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 501–600 of 800
Divers, R. M., Cohen, A. S., Elvevåg, B., Chandler, C., Turner, R. S., Reynolds, B., & Diaz-Asper, C. M. (2025) · The Clinical Neuropsychologist · doi:10.1080/13854046.2025.2519827 · Cited by 3
“Many approaches to objectifying speech have been employed: incorporating acoustic (e.g., Meilán et al., 2014), syntactical (e.g., Fraser et al., 2016) and semantic (Petti et al., 2020) methods.”
Kokkinakis, D., Fors, K. L., Fraser, K., & Nordlund, A. (2018) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/2e42uqpk9g23 · Cited by 3
“This dataset has been used in various studies in the past, e.g. Fraser et al. (2016) achieved classification accuracies of over 81% in distinguishing between participants with AD and healthy controls by computing a number of linguistic variables from the transcripts, and acoustic variables from the…”
MethodSelf-citationMeta-Semantic Representation for Early Detection of Alzheimer’s Disease
Choi, J. D., Li, M., Goldstein, F. C., & Hajjar, I. M. (2019) · International Workshop on Designing Meaning Representations (DMR) · doi:10.18653/v1/w19-3309 · Cited by 5
“One approach includes linguistically motivated analysis extracting lexical, grammatical, and syntactic features to detect language deficits in AD patients (Fraser et al., 2016; Orimaye et al., 2017).”
BackgroundCummings, L. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108587921.001 · Cited by 4
Magnani, L., Carmisciano, L., Dell’Orletta⋄, F., Bettinardi, O., Chiesa, S., Imbesi, M., Limonta, G., Montagna, E., Turone, I., Martinasso, D., et al. (2023) · BMJ Open · doi:10.1136/bmjopen-2022-066642 · Cited by 4
A Survey of Bias in Healthcare: Pitfalls of Using Biased Datasets and Applications
Velichkovska, B., Denkovski, D., Gjoreski, H., Kalendar, M., & Osmani, V. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-35314-7_50 · Cited by 3
A Graph Machine Learning approach to Automatic Dementia Detection
Stoppa, E., Donato, G. W. D., Poles, I., D’Arnese, E., Parde, N., & Santambrogio, M. D. (2023) · IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...) · doi:10.1109/bhi58575.2023.10313453 · Cited by 3
“In the work by Fraser et al. [9], 370 different features derived from Part of Speech (POS) tags, syntax analysis, grammatical constituents, psycholinguistic analysis, vocabulary richness, and acoustic attributes were used in order to detect Alzheimer’s Disease.”
MethodSOK: Application of machine learning models in child and youth mental health decision-making
Daneshvar, H., Boursalie, O., Samavi, R., Doyle, T. E., Duncan, L., Pires, P., & Sassi, R. B. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-13671-9.00003-x · Cited by 5
Mekulu, K., Aqlan, F., & Yang, H. Y. (2025) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2025.1681124 · Cited by 5
“All preprocessing, parameter tuning, and evaluation procedures are described to ensure reproducibility.”
InfluentialPredicting Montreal Cognitive Assessment Scores From Measures of Speech and Language
Wisler, A. A., Fletcher, A. R., & McAuliffe, M. J. (2020) · Journal of Speech Language and Hearing Research · doi:10.1044/2020_jslhr-19-00183 · Cited by 7
Cummings, L. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108587921.002 · Cited by 3
Automated Evaluation of Standardized Dementia Screening Tests
Braun, F. M., Förstel, M., Oppermann, B., Erzigkeit, A., Lehfeld, H., Hillemacher, T., & Riedhammer, K. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10436 · Cited by 9
“[6, 9, 10, 11, 12] obtained convincing results on spontaneous speech of the CTPD from the BDAE.”
Contrast-enhanced Automatic Cognitive Impairment Detection System with Pause-encoder
Lin, S.-Y., Chang, H.-L., Wai, T., Fu, L., & Chang, Y. (2022) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53654.2022.9945085 · Cited by 3
“In order to address the problem, recent research typically involves different levels of information, including acoustic and linguistic information extracted from spontaneous speech and transcripts [6]–[8].”
