ONGOING RESEARCH
(i) Detecting Developmental Delay and Autism through Home Videos of Bangladeshi children
Detecting Developmental Delay and Autism Through Machine Learning Models Using Home Videos of Bangladeshi Children: Development and Validation Study
Autism spectrum disorder (ASD) is currently diagnosed using qualitative methods that measure between 20-100 behaviors, can span multiple appointments with trained clinicians, and take several hours to complete. In our previous work, we demonstrated the efficacy of machine learning classifiers to accelerate the process by collecting home videos of US-based children, identifying a reduced subset of behavioral features that are scored by untrained raters using a machine learning classifier to determine children’s “risk scores” for autism. We achieved an accuracy of 92% (95% CI 88%-97%) on US videos using a classifier built on five features.
Present study, 2019-2020: “The Role of Language and Cultural Barriers in Mobile Detection of Autism through Machine Learning and Home Videos in Bangladesh”
(ii) Development of a protocol for addressing Child and adolescent mental health problems
- Validation of the protocol in several sites across Bangladesh including Rohinga Camps in Cox's Bazar, Chottogram, Bangladesh
- Member of the North East England And South Asia Mental Health Alliance (NEESAMA)
1st Steering Committee Meeting:
2nd Steering Committee Meeting:
Host – Bangladesh Protibondhi Foundation
Dates – 21 Oct to 24 Oct, 2019, in Dhaka
(III) Eight-year follow-up of families within a rural community in dacope upazila, khulna, bangladesh
(fieldwork completed in 2018. Data being analyzed)