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 401–500 of 800
Phonological and semantic strategies in a letter fluency task for people with Alzheimer’s disease
Park, J., Yoo, Y. R., Lim, Y., & Sung, J. E. (2022) · Frontiers in Psychology · doi:10.3389/fpsyg.2022.1053272 · Cited by 7
Language patterns in Japanese patients with Alzheimer disease: A machine learning approach
Momota, Y., Liang, K., Horigome, T., Kitazawa, M., Eguchi, Y., Takamiya, A., Goto, A., Mimura, M., & Kishimoto, T. (2022) · Psychiatry and Clinical Neurosciences · doi:10.1111/pcn.13526 · Cited by 11
“18,19,29,30 Although such quantitative analyses suggest the presence of useful clinical markers, conventional analyses of discourse require somewhat labor-intensive processes and examiner ’ s judgments, which could cause evaluative inconsistencies.”
BackgroundMethodResultInfluentialLearning implicit sentiments in Alzheimer's disease recognition with contextual attention features
Liu, N., Yuan, Z., Chen, Y., Liu, C., & Wang, L. (2023) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2023.1122799 · Cited by 9
“Fraser et al. (2016) extracted 42 mel-frequency cepstral coefficient (MFCC) features ( Chen et al., 2014) from Pitt datasets and is the first study to carry out an acoustic-prosodic analysis.”
MethodAutomatic selection of spoken language biomarkers for dementia detection
Ke, X., Mak, M., & Meng, H. M. L. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.10.018 · Cited by 10
Atypical cortical hierarchy in Aβ-positive older adults and its reflection in spontaneous speech
He, R., Al‐Tamimi, J., Sánchez‐Benavides, G., Montaña-Valverde, G., Gispert, J. D., Grau‐Rivera, O., Suárez‐Calvet, M., Minguillón, C., Fauria, K., Navarro, A., et al. (2024) · Brain Research · doi:10.1016/j.brainres.2024.148806 · Cited by 8
“…speech parameters at the acoustic-prosodic level, which require no transcription, have been shown to have high potential to accurately detect AD (Fraser et al., 2015), MCI (Fraser et al., 2019), and even earlier stages such as people at risk of AD with subjective cognitive decline (SCD) (He et…”
BackgroundDutta, M., Mello, T. M. D., Cheng, Y., Dash, N. S., Nandi, R., Dutt, A., & Bose, A. (2024) · Journal of Speech Language and Hearing Research · doi:10.1044/2024_jslhr-23-00254 · Cited by 11
Kleiman, M. J., & Galvin, J. E. (2024) · Journal of Alzheimer s Disease · doi:10.1177/13872877241291239 · Cited by 14
“Keywords : Mild cognitive impairment, speech behavior, neuropsychological assessment, machine learning”
Identification of Alzheimer’s Disease using Non-linguistic Audio Descriptors
Bhat, C. G., & Kopparapu, S. K. (2019) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2019.8903138 · Cited by 10
“Earlier works used manual transcriptions to obtain linguistic features from dementia speech to classify into dementia stages [4], [5], recent works use automatic speech recognition to obtain the lexical and semantic features for this purpose [6], [7].”
MethodInfluentialA Novel Screening System for Alzheimer’s Disease Based on Speech Transcripts Using Neural Network
Hong, S.-Y., Yao, L.-H., Cheah, W.-T., Chang, W., Fu, L., & Chang, Y. (2019) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2019.8914628 · Cited by 9
“extracted 370 features, including syntactic and acoustics features, to capture a wide range of linguistic phenomena[11].”
BackgroundBedi, A., Masri, M. K. A., Hennawi, H. A., Qadir, S., & Ottman, P. (2023) · Cureus · doi:10.7759/cureus.35941 · Cited by 13
“Natural language processing techniques have been shown to be promising in identifying suspected Alzheimer's disease by performing linguistic analysis of short samples of patients' speech and language [10].”