BackgroundSpeech Recognition for Early Detecting Alzheimer’s Disease by Using Machine Learning Algorithms
MohamedShreif, H. O., & Lawgali, A. O. (2022) · International Conference on Engineering & MIS (ICEMIS) · doi:10.1109/icemis56295.2022.9914339 · Cited by 3
“The study in [17] considers language as an epiphenomenon of memory; they suggest that deterioration of language may be one of the foremost symptoms of Alzheimer's complaint which may appear either veritably beforehand during the complaint, or at an after stage of its elaboration [18].”
BackgroundJiang, J., Guoyu, Z. H. A. O., Yingbo, M. A., Ding, G., & Lanfang, L. I. U. (2023) · Advances in Psychological Science · doi:10.3724/sp.j.1042.2023.01002 · Cited by 3
Connected Multi-speech Task for Detecting Alzheimer’s Disease Using a Two-Layer Model
Peng, Z., Yang, J., Lei, N., Jing-yu, Y., Lan, M., & Gao, L. H. (2022) · International Symposium on Computer Science and Intelligent Control (ISCSIC) · doi:10.1109/iscsic57216.2022.00028 · Cited by 3
“Semantic impairments in AD are largely reflected in the vocabulary and content of people’s picture descriptions, which is one of the features that distinguishes the AD and nonAD groups[32], PD was used in the first stage to distinguish the AD from non-AD groups.”
MethodNoninvasive Detection of Alzheimer’s Disease from Conversational Speech Using 1D-CNN
Alex, J. S. R., Bhyri, R., Usha, G. P., & Arvind, S. V. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-8338-2_49 · Cited by 3
An Ensemble Machine Learning Algorithm To Diagnose Alzheimer's Disease
Begam, R. B., Palanivelan, M., & Preethi, S. (2023) · International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI) · doi:10.1109/raeeucci57140.2023.10134473 · Cited by 4
Interpretable Hierarchical Deep Learning Model for Noninvasive Alzheimer’s Disease Diagnosis
Zokaeinikoo, M., Kazemian, P., & Mitra, P. (2023) · INFORMS Journal on Data Science · doi:10.1287/ijds.2020.0005 · Cited by 3
Language Changes in Late-Onset Alzheimer’s Disease
Can, E., & Kuruoğlu, G. (2019) · PSYCHOLINGUISTICS · doi:10.31470/2309-1797-2019-25-2-50-68 · Cited by 5
“Several studies have found evidence for a decrease in the syntactic complexity of language in AD (Fraser et al., 2016).”
Early Diagnosis of Alzheimer's Disease Using Hybrid Word Embedding and Linguistic Characteristics
Li, Y. (2020) · International Conference on Algorithms, Computing and Artificial Intelligence (ACAI) · doi:10.1145/3446132.3446197 · Cited by 4
“[/] but (.) it’s a cat.”
Munthuli, A., Vongsurakrai, S., Anansiripinyo, T., Ellermann, V., Sroykhumpa, K., Onsuwan, C., Chutichetpong, P., Hemrungrojn, S., Kosawat, K., & Tantibundhit, C. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9630779 · Cited by 6
“This promising use of language features as a viable marker for AD combined with the improvement of powerful computational linguistic tools has resulted in new diagnostic methods such as the Automated Spontaneous Speech Analysis [12].”
