Dennis Wall, PhD and his team at Harvard Medical School developed the basis for the Cognoa assessment by using machine learning, a statistical approach for detecting meaningful patterns in data. They used it to hone in on specific behaviors from the standard diagnostic instruments (ADOS, ADI-R and others) that have the highest value for detection of children at risk for developmental delay and autism. The results provided the basis for a predictive algorithm that relies on behavioral reports from parents coupled with an evaluation of short (< 5 minute) home videos of the child in a comfortable and natural setting.
Dr. Wall’s team developed simple instructions that non-clinicians could use to evaluate and correctly score the home videos and has demonstrated the reproducibility of this scoring methodology. Clinical validation of the questionnaire and screening tools are ongoing with collaborating clinical centers across the nation.
Dr. Wall and his colleagues have published several papers in peer-reviewed open-source journals that can be viewed using the links below: