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 301–400 of 800
Detecting semantic changes in Alzheimer’s disease with vector space models
Fraser, K., & Hirst, G. (2016) · Language Resources and Evaluation · Cited by 17
Self-citationDementia Scale Classification Based on Ubiquitous Daily Activity and Interaction Sensing
Okada, S., Inoue, K., Imai, T., Noguchi, M., & Kuwamura, K. (2019) · International Conference on Affective Computing and Intelligent Interaction and workshops · doi:10.1109/acii.2019.8925454 · Cited by 16
“[11] proposed an approach to identifying Alzheimer’s disease through speech recordings”
MethodReeves, S. M., Williams, V. J., Costela, F. M., Palumbo, R., Umoren, O., Christopher, M. M., Blacker, D., & Woods, R. L. (2020) · Neuropsychology · doi:10.1037/neu0000621 · Cited by 14
A Systematic Review of Expressive and Receptive Prosody in People With Dementia
Oh, C., Morris, R. J., & Wang, X. (2021) · Journal of Speech Language and Hearing Research · doi:10.1044/2021_jslhr-21-00013 · Cited by 19
Reilly, J. J., Finley, A. M., Litovsky, C. P., & Kenett, Y. N. (2023) · Journal of Experimental Psychology General · doi:10.1037/xge0001389 · Cited by 20
Shibata, D., Wakamiya, S., Ito, K., Miyabe, M., Kinoshita, A., & Aramaki, E. (2018) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3180308.3180332 · Cited by 14
“Some reports have described studies [2, 3] of healthy controls and dementia distinguished by machine learning with language and acoustic features.”
BackgroundA Review of Alzheimer's Disease Classification Using Neuropsychological Data and Machine Learning
Lyu, G. (2018) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei.2018.8633126 · Cited by 19
“The syntactic complexity of the image descriptions was measured by the number of direct components of the syntactic structure such as MLT, MLC, MLS [11].”
BackgroundMethodExploiting Pre-Trained ASR Models for Alzheimer's Disease Recognition Through Spontaneous SpeechPreprint
Qin, Y. H., Liu, W., Peng, Z., Ng, S.-I., Li, J., Hu, H., & Lee, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.01493 · Cited by 27
“Example features are part-of-speech, vocabulary richness and syntactic complexity features [14].”
BackgroundAutomatic classification of AD pathology in FTD phenotypes using natural speech
Cho, S., Olm, C. A., Ash, S., Shellikeri, S., Agmon, G., Cousins, K. A. Q., Irwin, D. J., Grossman, M., Liberman, M., & Nevler, N. (2024) · Alzheimer's & Dementia · doi:10.1002/alz.13748 · Cited by 13
Pan, Y., Mirheidari, B., Blackburn, D. J., & Christensen, H. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3533363 · Cited by 24
“Some studies suggest that integrating acoustic and linguistic information may not be necessary [32], [59], while others advocate for joint modelling of these modalities [36], [37], [46], [60], [61], [62], [63].”
Yamada, Y., Shinkawa, K., Nemoto, M., & Arai, T. (2021) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2021.712251 · Cited by 15
Hu, J., Li, J., Zeng, Y., Yang, D., Liang, D., Meng, H. M. L., & Ma, X. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642960 · Cited by 20
“As communication impairments are often indicative of NCDs, machine learning algorithms that detect and analyze anomalies in speech, language processing, and language production offer a new lens for NCD screening [18, 34, 48].”
BackgroundChen, Y.-T., Hartsuiker, R. J., & Pistono, A. (2024) · Aphasiology · doi:10.1080/02687038.2024.2358556 · Cited by 13
“In recent years, the use of machine learning methods for the classification of MCI, AD, and cognitively healthy controls has significantly increased (e.g., Fraser et al., 2016; Orimaye et al., 2017).”