BackgroundAlhassan, S., Alrajhi, W., Alhassan, A., & Almuhrij, A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-58562-8_3 · Cited by 7
Combining data mining and text mining for detection of early stage dementia:the SAMS framework
Bull, C., Asfiandy, D., Gledson, A., Mellor, J., Couth, S., Stringer, G., Rayson, P., Sutcliffe, A., Keane, J. A., Zeng, X., et al. (2016) · Lancaster EPrints (Lancaster University) · Cited by 7
Towards AI-powered Language Assessment ToolsPreprint
Parsapoor, M., Alam, M. R., & Mihailidis, A. (2021) · Research Square · doi:10.21203/rs.3.rs-246079/v1 · Cited by 10
Clinical translation of fluid, imaging, and digital biomarkers for Alzheimer’s disease
Bacci, J. R., Karagianni, S., Alexopoulou, Z.-S., Moukaled, S., Tato-Fernández, C., Arunachalam, P., Aslanyan, A., Aye, S., Rocha, A. S. L., Crugel, M., et al. (2026) · Alzheimer s Research & Therapy · doi:10.1186/s13195-025-01921-5 · Cited by 11
“Linguistically, word finding difficulties are a core characteristic [263, 264] along with simplified syntax [265] and reduced grammatical complexity [266].”
Speech error rates after a sports-related concussion
Patel, S. A., Grabowski, C., Dayalu, V. N., & Testa, A. J. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1135441 · Cited by 8
Fusion of Low-Level Descriptors of Digital Voice Recordings for Dementia Assessment
Karjadi, C., Xue, C., Cordella, C., Kiran, S., Paschalidis, I. C., Au, R., & Kolachalama, V. B. (2023) · Journal of Alzheimer s Disease · doi:10.3233/jad-230560 · Cited by 6
Kong, A. P., Cheung, R. T. H., Wong, G. H. Y., Choy, J. C. P., Dai, R., & Spector, A. E. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1124477 · Cited by 7
Language and Communication Interventions in People with Alzheimer’s Disease: A Systematic Review
Dimitriou, N., Νούσια, Α., Georgopoulou, E.-N., Μαρτζούκου, Μ., Liampas, I., Dardiotis, E., & Nasios, G. (2024) · Healthcare · doi:10.3390/healthcare12070741 · Cited by 7
“The domain of syntax consists of acceptable sentences regarding simple, common, and automated forms, but grammatical and syntactic difficulties emerge in more complex structures at early stages [12,15]; sentence comprehension deficits vary with the degree of dementia severity [16].”
BackgroundOrtiz-Pérez, D., Benavent-Lledó, M., Garcia-Rodriguez, J., Tomás, D., & Vizcaya-Moreno, M. F. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113787 · Cited by 7
“These psycholinguistic features have proven to be relevant in Alzheimer’s recognition [230].”
Towards early prediction of Alzheimer's disease through language samples
Meltzer, J. A. (2020) · EClinicalMedicine · doi:10.1016/j.eclinm.2020.100644 · Cited by 7
Self-citationCurcic, J., Vallejo, V., Sorinas, J., Sverdlov, O., Præstgaard, J., Piksa, M., Deurinck, M., Erdemli, G., Bügler, M., Tarnanas, I., et al. (2022) · JMIR Research Protocols · doi:10.2196/35442 · Cited by 11
“eye tracking while reading and voice analytics of conventional picture description tests may provide direct physiological assessments of cognition, which may increase sensitivity [30-37]; and AR or virtual reality testing may introduce more real-life assessments in a clinical setting [50,51].”
BackgroundResultGong, X., Wong, P. C. M., Fung, H. H.-L., Mok, V., Kwok, T. C. Y., Woo, J., Wong, K. H., & Meng, H. M. L. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph192013302 · Cited by 8
Igarashi, T., Umeda‐Kameyama, Y., Kojima, T., Akishita, M., & Nihei, M. (2023) · Frontiers in Medicine · doi:10.3389/fmed.2023.1145314 · Cited by 6
“Fraser et al. performed an image description task on mildly cognitively impaired ( n = 37) and normal ( n = 37) participants.”
