Deep learning and digital health to support post-stroke function-based rehablitation

Stroke is a global health-care problem that is common, serious, and disabling. In most countries, stroke is the second or third most common cause of death and one of the main causes of acquired adult disability. Because most patients with stroke will survive the initial illness, the greatest health effect is usually caused by the long-term consequences for patients and their families. The prevalence of stroke-related burdens is expected to increase over the next two decades. Although impressive developments have been made in the medical management of stroke, without a widely applicable or effective medical treatment most post-stroke care will continue to rely on rehabilitation interventions. Research shows that repetitive task training has a positive effect on improving functional ability after stroke, especially a moderate improvement has been shown in gait and speech improvement. This project aims to develop an intelligent system to support post-stroke survivors in improving speech, lower limb and upper limb functions. The system will generate the speech training tasks, using smart wristbands and smart shoes to collect the limb rehabilitation exercise movement. The system computer software will design the tasks and analyse the results to maximise the effectiveness of the training results. The global international collaboration between Ulster University(UK) and the National Tsing Hua University(Taiwan) can help to address the global challenge of post-stroke rehabilitation and understand how deep learning and digital health approach can be applied to it in different countries.