Medenica, V., Ivanović, L., & Milošević, N. (2024) · Applied Neuropsychology Adult · doi:10.1080/23279095.2024.2364229 · Cited by 19
Kim, T. M., Son, J., Chun, J., Lee, Y., Kim, D., Choi, I.-Y., Ko, T., & Choi, S. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108950 · Cited by 13
A Systematic Review of NLP for Dementia: Tasks, Datasets, and Opportunities
Peled-Cohen, L., & Reichart, R. (2025) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.35 · Cited by 20
“Before 2017, many studies relied on classic machine learning methods like SVM and Random Forests using straightforward features like N-grams (Jarrold et al., 2014; Fraser et al., 2016a; Zhou et al., 2016; Santos et al., 2017), achieving accuracy rates around 85%.”
Evaluating spoken language as a biomarker for automated screening of cognitive impairment
Lima, M. R. D., Capstick, A., Geranmayeh, F., Nilforooshan, R., Matarić, M. J., Vaidyanathan, R., & Barnaghi, P. M. (2025) · Communications Medicine · doi:10.1038/s43856-025-01263-1 · Cited by 23
“Deep learning techniques have been utilised for automatic feature extraction with pre-trained models for audio and text representation [18].”
Hall, A., Shinkawa, K., Kosugi, A., Takase, T., Kobayashi, M., Nishimura, M., Nemoto, M., Watanabe, R., Tsukada, E., Ota, M., et al. (2019) · PubMed · Cited by 17
Bias in medical artificial intelligence
AlHasan, A. (2021) · Bulletin of The Royal College of Surgeons of England · doi:10.1308/rcsbull.2021.111 · Cited by 15
Dementia Detection by Fusing Speech and Eye-Tracking Representation
Sheng, Z.-Y., Guo, Z., Li, X., Li, Y., & Ling, Z.-H. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747054 · Cited by 18
Daily Pain Prediction Using Smartphone Speech Recordings of Patients With Spine Disease
Duey, A. H., Rana, A., Siddi, F., Hussein, H., Onnela, J.-P. “., & Smith, T. R. (2023) · Neurosurgery · doi:10.1227/neu.0000000000002474 · Cited by 16
Detecting Early Stage Dementia based on Natural Language Processing
Shibata, D., Ito, K., Wakamiya, S., & Aramaki, E. (2019) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.b-j11 · Cited by 14
Ferrario, A., Luo, M., Polsinelli, A. J., Moseley, S., Mehl, M. R., Yordanova, K., Martin, M., & Demiray, B. (2022) · JMIR Aging · doi:10.2196/28333 · Cited by 17
“For example, Fraser et al [20] examined various linguistic features, such as part-of-speech (POS) tags, grammatical complexity, vocabulary richness, and repetitiveness, and showed them to be useful in predicting dementia cases.”
BackgroundIdentification of Dementia Using Audio BiomarkersPreprint
Chakraborty, R., Pandharipande, M. A., Bhat, C. G., & Kopparapu, S. K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.12788 · Cited by 21
“Earlier works used manual transcriptions to obtain linguistic features from dementia speech to classify into dementia stages [4], whereas recent works use automatic speech recognition to obtain the lexical and semantic features for this purpose [5, 6].”
Alzheimer's Dementia Detection from Audio and Text ModalitiesPreprint
Campbell, E. L., Docío-Fernández, L., Jiménez-Raboso, J., & Mateo, C. G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.04617 · Cited by 19
“is feature vector as input, an SVM is trained. Unlike the previous method, the classification here is performed at subject level, by considering the full transcript of each participant. Previous works [20] have shown that certain linguistic features are useful for detecting AD using Cookie Theft test. Here 13 features…”
MethodZolnour, A., Azadmaleki, H., Haghbin, Y., Taherinezhad, F., Nezhad, M. J. M., Rashidi, S., Khani, M., Taleban, A., Sani, S. M., Dadkhah, M., et al. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1669896 · Cited by 25
“…2023): (1) lexical richness was measured with established diversity metrics to gauge reliance on high-frequency vocabulary (Paganelli et al., 2003; Fraser et al., 2016; Meteyard et al., 2014); (2) syntactic complexity was assessed through part-of-speech tagging to reflect grammatical structure…”
Matsangidou, M., Solomou, T., Frangoudes, F., Papayianni, E., & Pattichis, C. S. (2023) · JMIR Aging · doi:10.2196/45799 · Cited by 12
Medicine's New Rhythm: Harnessing Acoustic Sensing via the Internet of Audio Things for Healthcare
Pervez, F., Shoukat, M., Suresh, V., Farooq, M. U. B., Sandhu, M. M., Qayyum, A., Usama, M., Girardi, A. M., Latif, S., & Qadir, J. (2024) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2024.3462812 · Cited by 16
“A similar study is presented in [147] that distinguishes patients with Alzheimer’s disease based on speech disruptions during a picture description task.”