MethodInfluentialVita, D. D., Sagliano, L., & Trojano, L. (2023) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2023.105277 · Cited by 10
BlaBla: Linguistic Feature Extraction for Clinical Analysis in Multiple Languages
Shivkumar, A., Weston, J., Lenain, R., & Fristed, E. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2880 · Cited by 11
Eyre, B., Balagopalan, A., & Novikova, J. (2020) · Workshop on Noisy User-generated Text (W-NUT) · doi:10.18653/v1/2020.wnut-1.25 · Cited by 8
Static vs. Dynamic Modelling of Acoustic Speech Features for Detection of Dementia
Syed, M. S. S., Syed, Z. S., Pirogova, E., & Lech, M. (2020) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2020.0111082 · Cited by 6
“[14] computed a large number of features to capture linguistic phenomena, such as grammar constituents, information content, part-of-speech, psycholinguistics, the richness of vocabulary, and the syntactic complexity of speech transcripts.”
BackgroundDevelopment of Thai Picture Description Task for Alzheimer’s Screening using Part-of-Speech Tagging
Sangchocanonta, S., Vongsurakrai, S., Sroykhumpa, K., Ellermann, V., Munthuli, A., Anansiripinyo, T., Onsuwan, C., Hemrungrojn, S., Kosawat, K., & Tantibundhit, C. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9629861 · Cited by 11
“with the improvement of computational linguistic tools has opened a way to new diagnostic methods such as Automated Spontaneous Speech Analysis (ASSA) as well as Spontaneous Speech (SS) [9].”
MethodGoing Beyond the Cookie Theft Picture Test: Detecting Cognitive Impairments Using Acoustic Features
Braun, F. M., Erzigkeit, A., Lehfeld, H., Hillemacher, T., Riedhammer, K., & Bayerl, S. P. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16270-1_36 · Cited by 15
“[16,13,2,15,20] obtained convincing results on spontaneous speech of the CTP from the BDAE.”
ResultClear Speech: Technologies that Enable the Expression and Reception of Language
Rudzicz, F. (2016) · Synthesis lectures on assistive, rehabilitative, and health-preserving technologies · doi:10.2200/s00672ed1v01y201509arh008 · Cited by 6
Self-citationLuo, M., Neysari, M., Schneider, G., Martin, M., & Demiray, B. (2020) · The Journals of Gerontology Series B · doi:10.1093/geronb/gbaa041 · Cited by 6
de la Fuente Garcia, S., Ritchie, C. W., & Luz, S. (2020) · Journal of Alzheimer's Disease · doi:10.3233/jad-200888 · Cited by 5
“There are only 6 studies where not only the dataset, but also each experimental group contains 100 or more participants/speech samples [6, 9, 11, 85, 92, 95].”
BackgroundMethodInfluentialJiang, H. F., Chen, Z., Liu, Y., Yang, C., Yuan, X., & He, R. (2025) · PLoS ONE · doi:10.1371/journal.pone.0324270 · Cited by 13
“Across different domains in speech and language, impairments in the semantic domain are found to be among the most prominent [15,16] and to be powerful indicators for detecting cognitive decline in the AD spectrum [11].”
A Novel Approach to Mimic Linguistic Features of Transcripts of Atypical Speech
Mirbagheri, M., Saghir, H., & Chau, T. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3603921 · Cited by 6
“This step facilitated the encoding of sentence boundaries, as inter-sentence thematic coherence is important for detecting AD [43].”
InfluentialFlick, G., & Ostrand, R. (2025) · Journal of Speech Language and Hearing Research · doi:10.1044/2025_jslhr-24-00297 · Cited by 7
“…empty or indefinite words (Croisile et al., 1996; Ehrlich, Obler, & Clark, 1997; Hier et al., 1985; Nicholas et al., 1985), higher frequency words (Fraser et al., 2015; Kavé & Goral, 2018), and function words (Almor, Kempler, MacDonald, Andersen, & Tyler, 1999; Fraser et al., 2015; Hier et al.,…”
InfluentialLinguistic Markers in Spontaneous Speech: Insights into Subjective Cognitive Decline (Review)
Segkouli, S., Γκιόκα, Μ., Kokkas, S., Votis, K., Valero, S., Miguel, A., Antoniades, A., Charalambous, E., & Manias, G. (2025) · Healthcare · doi:10.3390/healthcare13222888 · Cited by 11
“Based on a number of studies, morphosyntactic processing remains mostly intact at first; nonetheless, individuals with AD make significantly more inflectional errors (mistakes with prefixes and suffixes that change a word’s form) than healthy older adults [25,28–31].”
