Clinical Research

Detect the signs of dementia faster, more easily, and more objectively through speech with the help of artificial intelligence..

Work with us

Backed by clinical evidence

Linguistic features identify Alzheimer’s disease in narrative speech

Detecting Alzheimer’s disease

Analysis of spontaneous speech data elicited through Cookie Theft picture description (1-5 minute samples) from 240 people probable AD category and 233 healthy controls. Linguistic and acoustic variables used to train a machine learning classifier to distinguish between the groups, with 82% accuracy.

Fraser, K. C., Meltzer, J. A., & Rudzicz, F. (2016). Linguistic features identify Alzheimer’s disease in narrative speech. Journal of Alzheimer's Disease, 49(2), 407-422.
Using Linguistic Features Longitudinally to Predict Clinical Scores for Alzheimer's Disease and Related Dementias

Predicting MMSE for AD monitoring

A temporal Bayes network trained on 182 lexicosyntactic, 210 acoustic, and 85 semantic features extracted from 393 spontaneous speech samples elicited through Cookie Theft picture description can predict MMSE scores with a mean absolute error of 3.8, comparable to within-subject interrater (clinician) standard deviation of 3.9 to 4.8.

Yancheva, M., Fraser, K., & Rudzicz, F. (2015). Using Linguistic Features Longitudinally to Predict Clinical Scores for Alzheimer's Disease and Related Dementias.
Automated classification of primary progressive aphasia subtypes from narrative speech transcripts

Subtyping primary progressive aphasia

Syntactic and semantic features were automatically extracted from transcriptions of narrative speech for three groups: semantic dementia (SD), progressive nonfluent aphasia (PNFA), and healthy controls. Machine learning classifiers trained on these features were able to distinguish between the three participant groups with up to 100% accuracy.

Fraser, K.C., Meltzer, J.A., Graham, N.L., Leonard, C., Hirst, G., Black, S.E., & Rochon, E. (2014). Automated classification of primary progressive aphasia subtypes from narrative speech transcripts. Cortex, 55, 43-60.

Our technology

Drug development in Alzheimer's disease and dementia is hampered by our ability to identify at risk groups before the onset of clinically significant symptoms. Winterlight Labs is addressing this problem by pioneering a speech-based AI technology which could help accurately predict risk for dementia years before a clinical diagnosis is obtained. Our technology can help detect and monitor subtle changes in cognition by assessing individuals more frequently and more objectively than the assessments used today.

Image of ipad

Unique benefits

Image of checklist

Easy to administer

The assessment is fast and easy to administer: the patient only needs to describe a picture or recall words as instructed by an iPad. Traditional cognitive assessments like the MMSE and MoCA are stressful for the patient and can be undermined by learning effects. Our assessment however, is designed to be administered frequently (as often as monthly) giving a more granular picture of changes in cognition over time. As a result our assessment can be routinely completed to monitor cognitive health and track variables that might be impacted by treatment.

Image of graphed data

Automatic and objective scoring

The assessment can be completed objectively across patients and administrators. Standard cognitive assessments include components which are subjectively scored and often too coarse. We analyze hundreds of linguistic cues and vocal biomarkers to detect Alzheimer’s disease and other conditions with accuracies between 82% and 100%, as reported in our peer-reviewed academic studies.

Image of illuminated lightbulb

Discover Insights

Our analysis captures both the acoustic and lexical properties of speech to produce a set of over 500 variables. These variables are then grouped into aggregate metrics such word-finding difficulties, syntactic complexity, lexical richness, discourse mapping and more. They can be compared with an existing metric like an MMSE score.

Publications

Psychometric Approach to Speech Feature Analysis as an Objective Measure of Anxiety

DeSouza D., Xu M., Fidalgo C., Robin J., Simpson B. (2021)

Society of Biological Psychiatry (SOBP) Annual Meeting.

Read Read More
Up Caret

Comparing Pre-trained and Feature-Based Models for Prediction of Alzheimer's Disease Based on Speech

Balagopalan A., Eyre B., Robin J., Rudzicz F., Novikova J. (2021)

Frontiers in Aging Neuroscience.

Read Read More
Up Caret

Variation in speech and language variables based on demographic factors.

Robin J., Xu M., Simpson W. (2021)

International Society for CNS Clinical Trials and Methodology.

Read Read More
Up Caret

Analytical and clinical validation of digital language assessments.

Robin J., Xu M., Simpson W., Novikova J. (2021)

International Society for CNS Clinical Trials and Methodology.

