Longitudinal evidence for autism care.

My autism and mobile-health research examines how sustained digital contact can help families and practitioners understand developmental change between in-person visits. The central program is mCARE, a mobile-based care and remote-monitoring platform for children with autism spectrum disorder in Bangladesh. Its workflow brings together caregiver observations, remote experience sampling, structured data management, and practitioner access to longitudinal information. Rather than treating a mobile application as an isolated product, the work studies the larger relationship among family routines, reporting burden, clinical interpretation, local services, and the technologies that connect them.

The publication record follows mCARE from value-sensitive and behavior-informed design through deployment and analysis. One end-to-end study describes a two-year deployment across four specialist centers involving 300 children. Other studies examine caregiver experience, data-driven validation, developmental milestone achievement, and patterns of risk and resilience around the COVID-19 disruption. MPredA extends the program with machine-learning models that estimate improvement across milestone parameters. These models are presented as research tools for understanding longitudinal patterns—not as replacements for professional diagnosis or individualized care.

Across the program, the technical questions are inseparable from equity and context. Caregiver-reported observations may be incomplete or shaped by changing family circumstances. Connectivity, language, digital literacy, clinical workload, and cultural expectations influence whether a workflow can be sustained. The research therefore combines system design, longitudinal analysis, machine learning, and stakeholder-centered evaluation while making the limits of prediction explicit. The goal is practical evidence that can strengthen family–practitioner communication in settings where continuous specialist access may be difficult.