Language biomarker screening using AI: a transdiagnostic approach to the brain
Themistocleous, C. K., & Stark, B. C. (2026) · Scientific Reports · doi:10.1038/s41598-025-34257-z · Cited by 8
“Automated language analysis is progressively recognized as a digital health tool 70,71 , yet its clinical translation is constrained by several critical gaps.”
Hallani, A. E., Chakhtouna, A., & Adib, A. (2025) · International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) · doi:10.1109/iraset64571.2025.11007957 · Cited by 6
“1) Mel-Frequency Cepstral Coefficients (MFCCs): MFCCs are by far the most commonly used acoustic features in speech processing [28]–[31].”
Yih, T., Yang, H. J., Huang, L., & Yao, Q. (2025) · Aphasiology · doi:10.1080/02687038.2025.2511217 · Cited by 6
“Some of these features were frequently utilized in previous research on cognitive decline detection, shown to be effective for reflecting syntactic competence and detecting cognitive decline (Fraser et al., 2016; Guinn et al., 2014; Orimaye et al., 2017).”
Transformer-Based Deep Learning Approaches for Speech-Based Dementia Detection: A Systematic Review
Mobtahej, P., Gouron, S., Javaheri, R., Le, D. N., El‐Khoury, A., Naing, T. H., & Sajjadi, S. A. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3595781 · Cited by 9
“Language problems including impairment in word retrieval [5], increased hesitation [6], decreased vocabulary richness [7], paucity of speech output [8], and erroneous spelling in writing [9] have long been known to be associated with cognitive impairment seen in dementia.”
Zhang, L., Ngo, A. D., Thomas, J., Burkhardt, H. A., Parsey, C. M., Au, R., & Ghomi, R. H. (2021) · Exploration of Medicine · doi:10.37349/emed.2021.00044 · Cited by 6
“Members of their research team expanded upon this by successfully using linguistic and audio features extracted from the Boston Cookie Theft task [10] to distinguish between controls and participants diagnosed with “possible” or “probable” AD [11].”
BackgroundMethodSpeech Analysis in Preclinical Identification of Alzheimer’s Disease
Ivanova, O., & Meilán, J. J. G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-06242-1_36 · Cited by 6
Karaboga, M., Frei, N., Ebbers, F., Rovelli, S., Friedewald, M., & Runge, G. (2022) · vdf Hochschulverlag AG an der ETH Zürich eBooks · doi:10.3218/4141-5 · Cited by 7
Reeves, S. M., Williams, V. J., Blacker, D., & Woods, R. L. (2022) · Neuropsychology · doi:10.1037/neu0000884 · Cited by 6
Lexical Diversity and Language Impairment
Zozuk, N. Č. (2023) · Journal of Linguistics/Jazykovedný casopis · doi:10.2478/jazcas-2023-0047 · Cited by 7
Augmenting word2vec with latent Dirichlet allocation within a clinical application
Budhkar, A., & Rudzicz, F. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1414 · Cited by 5
“Fraser et al. (2016) investigated multiple linguistic and acoustic characteristics and obtained accuracies up to 81% with aggressive feature selection.”
BackgroundSelf-citationShinkawa, K., & Yamada, Y. (2018) · PubMed Central · Cited by 11
Jarrold, W., Rofes, A., Wilson, S. M., Pressman, P., Stabler, E. P., & Gorno‐Tempini, M. (2020) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc44109.2020.9176185 · Cited by 5
“…number of studies have evaluated automated speech-based diagnosis of neurodegenerative disorders using a technology pipeline that includes automated acoustic-prosodic feature extraction, automated transcription, lexical feature extraction, and machine learning [7], [8], [9], [10], [11], [12], [13].”
