Explainable Artificial Intelligence and Mobile Health for Treating Eating Disorders in Young Adults with Autism Spectrum Disorder Based on the Theory of Change: A Mixed Method Protocol

Autistic children often face difficulties eating well into their early adolescence, putting them at a greater risk of developing disordered eating habits during this developmental stage. Research suggests that mobile devices are easily accessible to young adults, and their widespread use can be leveraged to provide support and intervention for autistic young adults in preventing and self-managing eating disorders. By utilising Explainable Artificial Intelligence (XAI) and Machine Learning (ML) powered mobile devices, a progressive learning system can be developed that provides essential life skills for independent living and improved quality of life. In addition, XAI can enhance healthcare professionals’ decision-making abilities by utilising trained algorithms that can learn, providing a therapeutic benefit for preventing and mitigating the risk of eating disorders. This study will utilise the theory of change (ToC) approach to guide the investigation and analysis of the complex integration of autism, ED, XAI, ML, and mobile health. This approach will be complemented by user-centred design, Patient and Public Involvement and Engagement (PPIE) tasks, activities, and a mixed method approach to make the integration more rigorous, timely, and valuable. Ultimately, this study aims to provide essential life skills to autistic young adults to prevent and self-manage eating disorders using XAI-powered mobile devices.