Purpose: The implementation of artificial intelligence in hand surgery and rehabilitation is gaining popularity. The purpose of this scoping review was to give an overview of implementations of artificial intelligence in hand surgery and rehabilitation and their current significance in clinical practice.
Methods: A systematic literature search of the MEDLINE/PubMed and Cochrane Collaboration libraries was conducted. The review was conducted according to the framework outlined by the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews. A narrative summary of the papers is presented to give an orienting overview of this rapidly evolving topic.
Results: Primary search yielded 435 articles. After application of the inclusion/exclusion criteria and addition of supplementary search, 235 articles were included in the final review. In order to facilitate navigation through this heterogenous field, the articles were clustered into four groups of thematically related publications. The most common applications of artificial intelligence in hand surgery and rehabilitation target automated image analysis of anatomic structures, fracture detection and localization and automated screening for other hand and wrist pathologies such as carpal tunnel syndrome, rheumatoid arthritis or osteoporosis. Compared to other medical subspecialties the number of applications in hand surgery is still small.
Conclusion: Although various promising applications of artificial intelligence in hand surgery and rehabilitation show strong performances, their implementation mostly takes place within the context of experimental studies. Therefore, their use in daily clinical routine is still limited.
Keywords: Artificial Intelligence; Deep learning; Hand rehabilitation; Hand surgery; Machine learning; Mathematical modelling.
© 2023. The Author(s).