MethodMizuguchi, D., Yamamoto, T., Omiya, Y., Endô, K., Tano, K., Oya, M., & Takano, S. (2023) · Journal of Aging Research and Lifestyle · doi:10.14283/jarlife.2023.12 · Cited by 4
Applications of Clinical Text Mining
Dalianis, H. (2018) · Springer eBooks · doi:10.1007/978-3-319-78503-5_10 · Cited by 3
Spontaneous spatial information provided by dementia patients and elderly controls in narratives
Bosse, S. (2019) · Proceedings of the Linguistic Society of America · doi:10.3765/plsa.v4i1.4463 · Cited by 3
Large-Scale Dialog Corpus Towards Automatic Mental Disease Diagnosis
Sakishita, M., Kishimoto, T., Takinami, A., Eguchi, Y., & Kano, Y. (2019) · Studies in computational intelligence · doi:10.1007/978-3-030-24409-5_10 · Cited by 3
Spontaneous Speech in Dementia
Джан, Е., & Kuruoğlu, G. (2019) · PSYCHOLINGUISTICS · doi:10.31470/2309-1797-2019-26-2-175-189 · Cited by 6
Communicating a diagnosis of dementia
Dooley, J. (2016) · Figshare · Cited by 5
Using NLP to analyze whether customer statements comply with their inner beliefPreprint
Thaler, F., Faußer, S., & Gewald, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.11175 · Cited by 3
“First introduced by Davis and Mermelstein (1980), MFCCs proved to be particularly promising and computationally efficient for recognizing patterns in speech (Dave 2013; Fraser et al. 2016; Gupta et al. 2018; Logan 2000).”
BackgroundChang, H.-L., Wai, T., Liao, Y.-S., Lin, S.-Y., Chang, Y., & Fu, L. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3540207 · Cited by 7
“For instance, Fraser et al. [11] extracted 370 features, including part-of-speech, syntactic complexity, vocabulary richness, and repetitiveness, to capture a wide range of linguistic characteristics.”
Graph Attention Networks With Dual-Edge Connectivity for Alzheimer’s Disease Detection From Speech
Hallani, A. E., Chakhtouna, A., & Adib, A. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3632821 · Cited by 3
“…for this set of features because they are both clinically interpretable and computationally compact, offering a balanced tradeoff between interpretability and performance compared to more complex alternatives such as raw spectrograms and deep embeddings, which may overfit small datasets [22], [36].”
Shao, Y., Mei, B., Tan, C., Huo, H., & Fang, T. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755536 · Cited by 5
“Research has shown its effectiveness in ASR [17], speaker verification[13, 43], and SER[19, 27, 37],where it efficiently allocates different experts to process prosodic, phonetic, and spectral features, outperforming conventional deep learning approaches.”
Li, J., Mao, L., Mao, X., Wang, Z., Wang, Z., & Ni, X. S. (2025) · JMIR Formative Research · doi:10.2196/79411 · Cited by 2
“Traditional feature engineering approaches for ADRD detection have relied on manually engineered features (eg, lexical diversity, syntactic complexity, and coherence from transcripts) and acoustic features (eg, pause duration, reaction time, loudness, and speech rate) [19-21, 23 , 26 , 27 ].”
Mekulu, K., Aqlan, F., & Yang, H. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1675103 · Cited by 2
PersonaDrift: A Benchmark for Temporal Anomaly Detection in Language-Based Dementia Monitoring
Lai, J., & Mihaildis, A. (2025) · International Conference on Machine Learning and Natural Language Processing (MLNLP) · doi:10.1109/mlnlp66797.2025.11387796 · Cited by 3
“Prior studies have identified early signs such as reduced lexical diversity, increased pronoun use, topic repetition, and semantic incoherence as indicators of cognitive decline [3], [4].”
