobs, 2020), and neuropsychologic test scores (Lemos et al., 2012; Williams et al., 2013; Kang et al., 2019; Lee et al., 2019a) may provide useful features to machine learning classifiers for the…”
MethodLanguage Decline Characterizes Amnestic Mild Cognitive Impairment Independent of Cognitive Decline
Sherman, J. C., Henderson, C. R., Flynn, S., Gair, J. W., & Lust, B. (2021) · Journal of Speech Language and Hearing Research · doi:10.1044/2021_jslhr-20-00503 · Cited by 26
Artificial Intelligence in Medicine
Salvatore, C., Battista, P., & Castiglioni, I. (2020) · Wiley eBooks · doi:10.1002/9781119057840.ch19 · Cited by 22
Automated detection of progressive speech changes in early Alzheimer's disease
Robin, J., Xu, M., Balagopalan, A., Novikova, J., Kahn, L., Oday, A., Hejrati, M., Hashemifar, S., Negahdar, M., Simpson, W., et al. (2023) · Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring · doi:10.1002/dad2.12445 · Cited by 21
Bloom, P. P., Fisher, C., Tedesco, N., Kamdar, N. S., Garrido-Trevino, L., Robin, J., Asrani, S. K., & Lok, A. S.-F. (2024) · Hepatology · doi:10.1097/hep.0000000000001086 · Cited by 22
Looze, C. D., Dehsarvi, A., Crosby, L., Vourdanou, A., Coen, R. F., LAWLOR, B. A., & Reilly, R. B. (2021) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2021.637404 · Cited by 26
“Deficits in every one of these domains and conversational speech and language difficulties have been documented in adults with MCI and AD (Carlomagno et al., 2005; Feyereisen et al., 2007; Taler and Phillips, 2008; Rousseaux et al., 2010; Forbes-McKay et al., 2013; Drummond et al., 2015; Fraser et al., 2016).”
BackgroundUse of Artificial Intelligence in Clinical Neurology
Hillis, J. M., & Bizzo, B. C. (2022) · Seminars in Neurology · doi:10.1055/s-0041-1742180 · Cited by 22
Identifying neurocognitive disorder using vector representation of free conversation
Horigome, T., Hino, K., Toyoshiba, H., Shindo, N., Funaki, K., Eguchi, Y., Kitazawa, M., Fujita, T., Mimura, M., & Kishimoto, T. (2022) · Scientific Reports · doi:10.1038/s41598-022-16204-4 · Cited by 22
“In addition, previous studies using NLP and machine learning have shown that AD can be identified with high accuracy 10–18 .”
Evaluating the utility of daily speech assessments for monitoring depression symptoms
Gumus, M., DeSouza, D. D., Xu, M., Fidalgo, C., Simpson, W. S., & Robin, J. (2023) · Digital Health · doi:10.1177/20552076231180523 · Cited by 28
“On the other hand, linguistic features represent sentence generation, vocabulary and syntactic structures and sentiment, reflecting the content of speech and language.(13,14) Through cutting edge analysis methods such as signal processing, computational linguistics, and machine learning, changes in speech and language…”
BackgroundStanciu, S. G., König, K., Song, Y. M., Wolf, L., Charitidis, C. A., Bianchini, P., & Goetz, M. (2023) · Biophysics Reviews · doi:10.1063/5.0133027 · Cited by 23
Detecting bulbar amyotrophic lateral sclerosis (ALS) using automatic acoustic analysis
Simmatis, L. E. R., Robin, J., Spilka, M. J., & Yunusova, Y. (2024) · BioMedical Engineering OnLine · doi:10.1186/s12938-023-01174-z · Cited by 31
“Winterlight’s remote assessment system has been used extensively for detecting cognitive–linguistic impairments associated with a variety of neurodegenerative and psychiatric diseases [2, 10, 14, 25], but not yet the speech motor impairment and not yet in ALS.”
