AMSTERDAM, July 28, 2020
At this year’s virtual edition of the Alzheimer’s Association International Conference (AAIC) Conference, Winterlight presented three posters highlighting our advances in validating speech-based digital biomarkers.
In a longitudinal study, we found that individuals with low scores on a screening tool for mild cognitive impairment, the Montreal Cognitive Assessment (MoCA), showed lower scores on speech measures compared to those with high scores on the MoCA. This group showed speech patterns and change over six months similar to a group with mild cognitive impairment (MCI) and early Alzheimer’s disease (AD). These results suggest that those with undiagnosed/possible cognitive impairment show differences in speech similar to MCI/AD.
In a second study in collaboration with Dr. Anthony Yeung and other clinicians at the University of Toronto, we compared subjective speech ratings made by expert clinicians to automatically computed speech features, to determine which speech features correlate with clinically-relevant speech symptoms. For example, clinical assessments of word-finding difficulty were found to be associated with slower speech rates, longer word durations and increased pauses. This study helps us determine which automated, objectively measured speech characteristics correspond to expert clinical judgments.
Finally, the COVID-19 pandemic has highlighted the need for digital medicine tools to facilitate at-home assessment and monitoring. We evaluated our in-clinic and remotely collected speech data and found that sample quality was comparable across both settings, suggesting that the Winterlight speech assessment is well-suited for remote data collection and disease monitoring, reducing the need for clinic visits and facilitating at-home monitoring.
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 www.winterlightlabs.com.
Liam Kaufman, CEO
liam [at] winterlightlabs.com