BackgroundThaler, F., & Gewald, H. (2021) · Health Informatics - An International Journal · doi:10.5121/hiij.2021.10102 · Cited by 9
“Feature Types Roark [29], Khodabakhsh [30], Fraser [31], Gosztolya [32], Orimaye [33] Acoustic, Demographic, Linguistic López-de-Ipiña [34], Satt [35], Meilán [36], König [37], Al-Hameed [38], Christensen [39], Kato [40], Martínez-Sánchez [41], Tóth [42], Themistocleous [43], López [44], Chien [5],”
BackgroundInfluentialReading Fluency in Spanish Patients with Alzheimer’s Disease
Pérez‐Sánchez, M. D. C., González‐Nosti, M., Cuetos, F., Martínez, C., & Álvarez‐Cañizo, M. (2021) · Current Alzheimer Research · doi:10.2174/1567205018666210608102012 · Cited by 6
WDSAE-DNDT BASED SPEECH FLUENCY DISORDER CLASSIFICATION
Pravin, S. C., & Palanivelan, M. (2022) · Malaysian Journal of Computer Science · doi:10.22452/mjcs.vol35no3.3 · Cited by 6
The Discourse Profile in Corticobasal Syndrome: A Comprehensive Clinical and Biomarker Approach
de Almeida, I. J., Silagi, M. L., Carthery‐Goulart, M. T., Parmera, J. B., Cecchini, M. A., Coutinho, A. M., Brucki, S. M. D., Nitríni, R., & Schochat, E. (2022) · Brain Sciences · doi:10.3390/brainsci12121705 · Cited by 7
“Word-finding difficulties have been largely reported in studies of connected speech of clinical AD patients [23,25,26,29,70], as well as in confrontation naming tasks [71–73] and in the connected speech of lvPPA patients [25,32,74].”
ResultDesign and Validation of a System to Synchronize Speech Recognition and Eye-Tracking Measurements
Boulay, E., Wallace, B., Fraser, K., Kunz, M., Goubran, R. A., Knoefel, F. D., & Thomas, N. (2023) · IEEE Sensors Applications Symposium (SAS) · doi:10.1109/sas58821.2023.10254132 · Cited by 6
Self-citationLanguage in healthy and pathological ageing: Methodological milestones and challenges
Benítez‐Burraco, A., & Ivanova, O. (2023) · International Journal of Language & Communication Disorders · doi:10.1111/1460-6984.13003 · Cited by 7
Lust, B., Flynn, S., Henderson, C., Gair, J. W., & Sherman, J. C. (2023) · Journal of Neurolinguistics · doi:10.1016/j.jneuroling.2023.101190 · Cited by 7
Treviso, M., dos Santos, L. B., Shulby, C., Hübner, L. C., Mansur, L. L., & Aluísio, S. M. (2018) · Letras de Hoje · doi:10.15448/1984-7726.2018.1.30955 · Cited by 6
“…and tools aiming at the diagnosis of language-impairing dementias via machine learning methods are already available for the English language (FRASER et al., 2015a; yANCHEVA et al., 2015). yet a comprehensive NLP environment publicly available, designed for Brazilian Portuguese (BP), called…”
BackgroundMethodJerônimo, G. M. (2018) · Letras de Hoje · doi:10.15448/1984-7726.2018.1.28894 · Cited by 5
Scaling laws in natural conversations among elderly people
Abe, M., & Otake, M. (2021) · PLoS ONE · doi:10.1371/journal.pone.0246884 · Cited by 7
Rare-Class Dialogue Act Tagging for Alzheimer’s Disease Diagnosis
Nasreen, S., Hough, J., & Purver, M. (2021) · Annual Meeting of the Special Interest Group on Discourse and Dialogue · doi:10.18653/v1/2021.sigdial-1.32 · Cited by 12
“Many diagnosis classifi-cation models include some signals associated with non-understanding (e.g. Fraser et al., 2016; Broder-ick et al., 2018) but only as part of large general language feature sets.”