DuoViT-AD: A dual-scale vision transformer for Alzheimer’s disease detection from brain MRI
Trigui, S., & Bezine, H. (2026) · Pattern Recognition Letters · doi:10.1016/j.patrec.2026.02.033 · Cited by 3
Blázquez-Folch, J., Calm, B., Hinojosa-Calleja, A., García‐Gutiérrez, F., Alegret, M., Muñoz, N., Cano, A. C., Fernández, M. V., Miguel, A., Solivar, A., et al. (2026) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2026.1816747 · Cited by 2
“…have demonstrated the utility of individual feature domains—including acoustic parameters (Xue et al., 2021), lexical and syntactic measures (Fraser et al., 2016; Pekkala et al., 2013), semantic and graph-based representations (Ambadi et al., 2021), and deep learning–based language…”
Digital Measures of Drawing Process to Predict Multiple Cognitive and Gait Measures in Older Adults
Yamada, Y., Kobayashi, M., Shinakwa, K., Nemoto, M., Ota, M., Nemoto, K., & Arai, T. (2024) · IEEE International Conference on Digital Health (ICDH) · doi:10.1109/icdh62654.2024.00042 · Cited by 3
Understanding Cohesion in Writings and Speech of Schizophrenia Patients
AlQahtani, A., Kayi, E. S., & Diab, M. (2019) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2019.00068 · Cited by 4
“identify people who suffer from: depression and anxiety [6]– [10], Alzheimers [11]–[13], post traumatic stress disorder (PTSD) [14], or schizophrenia [15]–[17].”
BackgroundPathological verbal repetition by Chinese elders with Dementia of Alzheimer’s Type
Zhu, L., & Huang, L. (2020) · East Asian Pragmatics · doi:10.1558/eap.38862 · Cited by 6
Sriskandaraja, K., Ahmed, B., & Valenzuela, M. (2020) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc44109.2020.9176157 · Cited by 2
“NCA finds a linear transform of the input dataset (distance metric in the k-NN algorithm) such that the leave-one-out (LOO) classification accuracy on the training set is maximized in the transformed space [9].”
BackgroundMueller, K. D. (2023) · Springer eBooks · doi:10.1007/978-3-031-45190-4_4 · Cited by 5
Enhancing Dysarthria Detection: Harnessing Ensemble Models and MFCC
Jothieswari, J., Valli, T. M. S., & Suguna, S. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-1329-5_11 · Cited by 2
Screening for Alzheimer's Disease in Mainland China Based on Syntax Impairment
Yang, Y., Liang, L., Gan, J., Shen, Y., Lu, Z., Shang, W., Ji, W., Cui, S., Feng, G., Ma, Y., et al. (2024) · International Conference on Asian Language Processing · doi:10.1109/ialp63756.2024.10661175 · Cited by 2
“They found that pronouns / (nouns + pronouns) and verbs / (nouns + verbs) could discriminate between speech samples from AD patients and healthy controls [18].”
BackgroundKang, J., Li, J., Li, J., Wu, X., & Meng, H. M. L. (2024) · International Symposium on Chinese Spoken Language Processing (ISCSLP) · doi:10.1109/iscslp63861.2024.10800483 · Cited by 5
Geng, M., Xie, X., Deng, J., Jin, Z., Li, G., Wang, T., Hu, S., Li, Z., Meng, H. M. L., & Liu, X. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3547217 · Cited by 10
“Xunying Liu is with the Chinese University of Hong Kong, China and the corresponding author (email: xyliu@se.cuhk.edu.hk). themselves in speech impairments [13], [14].”
Miura, K. W., Sekiguchi, T., Tokunaga, S., Sugimoto, H., Kishimoto, T., Kudo, T., & Otake, M. (2025) · BMC Geriatrics · doi:10.1186/s12877-025-06444-0 · Cited by 3
“Furthermore, linguistic features, including speech volume, tense, and vocabulary, have been used as screening measures for cognitive deficits such as MCI and dementia [10–12].”
Estimation of Dementia Severity Using SVM based on Patient's Engagement Levels in Conversation
Yamazaki, R., Nishio, S., Shigenobu, K., Maalouly, E., & Ishiguro, H. (2021) · IEEE International Conference on Intelligence and Safety for Robotics (ISR) · doi:10.1109/isr50024.2021.9419571 · Cited by 3
“By using multimodal features including linguistic and acoustic features from larger sample size based on the DementiaBank dataset, an approach to distinguishing AD from HC obtained classification accuracies of over 81% with logistic regression [25].”