Read Read More
Up Caret

Augmenting BERT Carefully with Underrepresented Linguistic Features

Balagopalan A., Novikova J. (2020)

Machine Learning for Health Workshop at NeurIPS 2020.

Read Read More
Up Caret

Remote assessment of speech and language changes in Primary Progressive Aphasia (PPA) and behavioral variant Frontotemporal Dementia (bvFTD).

Robin J., Xu M., Kaufman L.D., Hagey M., Paul R., Siddiqui O., Ward M., Simpson W. (2020)

Clinical Trials on Alzheimer’s Disease.

Read Read More
Up Caret

Evaluation of speech-based digital biomarkers for Alzheimer’s Disease.

Robin J., Kaufman L.D., Simpson W. (2020)

Clinical Trials on Alzheimer’s Disease.

Read Read More
Up Caret

Evaluation of Speech-Based Digital Biomarkers: Review and Recommendations.

Robin J., Harrison J.E., Kaufman L.D., Rudzicz F., Simpson W., Yancheva M. (2020)

Digital Biomarkers, 99–108.

Read Read More
Up Caret

Fantastic Features and Where to Find Them: Detecting Cognitive Impairment with a Subsequence Classification Guided Approach

Eyre B., Balagopalan A., Novikova J. (2020)

W-NUT Workshop on Noisy User-generated Text at EMNLP 2020.

Read Read More
Up Caret

Hepatic Encephalopathy is Associated with a Distinct Speech Pattern.

Bloom P.P., Arvind A., Daidone M., Robin J., Xu M., Gupta A.S., Chung R.T. (2020)

American Association for the Study of Liver Diseases: The Liver Meeting.

Read Read More
Up Caret

Gathering normative speech data for depression research remotely, using online task marketplaces.

Fidalgo C., Xu M., Balagopalan A., Robin J., Kaufman L.D., Simpson W. (2020)

International Society for CNS Clinical Trials and Methodology.

Read Read More
Up Caret

A comparison of clinician assessment of speech versus automated speech analysis in Mild Cognitive Impairment and Alzheimer’s Dementia.

Yeung A., Iaboni A., Rochon E., Lavoie M., Santiago C., Yancheva M., Novikova J., Xu M., Robin J., Kaufman L.D., Mostafa F. (2020)

Alzheimer’s Association International Conference.

Read Read More
Up Caret

Quality comparison of remote vs. in-person digital speech assessment for dementia.

Robin J., Novikova J., Sirotkin S., Yancheva M., Kaufman L.D., Simpson W. (2020)

Alzheimer’s Association International Conference.

Read Read More
Up Caret

Comparing longitudinal changes in speech-based digital measures in cognitively healthy, possible cognitive impairment, and MCI/AD individuals.

Robin J., Xu M., Kaufman L.D., Simpson W. (2020)

Alzheimer’s Association International Conference.

Read Read More
Up Caret

To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection

Balagopalan A., Eyre B., Rudzicz F., Novikova J. (2020)

Proceedings of INTERSPEECH 2020.

Read Read More
Up Caret

Assessment of ataxia using natural language processing and computational analysis of speech.

Simpson W., Kaufman L.D., Balagopalan A., Khan N.C., Gupta A.S. (2020)

Ataxia Investigators Meeting.

Read Read More
Up Caret

Tracking changes in cognition in Mild Cognitive Impairment and Alzheimer’s Disease over a 6-month period using a speech-based digital biomarker.

Robin J., Simpson W., Kaufman L.D. (2020)

International Society for CNS Clinical Trials and Methodology.

Read Read More
Up Caret

Pause-Focussed Sequential Modelling for Predicting Cognitive Impairment on Limited Data

Eyre B., Balagopalan A., Novikova J. (2019)

Machine Learning for Health Workshop at NeurIPS 2019.

Read Read More
Up Caret

Evaluating a method for automatic and objective scoring of verbal response for the Montreal Cognitive Assessment (MoCA).

Kaufman L.D., Balagopalan A., Novikova J., Mostafa F. (2019)

Clinical Trials on Alzheimer’s Disease.

Read Read More
Up Caret

Early development of a unified, speech and language composite to assess the clinical severity of Frontotemporal Lobar Degeneration (FTLD).

Balagopalan A., Kaufman L.D., Novikova J., Siddiqui O., Paul R., Ward M., Simpson W. (2019)

Clinical Trials on Alzheimer’s Disease.

Read Read More
Up Caret

Cross-Language Aphasia Detection using Optimal Transport Domain Adaptation

Balagopalan A., Novikova J., McDermott M. B. A., Nestor B., Naumann T., Ghassemi M. (2019)

Machine Learning for Health Workshop at NeurIPS 2019.