BackgroundNyongesa, C. A., Hogarth, M. A., & Pa, J. (2025) · Journal of Alzheimer s Disease · doi:10.1177/13872877251339756 · Cited by 15
“9 10 – 12 Additionally, shifts in referential language, such as increased pronoun use, are attributed to dif fi culties in maintaining coherent and connected speech as impairment progresses.”
Fraser, K., Linz, N., Li, B., Fors, K. L., Rudzicz, F., König, A., Alexandersson, J., Robert, P. H., & Kokkinakis, D. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1367 · Cited by 35
“…our best English result (AUC=0.84, which corresponds to an accuracy of 75% and F 1 score of 0.77) is comparable to the other published results on this dataset (Prud’hommeaux and Roark, 2015; Yancheva and Rudzicz, 2016; Sirts et al., 2017; Fraser et al., 2016; Hern´andez-Dom´ınguez et al., 2018).”
BackgroundResultInfluentialSelf-citationNatural speech markers of Alzheimer's disease co-pathology in Lewy body dementias
Shellikeri, S., Cho, S., Cousins, K. A. Q., Liberman, M., Howard, E., Balganorth, Y., Weintraub, D., Spindler, M., Deik, A., Lee, E. B., et al. (2022) · Parkinsonism & Related Disorders · doi:10.1016/j.parkreldis.2022.07.023 · Cited by 12
Speech technology in healthcare
Deepa, P., & Khilar, R. (2022) · Measurement Sensors · doi:10.1016/j.measen.2022.100565 · Cited by 19
Domain Adaptation for Detecting Mild Cognitive Impairment
Masrani, V., Murray, G., Field, T. S., & Carenini, G. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-57351-9_29 · Cited by 13
“Fraser used DementiaBank, an American cohort of 204 persons with dementia and 102 controls, and performed factor analysis on a set of 370 lexical and acoustic features, finding optimal performance when 35-50 features are used[13].”
BackgroundMethodInfluentialBalagopalan, A., Shkaruta, K., & Novikova, J. (2020) · Workshop on Noisy User-generated Text (W-NUT) · doi:10.18653/v1/2020.wnut-1.21 · Cited by 18
Speech databases for mental disorders: A systematic review
Li, Y., Lin, Y., Ding, H., & Li, C. (2019) · General Psychiatry · doi:10.1136/gpsych-2018-100022 · Cited by 12
Computational Intelligent Models for Alzheimer's Prediction Using Audio Transcript Data
Khan, Y. F., Kaushik, B., & Mir, B. A. (2022) · Computing and Informatics · doi:10.31577/cai_2022_6_1589 · Cited by 13
Liu, A. A., & Barr, W. (2024) · Frontiers in Neurology · doi:10.3389/fneur.2023.1260523 · Cited by 12
Communication interventions for people with dementia and their communication partners
El‐Wahsh, S., Monroe, P., Kumfor, F., & Ballard, K. J. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-818685-5.00003-9 · Cited by 16
Spatio-Semantic Graphs From Picture Description: Applications to Detection of Cognitive Impairment
Ambadi, P. S., Basche, K. E., Koscik, R. L., Berisha, V., Liss, J., & Mueller, K. D. (2021) · Frontiers in Neurology · doi:10.3389/fneur.2021.795374 · Cited by 19
“…of this study was to evaluate the novel approach and validate its utility for detecting cognitive impairment, there is no evaluation of the marginal value of these features above and beyond other language-based features used in machine learning models of cognitive impairment based on speech (32).”