MethodFandiño, J. C. R., & Salazar, A. M. (2021) · Revista Ciencias de la Salud · doi:10.12804/revistas.urosario.edu.co/revsalud/a.9877 · Cited by 5
Exploring MMSE Score Prediction Model Based on Spontaneous Speech
Sun, L., Zheng, J., Li, J., & Qian, C. (2022) · Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering · doi:10.18293/seke2022-062 · Cited by 2
Social Embodiment of Companion Robots in Smart Spaces: IoRT for Independent Living
Muema, C., Lawrence, S., Anjum, T., & Shabani, A. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-19650-8_8 · Cited by 2
Monroe, P., Halaki, M., Luscombe, G. M., Kumfor, F., & Ballard, K. J. (2023) · Brain Impairment · doi:10.1017/brimp.2022.32 · Cited by 3
“Deficits range from word finding difficulties, higher level language and pragmatic deficits, circuitous and empty speech, to adynamic aphasia and mutism (Fraser et al., 2016; Savage et al., 2013a; Shany-Ur et al., 2012).”
Backgroundde Medeiros, K. (2023) · Springer eBooks · doi:10.1007/978-3-031-20970-3_10 · Cited by 2
Kokkinakis, D., Fors, K. L., & Nordlund, A. (2016) · International Workshop on Health Text Mining and Information Analysis (LOUHI) · doi:10.18653/v1/w16-6104 · Cited by 4
“Finally Finally, Fraser et al. (2016) also looked at the Demen-tiaBank and using 240 samples of AD and 233 from healthy controls, extracted 370 features, such as linguistic variables from transcripts (e.g., part-of-speech frequencies; syntactic complexity and grammatical constituents), psycholinguistic measures (e.g.,…”
BackgroundMethodInfluentialTowards international standards for evaluating machine learning.
Rudzicz, F., Paprica, P. A., & Janczarski, M. (2019) · National Conference on Artificial Intelligence · Cited by 2
Self-citationPaulino, A., Sierra, G., da Cunha, I., & Hernández-Domínguez, L. (2020) · Revista signos · doi:10.4067/s0718-09342020000100242 · Cited by 6
Detecting a History of Repetitive Head Impacts from a Short Voice RecordingPreprint
Tauro, M. G., Ravanelli, M., & Droppelmann, C. A. (2021) · medRxiv · doi:10.1101/2021.09.20.21263753 · Cited by 3
Influence of ASR and Language Model on Alzheimer's Disease DetectionPreprint
Codina, J., Cámbara, G., Luque, J., & Farrús, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.15704 · Cited by 3
“[33] identifies several factors —acoustic abnormality and impairments in semantics, syntax and information— as linguistic markers in narrative speech to detect AD, and [34] uses readability features to assess AD.”
BackgroundMeyer, T., Favaro, A., Cao, T., Butala, A., Oh, E. S., Motley, C., Irazoqui, P. P., Dehak, N., & Moro-Velázquez, L. (2023) · medRxiv · doi:10.1101/2023.05.30.23290742 · Cited by 2
“Several works have focused on automatic extraction and quantification of clinically-relevant features from speech signals (e.g., zero-crossing rate, Mel-Frequency Cepstral Coe ffi cients, phonemic grouping) [32, 33] and speech transcriptions (e.g., lexical richness, parts-of-speech tags) [34, 35].”
