Utilization of Machine Learning-Based Computer Vision and Voice Analysis to Derive Digital Biomarkers of Cognitive Functioning in Trauma Survivors

• Main Authors: Katharina Schultebraucks, Vijay Yadav, Isaac R. Galatzer-Levy
• Format: Article
• Language: English
• Published: Karger Publishers 2020-12-01
• Series: Digital Biomarkers
• Subjects: computer vision; deep learning; voice analysis; emergency department; digital biomarkers; cognitive functioning
• Online Access: https://www.karger.com/Article/FullText/512394

Background: Alterations in multiple domains of cognition have been observed in individuals who have experienced a traumatic stressor. These domains may provide important insights in identifying underlying neurobiological dysfunction driving an individual’s clinical response to trauma. However, such assessments are burdensome, costly, and time-consuming. To overcome barriers, efforts have emerged to measure multiple domains of cognitive functioning through the application of machine learning (ML) models to passive data sources. Methods: We utilized automated computer vision and voice analysis methods to extract facial, movement, and speech characteristics from semi-structured clinical interviews in 81 trauma survivors who additionally completed a cognitive assessment battery. A ML-based regression framework was used to identify variance in visual and auditory measures that relate to multiple cognitive domains. Results: Models derived from visual and auditory measures collectively accounted for a large variance in multiple domains of cognitive functioning, including motor coordination (R2 = 0.52), processing speed (R2 = 0.42), emotional bias (R2 = 0.52), sustained attention (R2 = 0.51), controlled attention (R2 = 0.44), cognitive flexibility (R2 = 0.43), cognitive inhibition (R2 = 0.64), and executive functioning (R2 = 0.63), consistent with the high test-retest reliability of traditional cognitive assessments. Face, voice, speech content, and movement have all significantly contributed to explaining the variance in predicting functioning in all cognitive domains. Conclusions: The results demonstrate the feasibility of automated measurement of reliable proxies of cognitive functioning through low-burden passive patient evaluations. This makes it easier to monitor cognitive functions and to intervene earlier and at a lower threshold without requiring a time-consuming neurocognitive assessment by, for instance, a licensed psychologist with specialized training in neuropsychology.