A Review of and Roadmap for Data Science and Machine Learning for the Neuropsychiatric Phenotype of Autism.

This review looks at how technology and computer analysis could improve autism diagnosis and treatment. Researchers found there are delays and problems in how autism is currently diagnosed and treated. New digital tools and smartphone apps could help identify autism behaviors earlier and provide better therapies. The technology could make autism services more accessible to families, though more research is needed to make these tools work in real-world settings.

This 2023 review examines the application of data science and machine learning to autism diagnosis, therapy, and tracking. The authors highlight significant bottlenecks in current diagnostic and therapeutic pipelines for autism, identifying opportunities for digital health solutions to improve access to services. The review covers digital phenotyping methods, case-control studies, and classification systems for autism-related behaviors. It discusses machine learning models integrated into digital diagnostics and therapeutics, while addressing factors necessary for real-world implementation.

The authors emphasize ongoing challenges and future opportunities in autism data science, noting the relevance to broader neurological behavior analysis and digital psychiatry fields.

Digital health technologies could address current bottlenecks in autism diagnosis and treatment by providing more accessible, objective assessment tools and personalized interventions. Implementation requires addressing factors for translational use and overcoming challenges related to autism's heterogeneous nature.

As a review paper, this study does not present original research data or specific outcome measures. The heterogeneous nature of autism and complexity of relevant behaviors present ongoing challenges for standardization and implementation of digital solutions.

Autism spectrum disorder (autism) is a neurodevelopmental delay that affects at least 1 in 44 children. Like many neurological disorder phenotypes, the diagnostic features are observable, can be tracked over time, and can be managed or even eliminated through proper therapy and treatments. However, there are major bottlenecks in the diagnostic, therapeutic, and longitudinal tracking pipelines for autism and related neurodevelopmental delays, creating an opportunity for novel data science solutions to augment and transform existing workflows and provide increased access to services for affected families. Several efforts previously conducted by a multitude of research labs have spawned great progress toward improved digital diagnostics and digital therapies for children with autism.

We review the literature on digital health methods for autism behavior quantification and beneficial therapies using data science. We describe both case-control studies and classification systems for digital phenotyping. We then discuss digital diagnostics and therapeutics that integrate machine learning models of autism-related behaviors, including the factors that must be addressed for translational use. Finally, we describe ongoing challenges and potential opportunities for the field of autism data science.

Given the heterogeneous nature of autism and the complexities of the relevant behaviors, this review contains insights that are relevant to neurological behavior analysis and digital psychiatry more broadly.