BackgroundA Survey of Detection of Cognitive Impairment using Non-invasive Indicators
Karande, S. C., & Kulkarni, V. (2020) · International Journal of Computer Applications · doi:10.5120/ijca2020920043 · Cited by 1
Personalized Early Stage Alzheimer’s Disease Detection: A Case Study of President Reagan’s Speeches
Wang, N., Luo, F., Peddagangireddy, V., Subbalakshmi, K. P., & Chandramouli, R. (2020) · Workshop on Biomedical Language Processing (BioNLP) · doi:10.18653/v1/2020.bionlp-1.14 · Cited by 3
Radjenovic, S., Voracek, M., & Adler, G. (2020) · Psychiatrische Praxis · doi:10.1055/a-1207-1255 · Cited by 2
A Language-Based Approach for Predicting Alzheimer Disease Severity
Ammar, R. B., & BenAyed, Y. (2021) · Lecture notes in business information processing · doi:10.1007/978-3-030-75018-3_19 · Cited by 1
Judgment of Alzheemer’s Desease Based on Multi-feature Mixed Model
Li, H., Wei, Z., Yunqiang, D., Chen, C., Hu, L., & Yin, J. (2022) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai55851.2022.9904098 · Cited by 1
“After studying the current situation of Alzheimer's disease judgment, this paper found the dilemma faced by traditional detection methods in the current stage [16].”
BackgroundGenesis of Clinical Linguistics: Cognitive-Communication Disorders and Their Research Directions
Igisheva, L., Nechaeva, I. A., Александровна, Р. А., & Shot, Y. (2022) · Bulletin of Kemerovo State University Series Humanities and Social Sciences · doi:10.21603/2542-1840-2022-6-4-277-284 · Cited by 1
Early Detection of Alzheimer's Disease Using VOT Mean Measure in New Tunisian Arabic Database
Dabbabi, K., Kehili, A., & Cherif, A. (2023) · IEEE International Conference on Advanced Systems and Emergent Technologies (IC_ASET) · doi:10.1109/ic_aset58101.2023.10150580 · Cited by 1
“The works in [3], [4], [5], [6] are such studies that were carried out for this task.”
BackgroundMethodInfluentialPronoun use in preclinical and early stages of Alzheimer's dementia
Bittner, D., Frankenberg, C., & Schröder, J. (2023) · Computer Speech & Language · doi:10.1016/j.csl.2023.101573 · Cited by 4
Assessment of communication-related quality of life in individuals with Alzheimer’s disease
Karalı, F. S., Baydin, B., & Çınar, N. (2024) · Aphasiology · doi:10.1080/02687038.2024.2369247 · Cited by 1
“It is mentioned that patients may differ in expressing language impairment in different subdomains (Fraser et al., 2016).”
Rodríguez, A. S. (2024) · Círculo de lingüística aplicada a la comunicación · doi:10.5209/clac.87529 · Cited by 1
Connected speech profiles in mild cognitive impairment reflect global cognition
Pellerin, S., Houzé, B., Bedetti, C., Phillips, N. A., & Brambati, S. M. (2025) · Journal of Alzheimer s Disease · doi:10.1177/13872877251329615 · Cited by 1
“Different CS pro fi les have been documented in AD, 19,20 but no study has investigated potential CS pro fi les in MCI.”
Quantized Approximate Signal Processing (QASP): Towards Homomorphic Encryption for Audio
Nguyen, T. D., Lesage, A., Cantini, C., & Riad, R. (2026) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2026-14 · Cited by 1
Dörr, F., Grandjean, L., Tröger, J., & Peter, J. (2025) · Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring · doi:10.1002/dad2.70127 · Cited by 1
“26,32 However, semantic verbal fluency tasks are easy to administer, cost-effective, and suitable for settings where no MRI or PET scanner is available or where remote assessments are necessary.”
Guo, L. Z., Liu, H., Yang, H., Chen, H., Du, W., & Liu, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6960-8_19 · Cited by 3
Chen, J., Hao, C., Zhang, X., Zhu, W., Hou, S., An, J., Bao, W., Wang, Z., Du, S., Wang, Q., et al. (2025) · Journal of Alzheimer s Disease · doi:10.1177/13872877251350101 · Cited by 3
“10 15 – 17 However, it should be noted that they have largely been reported to serve as screening tools for patients with cognitive impairment or dementia, rather than MCI.”
Emerging Trends in Early Dementia Diagnosis: An Analysis on Advanced Machine Learning Approaches
Gami, B., Agrawal, M., & Katarya, R. (2025) · ACM Computing Surveys · doi:10.1145/3764578 · Cited by 4
“This approach has also provided ideal performance in MCI and AD with vocal tasks [40, 80].”