MethodStakeholder perspectives on ethical and trustworthy voice AI in health care
Bélisle‐Pipon, J., Powell, M., English, R., Malo, M.-F. A., Ravitsky, V., & Bensoussan, Y. E. (2024) · Digital Health · doi:10.1177/20552076241260407 · Cited by 28
Multi-Modal Detection of Alzheimer's Disease from Speech and TextPreprint
Mittal, A., Sahoo, S., Datar, A., Kadiwala, J., Shalu, H., & Mathew, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.00096 · Cited by 31
“Extensive studies have been conducted in detecting the patterns and markers in the speech that could indicate early-stage AD [5, 15, 20].”
BackgroundMethodGuo, Z., Liu, Z., Ling, Z.-H., Wang, S., Jin, L., & Li, Y. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.542 · Cited by 30
“Fraser et al. (2016) extracted total 370 features considering part-of-speech, syntax, acoustics, as well as other aspects of linguistics, and obtained a best average accuracy of 82% for binary classification using the 35 top-ranked features on the DementiaBank corpus.”
MethodDiaz-Asper, C. M., Chandler, C., Turner, R. S., Reynolds, B., & Elvevåg, B. (2022) · Cortex · doi:10.1016/j.cortex.2022.08.005 · Cited by 24
“1 NLP Feature Selection For the free speech task, three classes of NLP features (a set of 73 total) were extracted, namely (i) word-level (lexeme), (ii) sentence-level (syntactic), and (iii) meaning (semantics) of expressions [20].”
MethodClassification of Alzheimer's Disease with Deep Learning on Eye-tracking Data
Sriram, H., Conati, C., & Field, T. S. (2023) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3577190.3614149 · Cited by 23
“Diagnostic Aphasia Examination [16], a task that has been used extensively for assessing spontaneous speech in a variety of clinical settings [8], including AD [14,23,24].”
BackgroundKatariya, R., Sammeta, S. S., Kale, M. B., Kotagale, N. R., Umekar, M. J., & Taksande, B. G. (2024) · Ageing Research Reviews · doi:10.1016/j.arr.2024.102269 · Cited by 22
The pathway to secondary prevention of Alzheimer's disease
McDade, E., Bednar, M. M., Brashear, H. R., Miller, D. S., Maruff, P., Randolph, C., Ismail, Z., Carrillo, M. C., Weber, C. J., Bain, L. J., et al. (2020) · Alzheimer's & Dementia: Translational Research & Clinical Interventions · doi:10.1002/trc2.12069 · Cited by 20
Lukic, S., Fan, Z., García, A. M., Welch, A. E., Ratnasiri, B. M., Wilson, S. M., Henry, M. L., Vonk, J., Deleon, J., Miller, B. L., et al. (2024) · Cortex · doi:10.1016/j.cortex.2023.12.013 · Cited by 19
Speech Paralinguistic Approach for Detecting Dementia Using Gated Convolutional Neural Network
Makiuchi, M. R., Warnita, T., Inoue, N., Shinoda, K., Yoshimura, M., Kitazawa, M., Funaki, K., Eguchi, Y., & Kishimoto, T. (2021) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2020edp7196 · Cited by 19
“[8] fused transcription-based linguistic features with acoustic features such as Mel-frequency cepstral coefficients (MFCC).”
BackgroundMethodInfluentialBose, A., Dutta, M., Dash, N. S., Nandi, R., Dutt, A., & Ahmed, S. (2022) · Journal of Alzheimer s Disease · doi:10.3233/jad-220166 · Cited by 20
“Recently, we reported that Bengali-speaking AD patients produced fewer pronouns in novel story telling [3], in direct contrast with the overuse of pronouns by English-speaking AD patients [5, 6].”
BackgroundAtoki, A. V., Aja, P. M., Ondari, E. N., & Shinkafi, T. S. (2023) · International Journal of Food Properties · doi:10.1080/10942912.2023.2243050 · Cited by 21
“As time goes on and AD worsens, complex motor processes become less coherent, which raises the chance of falling.([30]) Memory issues deteriorate during this stage, and the person might not be able to identify close family members.”