BackgroundWen, B., Wang, N., Subbalakshmi, K. P., & Chandramouli, R. (2022) · JMIR Formative Research · doi:10.2196/36590 · Cited by 14
“Furthermore, in the study by Fraser et al [33], RB was proved to have higher correlations with a diagnosis of AD.”
Spencer, E. J., Bryant, L., & Colyvas, K. (2020) · Topics in Language Disorders · doi:10.1097/tld.0000000000000212 · Cited by 14
“Likewise, in an investigation of linguistic features in the discourse of people with Alzheimer’s dementia, Fraser, Meltzer, and Rudzicz (2016) analyzed 370 linguistic features through a variety of computerized methods.”
BackgroundHampsey, E., Meszaros, M., Skirrow, C., Strawbridge, R., Taylor, R. H., Chok, L., Aarsland, D., Al‐Chalabi, A., Chaudhuri, К. R., Weston, J., et al. (2022) · BMJ Open · doi:10.1136/bmjopen-2022-061193 · Cited by 12
Shinkawa, K., Kosugi, A., Nishimura, M., Nemoto, M., Nemoto, K., Takeuchi, T., Numata, Y., Watanabe, R., Tsukada, E., Ota, M., et al. (2019) · Studies in health technology and informatics · doi:10.3233/shti190240 · Cited by 12
“These changes in the speech and gait features consistent with the results of previous studies that investigated the differnces in these measures with HC and dementia [10,13,22].”
BackgroundMethodResultInfluentialLi, V. O. K., Lam, J. C. K., Han, Y., Cheung, L. Y. L., Downey, J., Kaistha, T., & Gozes, I. (2021) · Journal of Molecular Neuroscience · doi:10.1007/s12031-021-01865-z · Cited by 11
Language disorders in understudied languages: Opening editorial
García, A. M., Tee, B. L., Deleon, J., Alladi, S., & Gorno‐Tempini, M. L. (2025) · Cortex · doi:10.1016/j.cortex.2025.05.009 · Cited by 13
Neurodegenerative Disorders of Speech and Language: Non-language-dominant Diseases
García, A. M., DeLeon, J., & Tee, B. L. (2022) · Encyclopedia of Behavioral Neuroscience, 2nd edition · doi:10.1016/b978-0-12-819641-0.00042-6 · Cited by 10
Turning the Spotlight to Cholinergic Pharmacotherapy of the Human Language System
Dávila, G., Torres‐Prioris, M. J., López-Barroso, D., & Berthier, M. L. (2023) · CNS Drugs · doi:10.1007/s40263-023-01017-4 · Cited by 11
Language abnormalities in Alzheimer's disease indicate reduced informativeness
Bayat, S., Sanati, M., Panahi, M. M., Khodadadi, A., Ghasimi, M., Rezaee, S., Besharat, S., Mahboubi‐Fooladi, Z., Almasi‐Dooghaee, M., Sanei‐Taheri, M., et al. (2024) · Annals of Clinical and Translational Neurology · doi:10.1002/acn3.52205 · Cited by 12
Chakravarthi, B. A., & Shivakanth, G. (2025) · Computational Intelligence · doi:10.1111/coin.70051 · Cited by 12
Modeling Dialogue in Conversational Cognitive Health Screening Interviews.