Abidin, A. Z., Ahmad, N. A., Zubir, Z., Othman, R., Ibrahim, N. N., & Hashim, A. A. (2025) · International Journal of Modern Education · doi:10.35631/ijmoe.726027 · Cited by 1
Wei, H. T., Kulzhabayeva, D., Erceg, L., Rose, M. K., Spencer, K. A., Robin, J., Bialystok, E., & Meltzer, J. A. (2025) · Journal of Speech Language and Hearing Research · doi:10.1044/2025_jslhr-24-00268 · Cited by 2
Self-citationMutala, V. S. B., Pouriyeh, S., Parizi, R. M., Xie, C. Y., Santopaolo, A., Basile, I., & Sannino, G. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229368 · Cited by 2
“Earlier work focuses on traditional acoustic features (e.g., speech rate) [20], traditional linguistic features (e.g., word frequency, repetitions) [21], and duration features [22].”
Pérez-Elvira, R., Oltra‐Cucarella, J., Juan, M. A., Polo-Ferrero, L., Díaz, M. Q., Bosch‐Bayard, J., Ruíz, A. S., Rashid, A. N. M. M. O., & Juárez‐Vela, R. (2026) · AI · doi:10.3390/ai7020069 · Cited by 2
“Computational analysis of natural language has enabled the quantification of subtle changes in the discourse of patients with dementia, identifying language-based biomarkers with both diagnostic and prognostic potential [22,23].”
InfluentialHow robust are linguistic markers of aging? The case of aging-related social media text
Cong, Y., Hu, J., Reese, T., & Liu, H. (2026) · Natural Language Processing Journal · doi:10.1016/j.nlp.2026.100203 · Cited by 1
Layer-wise analysis of Wav2Vec for early detection of cognitive decline
Talasila, S. L., & Rodda, V. (2026) · International Journal of Speech Technology · doi:10.1007/s10772-026-10253-0 · Cited by 1
“Linguistic features such as part-of-speech rates, Type-Token Ratio, Brunet’s Index, and Clause-like Semantic Units have been effective in evaluating Alzheimer’s sever - ity (Fraser et al., 2015), with closed-class words showing predictive value.”
Modir, A., Shalchizadeh, F., Ghasimi, A., & Shamekhi, S. (2025) · National and International Iranian Conference on Biomedical Engineering (ICBME) · doi:10.1109/icbme68496.2025.11392474 · Cited by 1
“K. C. Fraser et al. [15] analyzed speech recordings and their corresponding transcriptions from 240 individuals with AD and 233 healthy controls within the DementiaBank corpus.”
Multi-level language deficits in behavioural frontotemporal degeneration and related disorders
Deneve, A., Dubos, A. M., Tran, T. M., Renard, A., Carpentier, C., Forestier, N., Kuchcinski, G., Lopes, R., Amad, A., Lebouvier, T., et al. (2026) · Brain Communications · doi:10.1093/braincomms/fcag116 · Cited by 1
“24,25 Although they are an integral part of psychiatric symptomatology, with distinct patterns emerging across disorders, language abnormalities have been less systematically explored in psychiatry.”
Integrating acoustic, prosodic, and phonological features for automatic Alzheimer’s detection
Kurdi, M. Z. (2026) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2026.1786269 · Cited by 4
“Early evidence suggests that AD primarily aects lexical retrieval, which can manifest as word-finding diÿculties and reduced vocabulary richness (Kurdi, 2024a; Mirheidari et al., 2018; Fraser et al., 2016; Garrard et al., 2005; Hebert et al., 2000; Hier et al., 1985).”