BackgroundDetection of Alzheimer’s Disease Through Speech Features and Machine Learning Classifiers
Gulapalli, A. S., & Mittal, V. K. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-16-6309-3_59 · Cited by 5
Alzheimer’s Disease and Speech Background
Land, W. H., & Schaffer, J. D. (2019) · Springer eBooks · doi:10.1007/978-3-030-18496-4_4 · Cited by 5
Biomarker potential of real-world voice signals to predict abnormal blood glucose levelsPreprint
Jeon, J., Palanica, A., Sarabadani, S., Lieberman, M., & Fossat, Y. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.09.25.314096 · Cited by 6
Cummings, L. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108587921 · Cited by 24
Liu, W., Jao, Y., Paudel, A., & Yoon, S. O. (2023) · BMC Geriatrics · doi:10.1186/s12877-023-04320-3 · Cited by 5
Gao, N., & He, Q. (2024) · Aphasiology · doi:10.1080/02687038.2024.2434858 · Cited by 5
“Nevertheless, some studies (e.g., Ahmed et al., 2012, 2013; Bose et al., 2021; Chapin et al., 2022; Fraser et al., 2016; Ivanova et al., 2023) also indicated that AD patients exhibited more variations in syntactic proficiency compared with the healthy control (HC) group.”
Zozuk, N. C., Munková, D., Kelebercová, L., & Munk, M. (2025) · Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring · doi:10.1002/dad2.70122 · Cited by 7
“22 In our study, the average text length was 120 words for the HC group and 77 words for the AD group, which may account for the non-significant noun/verb ratios ( p = 0.0621, p = 0.3838, respectively).”
InfluentialUnveiling 30 years of research on speech biomarker of dementia using text mining
Oh, C., & Park, M. S. (2025) · Digital Health · doi:10.1177/20552076251360901 · Cited by 5
“Similarly, Fraser et al. 36 claimed that supplementing standard screening protocols with computerized analysis of language patterns could lead to more accurate assessments.”
Yigamawano, F. K., Odom-Mabey, A. R., Xue, C., Pandey, H. K., & Kolachalama, V. B. (2025) · The Journal of Prevention of Alzheimer s Disease · doi:10.1016/j.tjpad.2025.100396 · Cited by 7
Benchmarking speech biomarkers of Alzheimer's against cognitive and neural measures
Caro, I., Pérez, G., Bize, J. V., Ponferrada, J., Ferrante, F. J., Welford, A. S., Gauder, L., Olavarría, L., Henríquez, F., Ramos, T. D. J. M., et al. (2026) · Alzheimer s & Dementia · doi:10.1002/alz.71365 · Cited by 5
“9,14,23,64 Importantly, reports of higher classification performance in the speech biomarker literature 8,65 are often based on uninterpretable features from large language models or complex embeddings.”
InfluentialYamada, Y., Shinkawa, K., Shimmei, K., Kim, H., Daly, R., Depp, C. A., Jeste, D. V., & Lee, E. (2022) · Aging & Mental Health · doi:10.1080/13607863.2022.2087207 · Cited by 5
“Furthermore, the trends for these individuals were consistent with those observed in individuals with cognitive impairments (Fraser et al., 2016; Kavé & Goral, 2016).”
ResultStamouli, S., Nerantzini, M., Papakyritsis, I., Katsamanis, A., Chatzoudis, G., Dimou, A., Plitsis, M., Katsouros, V., Varlokosta, S., & Terzi, A. (2023) · Frontiers in Communication · doi:10.3389/fcomm.2023.919617 · Cited by 4
“, 2014) and automatic Alzheimer’s Disease identification (Fraser et al., 2016).”
BackgroundCUSCO: An Unobtrusive Custom Secure Audio-Visual Recording System for Ambient Assisted Living
Albert, P., Haider, F., & Luz, S. F. (2024) · Sensors · doi:10.3390/s24051506 · Cited by 5
“62.0% acoustic yes Mirheidari et al. [42] 62.3% text yes (ASR) Fraser et al. [43] 81.9% text/acoustic no (text) Yancheva and Rudzicz [44] 80.0% text/acoustic no (text) Hernández et al. [41] 68.0% text no Mirheidari et al. [42] 75.6% text no”
BackgroundInfluentialWang, M., & Wang, M. (2024) · International Journal of Language & Communication Disorders · doi:10.1111/1460-6984.13023 · Cited by 5
Qi, K., Shi, J., Summerour, C. E., Batsis, J. A., & Liang, X. (2024) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/healthcom60970.2024.10880714 · Cited by 5
“Recent works show that linguistic and acoustic features are characteristics in automatically detecting cognitive decline [18], [19].”