BackgroundInfluentialShankar, R., Bundele, A., & Mukhopadhyay, A. (2025) · Mayo Clinic Proceedings Digital Health · doi:10.1016/j.mcpdig.2025.100205 · Cited by 38
Computing the structure of language for neuropsychiatric evaluation
Cecchi, G., Gurev, V., Heisig, S., Norel, R., Rish, I., & Schrecke, S. R. (2017) · IBM Journal of Research and Development · doi:10.1147/jrd.2017.2648478 · Cited by 19
Exploring neural models for predicting dementia from language
Kong, W., Jang, H., Carenini, G., & Field, T. S. (2020) · Computer Speech & Language · doi:10.1016/j.csl.2020.101181 · Cited by 22
“We perform 10-fold cross validation following the practice in prior work [12, 28].”
BackgroundMethodInfluentialDementia Detection by Analyzing Spontaneous Mandarin Speech
Liu, Z., Guo, Z., Ling, Z.-H., Wang, S., Jin, L., & Li, Y. (2019) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc47483.2019.9023041 · Cited by 21
“Most of previous studies using this dataset [12]–[15] aimed to make a binary classification between AD group and control group, which had about 250 and 240 samples in the dataset.”
BackgroundResultAlzheimer's Dementia Detection from Audio and Language Modalities in Spontaneous Speech
Campbell, E. L., Docío-Fernández, L., Jiménez-Raboso, J., & Mateo, C. G. (2021) · IberSPEECH · doi:10.21437/iberspeech.2021-57 · Cited by 19
“According to the literature[4][5][6], using information from the patient’s voice, as well as from its transcription would ease the early AD detection task.”
BackgroundHealth Guardian Platform: A technology stack to accelerate discovery in Digital Health research
Wen, B., Siu, V. S., Buleje, I., Hsieh, K. Y., Itoh, T., Zimmerli, L., Hinds, N., Eyigöz, E., Dang, B., von Cavallar, S., et al. (2022) · IEEE International Conference on Digital Health (ICDH) · doi:10.1109/icdh55609.2022.00015 · Cited by 20
“There are many examples of AI research spanning vast domains of healthcare such as using automated speech and language analysis to identify individuals with Alzheimer’s disease [3] or determine severity of cognitive impairments [4], [5], automated drawing analysis to assess elderly cognition [6], and gait and motion m…”
BackgroundIvanova, O., Martínez‐Nicolás, I., García-Piñuela, E., & Meilán, J. J. G. (2023) · Frontiers in Language Sciences · doi:10.3389/flang.2023.1199107 · Cited by 25
Cognitive components of aging-related increase in word-finding difficulty
Wei, H. T., Kulzhabayeva, D., Erceg, L., Robin, J., Hu, Y. Z., Chignell, M., & Meltzer, J. A. (2024) · Aging Neuropsychology and Cognition · doi:10.1080/13825585.2024.2315774 · Cited by 21
“…have been used to develop natural language algorithms that extract acoustic and linguistic features, which can index language abilities such as semantic and syntactic complexity, discourse repetition, speech coher-ency, word-finding difficulties, etc (see Fraser et al., 2015; Robin et al., 2021).”
Self-citationAutomated speech-based screening for alzheimer's disease in a care service scenario
Tröger, J., Linz, N., Alexandersson, J., König, A., & Robert, P. (2017) · Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare · doi:10.1145/3154862.3154915 · Cited by 19
“…reporting classi-fiers discriminating between (1.a) cognitive impairment (CI) in a broader sense and healthy controls (HC) with 90% accuracy [30], (1.b) AD and HC with 80% to 95% accuracy [13, 7, 17, 14, 1], (1.c) MCI and HC with 79% to 88% accuracy [14, 27, 10] and (1.d) MCI and AD with 80% [14].”
