There is a rising epidemic of autism around the world that now affects an estimated 1 in 68 children in the United States, with similar prevalence rates found in many countries worldwide. Multiple barriers exist to identification and treatment of at-risk children. Our goal is to identify and diagnose every child with autism in Bangladesh before the age of 4 using mobile machine-learning technology that analyzes home videos and a short caregiver-directed questionnaire in minutes. This technology has the potential to leapfrog over existing cultural, language, technology, and health workforce barriers to ensure accurate identification of children with autism early in life. If validated, this proof-of-concept initiative to screen and diagnose children with autism could be extended to other under-resourced countries and to other neuro-developmental conditions thereby expanding the reach and impact of services that are central to achievement of the Sustainable Development Goals outlined in the recently launched Lancet Series on Advancing Early Childhood Development.
- Dennis Wall, Associate Professor of Pediatrics (Systems Medicine), of Biomedical Data Science and, by courtesy, of Psychiatry and Behavioral Sciences, Stanford University, School of Medicine
- Naila Khan, Professor and Department Head, Department of Pediatric Neuroscience, Bangladesh Institute of Child Health, Dhaka Shishu (Children's) Hospital