Winterlight predicts cognitive status using 2 minutes of speech

TORONTO, May 18, 2019

Today at the 74th Annual Meeting of the Society for Biological Psychiatry, Winterlight is presenting a poster highlighting the use of verbal picture descriptions to predict cognitive status.

Using data from 219 individuals who described a picture in their own words, we were able to estimate an individual’s score on the Montreal Cognitive Assessment (MoCA) within 2.6 points (8.7% error). Pauses, speaking rate, duration of speech and spectral composition of the sound itself were all important markers. Predictions of MoCA Index scores for different domains of cognitive functioning, including: Memory, Executive Function, Visuospatial, Attention, Language and Orientation were also accurate, with error ranging from 6.4%-20.6%.

These results extend our previous work using speech to predict scores on the Mini Mental State Examination (MMSE), while also highlighting an improvement in precision (MMSE error = 2.9 pts, MoCA error = 2.6 pts). This type of technology enables quicker, more objective assessment of one's cognitive status while also allowing for frequent and remote self assessment.

Download Poster

About Winterlight Labs

Winterlight Labs is commercializing a proprietary language-based diagnostic system that analyzes natural speech to detect and monitor dementia, Alzheimer’s, aphasia, and various other cognitive conditions. Winterlight's scalable platform uses short recorded speech samples to analyze hundreds of linguistic cues, and can detect dementia and other conditions with a high level of accuracy. This is a major improvement over current pencil-and-paper tests which are time-consuming, costly, and difficult to administer. The platform has applications in drug trials, long-term and primary care, and speech-language pathology.

Since its founding, Winterlight Labs has seen strong interest from pharmaceutical companies and other potential partners who view the technology as a major improvement over current methods of detection or screening. The company has gained support from the pan-Canadian AGE-WELL Network of Centres of Excellence (NCE), the Ontario Brain Institute, Ontario Centres of Excellence, and the University of Toronto Banting and Best Centre for Innovation and Entrepreneurship. For more information, visit

Media Inquiries:
Winterlight Labs
Liam Kaufman, CEO
liam [at]