BackgroundMethodResultInfluentialAnalysis and Classification of Word Co-Occurrence Networks From Alzheimer’s Patients and Controls
Millington, T., & Luz, S. F. (2021) · Frontiers in Computer Science · doi:10.3389/fcomp.2021.649508 · Cited by 18
Mueller, K. D., Koscik, R. L., Clark, L. R., Hermann, B. P., Johnson, S. C., & Turkstra, L. S. (2017) · Archives of Clinical Neuropsychology · doi:10.1093/arclin/acx116 · Cited by 20
The Effect of Heterogeneous Data for Alzheimer's Disease Detection from SpeechPreprint
Balagopalan, A., Novikova, J., Rudzicz, F., & Ghassemi, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.12254 · Cited by 22
“Fraser et al. [8] used linguistic and acoustic features to classify healthy and pathological speech transcripts with an accuracy of 82% .”
BackgroundSelf-citationZhang, Z., Wang, T., Hu, Z., Yang, L.-Z., & Li, H. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3509620 · Cited by 17
“Thus early cognitive decline in AD can be manifested through subtlechangesinspeechpatterns,providingauniquewindowfor observinganindividual’scognitivestate[11],[12].”
König, A., Zeghari, R., Guerchouche, R., Duc Tran, M., Bremond, F., Linz, N., Lindsay, H., Langel, K., Ramakers, I., Lemoine, P., et al. (2021) · BMJ Open · doi:10.1136/bmjopen-2020-047083 · Cited by 17
Agmon, G., Pradhan, S., Ash, S., Nevler, N., Liberman, M., Grossman, M., & Cho, S. (2024) · Journal of Speech, Language, and Hearing Research · doi:10.1044/2023_jslhr-23-00009 · Cited by 17
A Hybrid Deep Ensemble for Speech Disfluency Classification
Pravin, S. C., & Palanivelan, M. (2021) · Circuits Systems and Signal Processing · doi:10.1007/s00034-021-01657-1 · Cited by 21
Alzheimer’s disease diagnosis using genetic programming based on higher order spectra features
Nasrolahzadeh, M., Rahnamayan, S., & Haddadnia, J. (2021) · Machine Learning with Applications · doi:10.1016/j.mlwa.2021.100225 · Cited by 24
Dementia Speech Dataset Creation and Analysis in Indic Languages—A Pilot Study
Vekkot, S., Prakash, N. N. V. S., Reddy, T. S. E., Sripathi, S. R., Lalitha, S., Gupta, D., Zakariah, M., & Alotaibi, Y. A. (2023) · IEEE Access · doi:10.1109/access.2023.3334790 · Cited by 18
“Fraser et al. [44] recorded speech from 95 participants, including 45 with Alzheimer’s disease and 50 with healthy controls.”
BackgroundA novel speech analysis algorithm to detect cognitive impairment in a Spanish population
Kaser, A. N., Lacritz, L. H., Winiarski, H. R., Gabirondo, P., Schaffert, J., Coca, A. J., Jiménez-Raboso, J., Rojo, T., Zaldua, C., Honorato, I., et al. (2024) · Frontiers in Neurology · doi:10.3389/fneur.2024.1342907 · Cited by 21
Learning multiview embeddings for assessing dementia
Pou-Prom, C., & Rudzicz, F. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1304 · Cited by 20
“On the same dataset, Fraser et al. (2015) extracted an extensive list of lexicosyntactic features from the transcripts and identified participants with AD with an accuracy of 81%.”
BackgroundSelf-citationEvaluation of macrolinguistic aspects of the oral discourse in patients with Alzheimer’s disease
de Lira, J. O., Minett, T., Bertolucci, P. H. F., & Ortiz, K. Z. (2018) · International Psychogeriatrics · doi:10.1017/s1041610218001758 · Cited by 18
Favaro, A., Motley, C., Cao, T., Iglesias, M., Butala, A., Oh, E. S., Stevens, R. D., Villalba, J., Dehak, N., & Moro-Velázquez, L. (2023) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt54892.2023.10022435 · Cited by 22
“In this respect, it has already been shown that the retrieval of lexical items and the construction of coherent narratives are usually more challenging for subjects with semantic dementia [8].”