BackgroundFusing Speech and Language Models for Dementia Detection
Deußer, T., Siddiqi, A. M., Sparrenberg, L., Adams, T., Bauckhage, C., & Sifa, R. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825055 · Cited by 6
“In the following sections, we first discuss related studies.”
InfluentialNtampakis, N., Diamantaras, K., Chouvarda, I., Tsolaki, M., Sarigianndis, P., & Argyriou, V. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05185-1_40 · Cited by 7
An automated speech analysis system for the detection of cognitive decline in elderly
Loizou, C. P., & Pantzaris, M. (2023) · International Journal of Speech Technology · doi:10.1007/s10772-023-10016-1 · Cited by 4
“Speech signal normalization and filtering were not conducted in any of the experiments listed in Table 1 (Beltrami et al., 2016; Fraser et al., 2016; Konig et al., 2018; König et al., 2015; Meilan et al., 2018; Meilán et al., 2014; Mueller et al., 2017; Rektorova et al., 2016; Roark et al., 2011), where CD was evaluat…”
MethodResultInfluentialPathogen infection in Alzheimer’s disease: pathophysiology and therapeutic strategies
Xiong, M., Yu, H., Tian, Y., Meng, L., & Zhang, Z. (2023) · Ageing and Neurodegenerative Diseases · doi:10.20517/and.2022.32 · Cited by 4
Using Machine Learning for Recognition of Alzheimer’s Disease Based on Transcription Information
Vishniakou, U. А., & Yu, C. Y. (2024) · Doklady BGUIR · doi:10.35596/1729-7648-2023-21-6-106-112 · Cited by 12
Yamada, Y., Shinkawa, K., Kosugi, A., Kobayashi, M., Takagi, H., Nemoto, M., Nemoto, K., & Arai, T. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-51057-2_19 · Cited by 5
Measuring Cognitive Status from Speech in a Smart Home Environment
Fraser, K., & Komeili, M. (2021) · IEEE Instrumentation & Measurement Magazine · doi:10.1109/mim.2021.9513645 · Cited by 5
Self-citationInvestigating non lexical markers of the language of schizophrenia in spontaneous conversations
Li, C., Amblard, M., Braud, C., Demily, C., Franck, N., & Musiol, M. (2021) · Workshop on Computational Approaches to Discourse (CODI) · doi:10.18653/v1/2021.codi-main.3 · Cited by 4
“…et al., 2014; Gun-tuku et al., 2019; Sekuli´c and Strube, 2019), post-traumatic stress disorder (Pedersen, 2015; Kleim et al., 2018), suicide risk (Benton et al., 2017), Alzheimer’s disease (Orimaye et al., 2014; Fraser et al., 2016), and autism (Goodkind et al., 2018; Sakishita et al., 2019).”
Cognitive Assessment of Japanese Older Adults with Text Data Augmentation
Igarashi, T., & Nihei, M. (2022) · Healthcare · doi:10.3390/healthcare10102051 · Cited by 7
Gkoumas, D., Purver, M., & Liakata, M. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.986 · Cited by 7
Siena, F. L., Vernon, M., Watts, P., Byrom, B., Crundall, D. E., & Breedon, P. (2020) · Journal of Medical Systems · doi:10.1007/s10916-020-01671-x · Cited by 4
Augmenting word2vec with latent Dirichlet allocation within a clinical applicationPreprint
Budhkar, A., & Rudzicz, F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.03967 · Cited by 4
“Fraser et al. (2016) investigated multiple linguistic and acoustic characteristics and obtained accuracies up to 81% with aggressive feature selection.”
BackgroundSelf-citationPersonalized Early Stage Alzheimer’s Disease Detection: A Case Study of President Reagan’s SpeechesPreprint
Wang, N., Peddagangireddy, V., Luo, F., Subbalakshmi, K. P., & Chandramouli, R. (2020) · medRxiv · doi:10.1101/2020.05.01.20087627 · Cited by 5
“8 percent accuracy in distinguishing AD patients from healthy controls using temporal and acoustic features ([8]; [9]).”
