Winterlight Tests Show Speech-Based Measures Can Detect Changes in Alzheimer's Disease

Winterlight Labs, a developer of digital biomarkers for the analysis of speech and language in neurological conditions, and pharmaceutical company Genentech released new data showing the sensitivity of speech-based digital measures in detecting disease-related longitudinal change in Alzheimer's disease.

Using data from Genentech's Tauriel trial of semorinemab in early-stage Alzheimer's disease, these analyses provide new evidence that automated measures for assessing patient speech can characterize longitudinal decline with comparable sensitivity to clinician-administered neuropsychological assessments. Digital measures can allow for better characterization of speech and language patterns, improved insight into the effects of novel treatments, and could support a shift to more hybrid or remote trial designs.

In this analysis, Winterlight's speech-based digital biomarker platform processed recordings of conventional administrations of the Clinical Dementia Rating (CDR) from 101 patients in the Tauriel trial and generated more than 500 acoustic and linguistic markers. Selected markers that indicate progressive change were combined into a composite speech score and compared to standard clinical endpoints. The composite speech score demonstrated similar results in detecting longitudinal changes compared to the CDR Sum of Boxes rating and the Alzheimer's Disease Assessment Scale-Cognitive Subscale. The findings indicated a more significant longitudinal effect than the Repeatable Battery for the Assessment of Neuropsychological Status test and the language subscales of the Alzheimer's Disease Assessment Scale-Cognitive Subscale (ADAS-Cog) measuring word-finding difficulty and spoken language ability.

"Given the crucial role that language changes play in Alzheimer's, automated language processing represents a new tool to characterize speech and language patterns and provide additional insight into a patient's condition," said Jessica Robin, director of clinical research at Winterlight Labs, in a statement. "We've worked to streamline the process of implementing automated tools into research, allowing for low-burden assessments suitable for remote testing that can help demonstrate how language changes because of disease progression or therapeutic interventions. Collaborating with Genentech to analyze speech samples from a well-characterized, longitudinal trial cohort has enabled us to advance the study of language changes in Alzheimer's."

SpeechTek Covers
for qualified subscribers
Subscribe Now Current Issue Past Issues