BackgroundDistinguishable features of spontaneous speech in Alzheimer’s clinical syndrome and healthy controls
Burke, E. M., Gunstad, J., Pavlenko, O., & HAMRICK, P. J. J. (2023) · Aging Neuropsychology and Cognition · doi:10.1080/13825585.2023.2221020 · Cited by 18
“…studies have identified lexical-semantic features that can distinguish persons with and without neurological conditions (e.g., Boschi et al., 2017; Fraser et al., 2016; Ostrand & Gunstad, 2021; Roark et al., 2011), very few studies have examined whether the same set of speech features found to be…”
BackgroundInfluentialBurke, E. M., Gunstad, J., & HAMRICK, P. J. J. (2023) · Applied Corpus Linguistics · doi:10.1016/j.acorp.2023.100064 · Cited by 24
Paralinguistic and linguistic fluency features for Alzheimer's disease detection
Campbell, E. L., Mesía, R. Y., Docío-Fernández, L., & Mateo, C. G. (2021) · Computer Speech & Language · doi:10.1016/j.csl.2021.101198 · Cited by 16
Primary Progressive Aphasia: Use of Graphical Markers for an Early and Differential Diagnosis
Plonka, A., Mouton, A., Macoir, J., Tran, T.-M., Derremaux, A., Robert, P. H., Manera, V., & Gros, A. (2021) · Brain Sciences · doi:10.3390/brainsci11091198 · Cited by 20
“These results are in line with other studies that show early dysexecutive symptoms in patients with PPA [56] and a severe language impairment in patients with AD [57].”
ResultTanaka, H., Adachi, H., Ukita, N., Kudo, T., & Nakamura, S. (2016) · Proceedings of the 18th ACM International Conference on Multimodal Interaction · doi:10.1145/2993148.2993193 · Cited by 14
“Recently and achieving higher accuracy, Fraser et al [5] studied the potential of using language features to identify Alzheimer’s disease.”
BackgroundResultA hybrid knowledge and ensemble classification approach for prediction of venous thromboembolism
Sabra, S., Malik, K. M., Afzal, M., Sabeeh, V., & Eddine, A. C. (2019) · Expert Systems · doi:10.1111/exsy.12388 · Cited by 17
“Moreover, when evaluating the performance of MLPNN and comparing its prediction precision to the colorectal cancer prediction model in (Fraser et al., 2015), our standalone MLPNN produced AUROC of 87.5% compared with their 81.7% for 30 ‐ day admission and AUROC 68% for readmission…”
ResultInfluentialSlovak database of speech affected by neurodegenerative diseases
Rusko, M., Sabo, R., Trnka, M., Zimmermann, A., Malaschitz, R., Ružický, E., Brandoburová, P., Kevická, V., & Škorvánek, M. (2024) · Scientific Data · doi:10.1038/s41597-024-04171-6 · Cited by 27
A longitudinal multi-modal dataset for dementia monitoring and diagnosis
Gkoumas, D., Wang, B., Tsakalidis, A., Wolters, M. K., Purver, M., Zubiaga, A., & Liakata, M. (2024) · Language Resources and Evaluation · doi:10.1007/s10579-023-09718-4 · Cited by 25
Classification of Alzheimer's using Deep-learning Methods on Webcam-based Gaze Data
Harisinghani, A., Sriram, H., Conati, C., Carenini, G., Field, T. S., Jang, H., & Murray, G. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3591126 · Cited by 19
AI‐based assessments of speech and language impairments in dementia
Parsapoor, M. (2023) · Alzheimer s & Dementia · doi:10.1002/alz.13395 · Cited by 19
Multilingual Prediction of Cognitive Impairment with Large Language Models and Speech Analysis
Agbavor, F., & Liang, H. (2024) · Brain Sciences · doi:10.3390/brainsci14121292 · Cited by 21
“Other studies [9,21,22] have utilized linguistic features from LLMs such as Bidirectional Encoder Representations from Trans-formers (BERT) [23] and Generative Pre-trained Transformer 3 (GPT-3) [24] for dementia detection.”
