Review Article

Use of Artificial Intelligence Systems for Hand Motor Recovery in Stroke: A Narrative Review

Abstract

With the global population aging rapidly, the incidence of stroke and its associated burden on healthcare systems and society are projected to rise significantly. Stroke survivors often experience a range of long-term complications, including sensory, motor, cognitive, and psychological impairments. Among these, upper limb dysfunction—particularly involving the hands—is a major barrier to performing essential activities of daily living (ADLs) in patients with hemiplegia. Consequently, restoring hand function has become a central focus in post-stroke rehabilitation. Motor recovery is often facilitated through compensatory methods, such as the use of robotic devices for hand therapy, which have seen notable development since the late 20th century. This review explored the current landscape of hand rehabilitation systems that incorporate hand motion recognition technologies, examining their technical approaches, strengths, and limitations. In addition, the role of artificial intelligence in enhancing the functionality and adaptability of these systems is discussed. The paper also outlines existing challenges and suggests directions for future research in the field.