Read Read More
Up Caret

Comparing a speech-based digital biomarker to the Montreal Cognitive Assessment (MoCA) for tracking cognition over a 6-month period in a naturalistic cohort of older adults.

Simpson W., Balagopalan A., Kaufman L.D., Yancheva M. (2019)

Clinical Trials on Alzheimer’s Disease.

Read Read More
Up Caret

Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power

Novikova J., Balagopalan A., Shkaruta K., Rudzicz F. (2019)

W-NUT Workshop on Noisy User-generated Text at EMNLP 2019.

Read Read More
Up Caret

Use of a voice-based digital biomarker in patients with depression.

Simpson W., Balagopalan A., Kaufman L.D., Yeung A., Butler A (2019)

International Society for CNS Clinical Trials and Methodology.

Read Read More
Up Caret

Utility of speech-based digital biomarkers for evaluating disease progression in clinical trials of Alzheimer’s disease.

Simpson W., Kaufman L.D., Detke M., Lynch S., Butler A., Dominy A. (2019)

Alzheimer’s Association International Conference.

Read Read More
Up Caret

Comparison of a speech-based digital biomarker with the MoCA in a naturalistic cohort of seniors.

Simpson W., Kaufman L.D., Balagopalan A., Novikova J. (2019)

Alzheimer’s Association International Conference.

Read Read More
Up Caret

Using acoustic and linguistic markers from spontaneous speech to predict scores on the Montreal Cognitive Assessment (MoCA).

Balagopalan A., Yancheva M., Novikova J., Simpson W. (2019)

Society of Biological Psychiatry.

Read Read More
Up Caret

Impact of ASR on Alzheimer's Disease Detection: All Errors are Equal, but Deletions are More Equal than Others

Balagopalan A., Shkaruta K., Novikova J. (2019)

W-NUT Workshop on Noisy User-generated Text at EMNLP 2020.

Read Read More
Up Caret

Detecting Cognitive Impairments by Agreeing on Interpretations of Linguistic Features

Zhu Z., Novikova J., Rudzicz F. (2019)

NAACL 2019.

Read Read More
Up Caret

The Effect of Heterogeneous Data for Alzheimer’s Disease Detection from Speech

Balagopalan A., Novikova J., Rudzicz F., Ghassemi M. (2018)

Machine Learning for Health Workshop at NeurIPS 2018.

Read Read More
Up Caret

Semi-supervised Classification by Reaching Consensus Among Modalities

Zhu Z., Novikova J., Rudzicz F. (2018)

IRASL, Interpretability and Robustness in Audio, Speech and Language Workshop at NeurIPS 2018.

Read Read More
Up Caret

Learning Multiview Embeddings for Assessing Dementia

Pou-Prom C., Rudzicz F. (2018)

Proceedings of Empirical Methods in Natural Languages Processing 2018.

Read Read More
Up Caret

A Swedish Cookie-Theft Corpus

Kokkinakis D., Lundholm Fors K., Fraser K.C., Nordlund A. (2018)

Proceedings of the 11th edition of the Language Resources and Evaluation Conference (LREC). Miyazaki, Japan.

Read Read More
Up Caret

On the Importance of Normative Data in Speech-based Assessment

Noorian Z., Pou-Prom C., Rudzicz F. (2017)

Machine Learning for Health Workshop at NIPS 2017.

Read Read More
Up Caret

Rhetorical Structure and Alzheimer’s Disease

Abdalla M., Rudzicz F., Hirst G. (2017)

Aphasiology, 32(1):41-60.

Read Read More
Up Caret

Identifying and Avoiding Confusion in Dialogue with People with Alzheimer’s Disease

Chinaei H., Danks A, Mehta T., Chan-Currie L., Lin H., Rudzicz F. (2017)

Computational Linguistics, 43(2):377-406.

Read Read More
Up Caret

Speech Recognition in Alzheimer’s Disease and in its Assessment

Zhou L., Fraser K., Rudzicz F. (2016)

Proceedings of Interspeech 2016.

Read Read More
Up Caret

Vector-space Topic Models for Detecting Alzheimer's Disease

Yancheva, M., Rudzicz, F. (2016)

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

Read Read More
Up Caret

Toward Dementia Diagnosis via Artificial Intelligence

Rudzicz F. (2016)

Today’s Geriatric Medicine, 9(2):8, March.

Read Read More
Up Caret

Get in touch

Mailing Address

Winterlight Labs
46 Hayden St
Suite 400
Toronto
Ontario, Canada
M4Y 1V8

Send us a message