IAA BtG: A new window into autism spectrum disorder from space research

Impact Accelerator Account: Bridging the Gaps project.

Network and dynamical systems analysis, developed by Clark and Macdonald within EPSRC-funded research, has enabled advances in autonomous drone control, brain neuroimaging analysis, dynamical system monitoring, and most recently the design of space systems. This research provides an analytical framework for evaluating swipe patterns from a recently completed, and world leading, autism diagnostic clinical trial of 760 pre-school children.

Autism spectrum disorder (ASD) is a neurodevelopmental condition affecting at least 700,000 individuals in the UK with an aggregate annual healthcare and support cost of at least £28 billion. Early identification, proceeded by therapeutic intervention, can produce significant, lifelong health and economic benefit. An ASD diagnosis currently requires a trained clinician, but there is a long and growing waiting list for such assessments. To meet demand, and create more accessible means of assessment, bespoke touchscreen games have been developed for early autism detection and recently trialled for children aged 3–6 years.

Touchscreen games provide a scalable alternative for detecting autism, with machine learning analysis able to detect autism with up to 93% accuracy from children’s motor patterns. Machine learning detects differences in user swipe interactions but cannot reveal the nature of these discrepancies, in particular how swipe patterns differ. By employing network analysis, we can identify – for the first time – the specific pattern signatures of autistic users, which will improve the detection of ASD and the accuracy in differentiating ASD from other neurodevelopmental disorders. We will explore how the development of children with neurodevelopmental disorders differs from their typically developed counterparts. Crucial insights that will form the basis of effective diagnosis, supporting and tailoring therapeutic interventions to address the massive economic impact of mis- or late diagnosis.

A project to improve our understanding of and ability to diagnose pre-school children with autism spectrum disorder. The project shall investigate the use of network analysis to analyse the swipe patterns of children interacting with a touchscreen game.