Our Science

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 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:

Clinical Validation of Cognoa’s Screening Questionnaire

ML Algorithms that Power the Screening Questionnaire

ML Algorithms that Power the Video-based Evaluations

The Power of Internet-Based Research

Related Publications *

  1. Randomized, controlled trial of an intervention for toddlers with autism: the Early Start Denver Model. Dawson G, Rogers S, Munson J, Smith M, Winter J, et al. (2010) Pediatrics 125: e17–23. [PubMed]
  2. Object play in infants with autism: methodological issues in retrospective video analysis. Baranek GT, Barnett CR, Adams EM, Wolcott NA, Watson LR, et al. (2005) Am J Occup Ther 59: 20–30. [PubMed]
  3. Precursors and trajectories of sensory features: qualitative analysis of infant home videos. Freuler A, Baranek GT, Watson LR, Boyd BA, Bulluck JC (2012) Am J Occup Ther 66: e81–84. [PMC free article] [PubMed]
  4. Use of home videotapes to confirm parental reports of regression in autism. Goldberg WA, Thorsen KL, Osann K, Spence MA (2008) J Autism Dev Disord 38: 1136–1146. [PubMed]
  5. Integrating computerized primitives and annotated video patterns: a proposed model for autism diagnosis and research. Jameson R, Lorence D, Lee J (2012) J Med Syst 36: 2037–2045. [PubMed]
  6. Attentional skills during the first 6 months of age in autism spectrum disorder. Maestro S, Muratori F, Cavallaro MC, Pei F, Stern D, et al. (2002) J Am Acad Child Adolesc Psychiatry 41: 1239–1245. [PubMed]
  7. Computerized home video detection for motherese may help to study impaired interaction between infants who become autistic and their parents. Mahdhaoui A, Chetouani M, Cassel RS, Saint-Georges C, Parlato E, et al. (2011) Int J Methods Psychiatr Res 20: e6–18. [PubMed]
  8. Early recognition of children with autism: a study of first birthday home videotapes. Osterling J, Dawson G (1994) J Autism Dev Disord 24: 247–257. [PubMed]
  9. Onset patterns in autism: correspondence between home video and parent report. Ozonoff S, Iosif AM, Young GS, Hepburn S, Thompson M, et al. (2011) J Am Acad Child Adolesc Psychiatry 50: 796–806 e791. [PMC free article] [PubMed]
  10. Timing of identification among children with an autism spectrum disorder: findings from a population-based surveillance study. Shattuck PT, Durkin M, Maenner M, Newschaffer C, Mandell DS, et al. (2009) J Am Acad Child Adolesc Psychiatry 48: 474–483. [PMC free article] [PubMed]
  11. Examining restricted and repetitive behaviors in young children with autism spectrum disorder during two observational contexts. Stronach S, Wetherby AM (2012) Autism. [PubMed]
  12. Clinical assessment and management of toddlers with suspected autism spectrum disorder: insights from studies of high-risk infants. Zwaigenbaum L, Bryson S, Lord C, Rogers S, Carter A, et al. (2009) Pediatrics 123: 1383–1391. [PMC free article] [PubMed]
* Some of these publications are in copyrighted journals and, as such, there may be charges associated with downloading or viewing papers that are outside the control of Cognoa.