Farzana, S., Valizadeh, M., & Parde, N. (2020) · Language Resources and Evaluation · Cited by 10
An efficient context-aware screening system for Alzheimer's disease based on neuropsychology test
Tsai, A. C.-Y., Hong, S.-Y., Yao, L.-H., Chang, W., Fu, L., & Chang, Y. (2021) · Scientific Reports · doi:10.1038/s41598-021-97642-4 · Cited by 12
Feenaughty, L. (2022) · Aphasiology · doi:10.1080/02687038.2022.2099527 · Cited by 11
“This duration was also sufficient for the language analyses because participants produced the recommended minimum 100 – 150 words (Fraser et al., 2016; Mueller et al., 2018) or, on average, approximately 300 – 400 words (Brookshire & Nicholas, 1994) to obtain reliable and valid results for…”
BackgroundAutomatic Audio-based Screening System for Alzheimer’s Disease Detection
Lin, S.-Y., Chang, H.-L., Hwang, J.-J., Wai, T., Chang, Y., & Fu, L. (2022) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53654.2022.9945127 · Cited by 12
“Fraser et al. [18] also utilized both acoustic and linguistic features, selected 35 top-ranked features out of 370 features.”
BackgroundMiura, K. W., Tokunaga, S., Sekiguchi, T., Sugimoto, H., & Otake, M. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1114790 · Cited by 11
“Some attempts have been made to screen patients with dementia and MCI by linguistic features such as speech volume, tense, and vocabulary (Fraser et al., 2016; Asgari et al., 2017).”
BackgroundGao, N., & He, Q. (2024) · Humanities and Social Sciences Communications · doi:10.1057/s41599-024-03509-0 · Cited by 10
“However, increasing studies (e.g., Ahmed et al. 2012, 2013; Bose et al. 2021; Chapin et al. 2022; Fraser et al. 2016; Ivanova et al. 2023; Sajjadi et al. 2012) discern that AD patients present changes in syntactic ability, particularly in terms of syntactic complexity.”
Lima, B. S., Murphy, K. J., Troyer, A. K., Levine, B., Graham, N. L., Léonard, C., Tang‐Wai, D. F., Black, S. E., & Rochon, E. A. (2020) · Aphasiology · doi:10.1080/02687038.2020.1843593 · Cited by 11
“proportion of high-frequency words (Ash et al., 2006; Bird et al., 2000; Fraser et al., 2016; Meteyard & Patterson, 2009; Wilson et al., 2010).”
BackgroundPredicting Dementia Risk Using Paralinguistic and Memory Test Features with Machine Learning Models
You, Y., Ahmed, B., Barr, P., Ballard, K. J., & Valenzuela, M. (2019) · IEEE Healthcare Innovations and Point of Care Technologies Conference (HI-POCT) · doi:10.1109/hi-poct45284.2019.8962887 · Cited by 17
“In addition, the maximum, minimum, standard deviation, skewness and kurtosis of the MFCC coefficients as well as their first derivative were included.”
BackgroundInfluentialYamada, Y., Shinkawa, K., Kobayashi, M., Takagi, H., Nemoto, M., Nemoto, K., & Arai, T. (2021) · Journal of Medical Internet Research · doi:10.2196/27667 · Cited by 12
“Using a combination of these features, previous studies [19-25 , At the same time, there is growing interest in using speech data that can be collected in everyday situations for applications in health care owing to the popularity of voice-based interaction systems such as voice assistants in smart…”
InfluentialExplainable Rumor Detection using Inter and Intra-feature Attention NetworksPreprint
Chen, M., Wang, N., & Subbalakshmi, K. P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.11057 · Cited by 12
“As mentioned earlier, we extracted three categories of features: content linguistic features [41], user features and latent features derived from the USE embedding of tweets and responses.”
MethodCombining Prosodic, Voice Quality and Lexical Features to Automatically Detect Alzheimer's DiseasePreprint
Farrús, M., & Codina, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.09272 · Cited by 17
“Although several works have focused on the automatic detection and classification of AD [9, 10], this field still suffers of a lack of standardisation.”
BackgroundMachine Learning Applications for IoT Healthcare
Agarwal, N., Singh, P., Singh, N., Singh, K. K., & Jain, R. (2021) · Wiley eBooks · doi:10.1002/9781119761884.ch6 · Cited by 13
An approach for assisting diagnosis of Alzheimer's disease based on natural language processing
Liu, N., & Wang, L. (2023) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2023.1281726 · Cited by 10
Coppieters, R., Bouzigues, A., Jiskoot, L. C., Montembeault, M., Tee, B. L., Rohrer, J. D., Bruffaerts, R., Russell, L. L., Foster, P. H., Ferry‐Bolder, E., et al. (2024) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2024.105909 · Cited by 15
MacPherson, Y., & Pham, K. (2020) · Springer eBooks · doi:10.1007/978-3-030-47994-7_22 · Cited by 9
“The results can mean the development of tools that can exacerbate inequalities, such as tech that can only detect Alzheimer’s (Fraser et al. 2016) in native English speakers.”
BackgroundZhou, D., Yuan, J., & Si, J. (2021) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2021.102119 · Cited by 12
A Comparison of Speech Features between Mild Cognitive Impairment and Healthy Aging Groups
Kim, K. W., Na, S., Chung, Y., & Shin, B. (2021) · Dementia and Neurocognitive Disorders · doi:10.12779/dnd.2021.20.4.52 · Cited by 12
Novel Framework for Alzheimer Early Diagnosis using Inductive Transfer Learning Techniques
Sahu, H. K., Kumar, S., Alsamhi, S. H., Chaube, M. K., & Curry, E. (2022) · International Conference on Emerging Smart Technologies and Applications (eSmarTA) · doi:10.1109/esmarta56775.2022.9935379 · Cited by 9
“Accuracy Precision Recall F1-Score [14] 0.”
ResultInfluentialEffectiveness of Mental Health Care by Using Machine Learning on Manufacturing Worker
Lim, J., Lee, S., Noh, J., Lee, W., Su, P., & Yoon, Y. (2023) · International Journal of Precision Engineering and Manufacturing-Smart Technology · doi:10.57062/ijpem-st.2023.0066 · Cited by 9
Robin, J., Xu, M., Kaufman, L. D., Simpson, W. S., McCaughey, S. M., Tatton, N. A., Wolfus, C., & Ward, M. E. (2023) · Cognitive and Behavioral Neurology · doi:10.1097/wnn.0000000000000356 · Cited by 10
TaghiBeyglou, B., & Rudzicz, F. (2023) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100046 · Cited by 18
Self-citationLü, W., Zhang, M., Yu, W., Kuang, W., Chen, L., Zhang, W., Yu, J., & Lü, Y. (2023) · BMJ Open · doi:10.1136/bmjopen-2023-073011 · Cited by 10
Propositional density: cognitive impairment and aging
Harrag, C., Sabil, A., Conceição, M. C., & Radvansky, G. A. (2024) · Frontiers in Psychology · doi:10.3389/fpsyg.2024.1434506 · Cited by 9
“For example, Mitzner and Kemper (2003) and Fraser et al. (2016) noted that Alzheimer’s disease impacts different brain regions, causing heterogeneity in language samples.”
BackgroundResultAdvanced speech biomarker integration for robust Alzheimer’s disease diagnosis
Hallani, A. E., Chakhtouna, A., & Adib, A. (2025) · Annals of Telecommunications · doi:10.1007/s12243-025-01073-5 · Cited by 12
“These features often include prosodic elements (e.g., pitch, intensity, speech rate), spectral characteristics (e.g., formants, Mel-frequency cepstral coefficients (MFCC)), and voice quality measures (e.g., jitter, shimmer, harmonic-to-noise ratio (HNR)) [21, 24].”
InfluentialPredicting Prodromal Dementia Using Linguistic Patterns and Deficits
Alkenani, A. H., Li, Y., Xu, Y., & Zhang, Q. (2020) · IEEE Access · doi:10.1109/access.2020.3029907 · Cited by 12
“Linguistic features have widely been employed to reveal dementia stages in previous studies [23], [30], [38], [53]–[56]; nevertheless, our study focused on one linguistic perspective that is lexicosyntactic features as being recommended for further inves-”
MethodSelecting and Analyzing Speech Features for the Screening of Mild Cognitive Impairment
Yang, Q., Xu, F., Ling, Z.-H., Li, X., Li, Y., & Fang, D. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9630752 · Cited by 10
Sabra, S., Malik, K. M., & Alobaidi, M. (2017) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac.2017.34 · Cited by 9
“We found only two studies [19, 20] that focused on linguistic features from clinical narratives.”
