SenseToKnow (S2K) is a tablet-based app developed by Duke University researchers to improve autism diagnosis in children. Guided by machine learning and computer vision, the app plays short movies and tracks autism signs using recorded behavioral responses.
Using the tablet’s front-facing camera and computer vision, the app detects signs of autism, such as differences in social attention, facial expressions, and head movements. Machine learning analyzes the data to screen for autism. The AI compares each child’s biomarkers to how indicative they are of autism at a population level. Machine learning and computer vision allow the tool to capture behaviors other screening tests might miss and report on which biomarkers are of the most interest and most predictive for that particular child. Learn more about this tool on the S2K website. Information is provided in English and Spanish.