Oiza-Zapata, I., & Gallardo-Antolín, A. (2025) · Electronics · doi:10.3390/electronics14112248 · Cited by 18
A Comparative Study of Machine Learning Models for Parkinson’s Disease Detection
Bunterngchit, C., & Bunterngchit, Y. (2022) · International Conference on Decision Aid Sciences and Applications (DASA) · doi:10.1109/dasa54658.2022.9765159 · Cited by 15
Καλτσά, Μ., Tsolaki, A., Lazarou, I., Mittas, I., Papageorgiou, M., Papadopoulou, D., Tsimpli, I. M., & Tsolaki, M. (2024) · Journal of Alzheimer s Disease Reports · doi:10.3233/adr-230204 · Cited by 21
Detecting fatigue in multiple sclerosis through automatic speech analysis
Dias, M., Dörr, F., Garthof, S., Schäfer, S., Elmers, J., Schwed, L., Linz, N., Overell, J. R., Hayward-Koennecke, H. K., Tröger, J., et al. (2024) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2024.1449388 · Cited by 17
“Furthermore, free speech tasks can capture a wide range of linguistic and paralinguistic features, such as speech rate, fluency, lexical diversity, and voice quality, which are often affected in these disorders (Fraser et al., 2016; König et al., 2015).”
BackgroundMatsangidou, M., Solomou, T., Frangoudes, F., Papayianni, E., Kkeli, N., & Pattichi, C. S. (2024) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2024.103413 · Cited by 15
Zolnoori, M., Zolnour, A., Vergez, S., Sridharan, S., Spens, I., Topaz, M., Noble, J. M., Henry, S. B., Hirschberg, J., Bowles, K. H., et al. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae300 · Cited by 17
Metadata
- Authors
- Fraser, K. C., Meltzer, J. A., & Rudzicz, F.
- Affiliations
- University of Toronto (CA)
- Rotman Research Institute (CA)
- University Health Network (CA)
- Corresponding author
- Rudzicz, Frank
- Venue
- Journal of Alzheimer's Disease
- Publisher
- SAGE Publications
- Published
- 2015-11-27
- Volume
- 49
- Issue
- 2
- Pages
- 407-422
- ISSN
- 1387-2877 (ISSN-L)
- 1875-8908
- OpenAlex
- W1853705225
- Semantic Scholar
- bdd4aee4ea351e615eae0e4ab317bf974f1f731b
- Cited by
- 797
- References
- 98
- Citations by year
- 2026: 92 · 2025: 87 · 2024: 81 · 2023: 93 · 2022: 77 · 2021: 104 · 2020: 115 · 2019: 59 · 2018: 41 · 2017: 33 · 2016: 14
- FWCI
- 23.78
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Alzheimer s Disease (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Carnegie Mellon University
- Alzheimer Society
- National Institutes of Health (5p01ag003705-04)
- Medical Center, University of Pittsburgh
- Natural Sciences and Engineering Research Council of Canada
- National Institute on Aging (AG-005133, P50AG005133, AG003705)
- National Institute on Deafness and Other Communication Disorders (R01DC008524)
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neurobiology of Language and Bilingualism
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- Alzheimer's disease, language impairment
- MeSH terms
- Machine Learning, Aged, Aged, 80 and over, Alzheimer Disease, Diagnosis, Computer-Assisted, Factor Analysis, Statistical, Female, Humans, Language Disorders, Linguistics, Male, Mental Status Schedule, Middle Aged, Photic Stimulation, Speech, Verbal Behavior, Logistic Models, Narration
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.