BackgroundHuang, L., Liu, Z., & Li, Y. (2022) · Clinical Linguistics & Phonetics · doi:10.1080/02699206.2022.2092423 · Cited by 10
“Based on this characteristic many researchers have used picture descriptive discourse to study language impairment features which are hypothesised to be affected by working memory and semantic memory limitations in AD (Dijkstra et al., 2002; Fraser et al., 2016; Van Petten et al., 1999).”
BackgroundTang, L., Zhang, Z., Feng, F., Yang, L., & Li, H. H. (2023) · Dementia and Geriatric Cognitive Disorders · doi:10.1159/000531818 · Cited by 13
Modality fusion using auxiliary tasks for dementia detection
Shao, H., Pan, Y., Wang, Y., & Zhang, Y. (2025) · Computer Speech & Language · doi:10.1016/j.csl.2025.101814 · Cited by 9
Predicting Cognitive Decline: A Multimodal AI Approach to Dementia Screening from Speech
Chi, L., Sharma, A., Gebhardt, A., & Colonel, J. T. (2025) · IEEE International Conference on AI and Data Analytics (ICAD) · doi:10.1109/icad65464.2025.11114053 · Cited by 13
“Fraser et al. achieved 81-82% accuracy on the DementiaBank dataset using lexical and syntactic features [23].”
Orimaye, S. O., Goodkin, K., Riaz, O. A., Salcedo, J.-M. M., Al-Khateeb, T., Awujoola, A. O., & Sodeke, P. O. (2020) · PLoS ONE · doi:10.1371/journal.pone.0229460 · Cited by 9
“For example, the efficacy of the Wechsler Logical Memory (WLM) I and II, which are two of the five different subtests of the Wechsler Memory Scale (WMS) [23], have been reported by some researchers to independently screen MCI-AD patients through a narrative task [6, 15, 24].”
BackgroundMethodLoizou, C. P. (2021) · Speech Communication · doi:10.1016/j.specom.2021.04.001 · Cited by 10
ML-Based Analysis to Identify Speech Features Relevant in Predicting Alzheimer's Disease
Kumar, Y., Maheshwari, P., Joshi, S., & Baths, V. (2022) · International Conference on Computing and Artificial Intelligence (ICCAI) · doi:10.1145/3532213.3532244 · Cited by 10
The Generalizability of Longitudinal Changes in Speech Before Alzheimer’s Disease Diagnosis
Petti, U., Baker, S., Korhonen, A., & Robin, J. (2023) · Journal of Alzheimer s Disease · doi:10.3233/jad-220847 · Cited by 13
Smartwatch-derived Acoustic Markers for Deficits in Cognitively Relevant Everyday Functioning
Yamada, Y., Shinakwa, K., Kobayashi, M., Nemoto, M., Ota, M., Nemoto, K., & Arai, T. (2023) · IEEE International Conference on Digital Health (ICDH) · doi:10.1109/icdh60066.2023.00015 · Cited by 11
“These acoustic features were determined on the basis of previous studies on Alzheimer's disease and related neurological disorders [35,36,49,52].”
BackgroundMethodInfluentialLinguistic-based Mild Cognitive Impairment detection using Informative Loss
Fard, A. P., Mahoor, M. H., Alsuhaibani, M., & Dodge, H. H. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108606 · Cited by 14
Predicting Early Indicators of Cognitive Decline from Verbal Utterances
Padhee, S., Illendula, A., Sadler, M., Shalin, V. L., Banerjee, T., Thirunarayan, K., & Romine, W. L. (2020) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm49941.2020.9313106 · Cited by 10
“used both linguistic and acoustic features and achieved an accuracy of over 81% in distinguishing individuals with AD (combining possible AD and probable AD) from those without AD (elderly controls) [7], we treat samples of possible AD and probable AD separately.”