BackgroundAugmenting BERT Carefully with Underrepresented Linguistic FeaturesPreprint
Balagopalan, A., & Novikova, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.06153 · Cited by 5
“Prior work has shown that features relying on both of the above underrepresented properties are important for AD detection from picture descriptions (Fraser et al., 2016; Yancheva et al., 2015). Particularly, variations in proportions of various production rules from the constituency parse representation, depth of the…”
BackgroundInfluentialArtificial Intelligence in Bioinformatics
Raj, V. S., Priyadarshini, A., Yadav, M. K., Pandey, R. P., Gupta, A. A., & Vibhuti, A. (2021) · Wiley eBooks · doi:10.1002/9781119711278.ch2 · Cited by 5
Mo, T., Lam, J. C. K., Li, V. O. K., & Cheung, L. Y. L. (2024) · medRxiv · doi:10.1101/2024.08.22.24312463 · Cited by 21
Shankar, R., Chew, E., Bundele, A., & Mukhopadhyay, A. (2025) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2025.1581891 · Cited by 5
“Studies in Alzheimer’s disease and mild cognitive impairment have found that linguistic features extracted from spontaneous speech can predict cognitive status with high accuracy (Fraser et al., 2016; König et al., 2015; Beltrami et al., 2018).”
Tefera, E., Borges, H., Blewitt, C. O., Mansoor, A., Teerawanichpol, P., Peters, H. R., Rosenberg, A. M., Henin, S. E., Barr, W., Johnson, S. B., et al. (2025) · Neurology Open Access · doi:10.1212/wn9.0000000000000018 · Cited by 3
Sajjadi, S. A., Khan, Z., El‐Khoury, A., Bubbico, G., Akhlaghipour, G., Corrada, M. M., Kawas, C. H., & Paganini‐Hill, A. (2025) · Alzheimer s & Dementia · doi:10.1002/alz.70450 · Cited by 5
“…of connected speech analysis in detection of mild cognitive impairment and dementia and showed features such as reduced syntactic complexity, 26–28 impoverished semantic and lexical content, 26,28,29 reduced speech rate, 30 number of words, 31 discourse coherence, 32 and information content…”
Speech and language outcome measures in clinical trials of Alzheimer’s and Parkinson’s diseases
Berthier, M. L., Welford, A. S., Orozco‐Arroyave, J. R., López-Barroso, D., Torres‐Prioris, M. J., Dávila, G., & García, A. M. (2025) · Expert Review of Neurotherapeutics · doi:10.1080/14737175.2025.2600616 · Cited by 4
“When combined with other measures, syntactic features (mean length of sentences, T-units and clauses, and metrics extracted from parse tree) from narrative discourse contributed to identifying persons with AD with 81.92% accuracy [116].”
InfluentialApplication of Machine Learning in Mental Health
郑, 本. (2022) · Advances in Social Sciences · doi:10.12677/ass.2022.1111656 · Cited by 3
A Short Survey on Alzheimer's Disease: Recent Diagnosis and Obstacles
Thatere, A. B., Verma, P., Reddy, K. T. V., & Umate, L. (2023) · DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry (IDICAIHEI) · doi:10.1109/idicaiei58380.2023.10406885 · Cited by 3
Meyer, T., Favaro, A., Oh, E. S., Butala, A., Motley, C., Irazoqui, P. P., Dehak, N., & Moro-Velázquez, L. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109398 · Cited by 3
The effect of mild-stage Alzheimer’s disease on the acoustic parameters of voice
Sarımehmetoğlu, E. A., & Barmak, E. (2025) · The Egyptian Journal of Otolaryngology · doi:10.1186/s43163-025-00765-y · Cited by 6
Using Corrected ASR Projection to Improve AD Recognition Performance from Spontaneous Speech
Zhang, Y., Jin, Y., Chen, G., Ma, Y., Jia, M., & Song, P. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890111 · Cited by 5
“Textual feature-based approaches mainly leverage language models or manually extracted features such as semantics, sentence structure, grammar, and vocabulary [7].”
Everyday Language and Cognitive Functioning in Late Life
Zhang, S., Zhou, Z., Ng, Y. T., Muñoz, E., Li, J. J., & Fingerman, K. L. (2025) · The Journals of Gerontology Series B · doi:10.1093/geronb/gbaf084 · Cited by 4
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.