Yoo, Y. R., Park, J., & Sung, J. E. (2026) · American Journal of Speech-Language Pathology · doi:10.1044/2026_ajslp-25-00422 · Cited by 1
Chen, X., Chen, J., Pan, X., Zhang, X., & Feng, S. (2026) · Humanities and Social Sciences Communications · doi:10.1057/s41599-026-07258-0 · Cited by 1
“Fraser et al. discovered that the manifestations of semantic impairment in AD patients include a reduced proportion of nouns, an increased proportion of pronouns, higher word frequency, and shorter word length (Fraser et al., 2015).”
InfluentialCunha, E. D., Manera, V., Chorin, F., Lemaire, J., Plonka, A., Mouton, A., Zory, R., & Gros, A. (2026) · The Journal of Prevention of Alzheimer s Disease · doi:10.1016/j.tjpad.2026.100573 · Cited by 1
“Connected speech, defined as continuous, naturalistic language production and ecological measure beyond isolated words or single ‑ sentence utterances , has emerged as a promising marker for dynamic profiling of neurodegenerative progressions [13 – 15].”
A Transformer-Based Multimodal On-Device AI System for Vulnerable Elderly Care in Aging Societies
Lee, L. J. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-26211-0_2 · Cited by 1
Sweidan, J., El‐Yacoubi, M. A., & Semmar, N. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114166 · Cited by 1
Madden, K. M., Feldman, B., Jimenez, D., Khokhar, M., Li, Q., Nguyen, M., & Zhu, J. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001444 · Cited by 1
“Although our hybrid model operated on learned text embeddings as opposed to hand-engineered linguistic features, prior work suggests that persons with Alzheimer’s disease exhibit reduced vocabulary richness, decreased semantic specificity, increased repetition and information impairment [42].”
Jinming, X., Kathiresan, T., Siddiqui, A., & Vogel, A. P. (2026) · Future Neurology · doi:10.1080/14796708.2026.2692075 · Cited by 1
Speech-to-Text-to-Graph: GCN-Based Alzheimer’s Detection from Narrative Transcripts
Hallani, A. E., Chakhtouna, A., Adib, A., & Saoudi, S. (2026) · International Symposium on Signal, Image, Video and Communications (ISIVC) · doi:10.1109/isivc69944.2026.11574159 · Cited by 1
“Typical cues include lexical richness, semantic density, syntactic complexity, empty speech, part-of-speech distributions, narrative coherence, and content-word usage [4], [5], [13].”
Mudar, R. A., Hadley, P. A., Baby, E., & Mahendra, N. (2026) · Topics in Language Disorders · doi:10.1097/tld.0000000000000390 · Cited by 1
Serban, A., Re, M. D., Lima, M. R. D., Amador, J., Arroyo, P. F., Harrison, M., True, J., Nilforooshan, R., Calvo, R. A., & Vaidyanathan, R. (2026) · JMIR Research Protocols · doi:10.2196/99729 · Cited by 1
Tavakoli, M., Dadgostar, M., Green, J. R., Salat, D. H., Arnold, S. E., Connaghan, K. P., Richburg, B. D., Barnett, N. V., Tkeshelashvili, M., & Eshghi, M. (2026) · JMIR Formative Research · doi:10.2196/89830 · Cited by 2
“Speech and language changes are increasingly recognized as early markers of AD pathology [14-16].”
Holvoet, P. (2021) · Springer eBooks · doi:10.1007/978-3-030-68844-8_10 · Cited by 1
Bednorz, A., Lach, E., & Seiffert, P. (2022) · Neuropsychiatria i Neuropsychologia · doi:10.5114/nan.2022.117959 · Cited by 3
Alzheimer’s Detection with Speech Using Singular Spectrum Analysis Trend Extraction Method
Liao, G.-Z., Ling, B. W., & Ho, C. Y. (2022) · International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP) · doi:10.1109/csndsp54353.2022.9907998 · Cited by 2
“The methods proposed in Reference [8] and Reference [12], they study subjects whose native language is not Chinese.”
BackgroundMethodSpeech Recognition Via Machine Learning in Recording Studio
Devi, M. R., Sarma, M. K., & Talukdar, J. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-1699-3_4 · Cited by 1
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.