Cognitive Internet of Things (IoT) and computational intelligence for mental well-being
Thapa, S., Ghimire, A., Adhikari, S., Bhoi, A. K., & Barsocchi, P. (2022) · Elsevier eBooks · doi:10.1016/b978-0-323-85751-2.00004-9 · Cited by 13
García, S. D. L. F., Haider, F., & Luz, S. F. (2020) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc44109.2020.9176305 · Cited by 11
“Although the comprehensive model by [8] included acoustic features, only two recent studies have relied exclusively on audio recordings from the Pitt Corpus , and used them to train a classifier for AD detection.”
MethodInfluentialAn Automatic System for Dementia Detection using Acoustic and Linguistic Features
González-Atienza, M., Peinado, A. M., & González, J. A. (2021) · IberSPEECH · doi:10.21437/iberspeech.2021-56 · Cited by 9
“[16] studied the potential of using linguistic features to identify Alzheimer’s disease.”
BackgroundMethodInfluentialRobustness and Sensitivity of BERT Models Predicting Alzheimer’s Disease from Text
Novikova, J. (2021) · Workshop on Noisy User-generated Text (W-NUT) · doi:10.18653/v1/2021.wnut-1.37 · Cited by 15
Bittner, D., Frankenberg, C., & Schröder, J. (2022) · Brain Sciences · doi:10.3390/brainsci12010121 · Cited by 12
Kesler, S. R., Henneghan, A. M., Thurman, W., & Rao, V. (2022) · JMIR Cancer · doi:10.2196/34828 · Cited by 8
(2017) · doi:10.18653/v1/w17-23 · Cited by 8
Classification and diagnosis model for Alzheimer’s disease based on multimodal data fusion
Fu, Y., Xu, L., Zhang, Y., Zhang, L., Zhang, P. F., Cao, L., & Jiang, T. (2024) · Medicine · doi:10.1097/md.0000000000041016 · Cited by 9
Leveraging Multimodal Methods and Spontaneous Speech for Alzheimer’s Disease Identification
Gao, Y., Guo, L. Y., & Liu, H. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10887657 · Cited by 7
“Existing speech-based methods typically extract acoustic and linguistic features from spontaneous speech for automated diagnosis [2].”
Automated Speech Markers of Alzheimer Dementia: Test of Cross-Linguistic Generalizability
Pérez-Toro, P. A., Ferrante, F. J., Pérez, G. N., Tee, B. L., Deleon, J., Nöth, E., Schuster, M. E., Maier, A., Slachevsky, A., Gorno‐Tempini, M. L., et al. (2025) · Journal of Medical Internet Research · doi:10.2196/74200 · Cited by 14
“One involves targeting heterogeneous feature sets that mix domains known to be affected (eg, semantics) and often spared (eg, morphosyntax) in AD [8,18,19].”
Multi-modal data analysis for early detection of alzheimer’s disease and related dementias
Wang, L., Glass, J. R., Kourtis, L. C., & Au, R. (2025) · The Journal of Prevention of Alzheimer s Disease · doi:10.1016/j.tjpad.2025.100399 · Cited by 10
“Fraser et al. (2016), using a computational approach with 370 linguistic and acoustic features, achieved up to 82 % accuracy in classifying AD versus controls from picture descriptions [21].”
Speech and language in healthy ageing and Alzheimer’s dementia
García, A. M. (2026) · Nature Reviews Psychology · doi:10.1038/s44159-026-00553-2 · Cited by 12
“Discourse production in Alzheimer’s dementia is also typified by reduced informativeness and coherence 90,134 , and both patterns worsen in proportion to executive and memory dysfunction 134,135 and with disease progression 136 .”
Influential
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.