Machine Learning Algorithms for the Prediction of Language and Cognition Rehabilitation Outcomes of Post-stroke Patients: A Scoping Review

Le résumé fourni par la source

Abstract Stroke is one of the leading causes of long-term disabilities in motor and cognition functionality. An early and accurate prediction of rehabilitation outcomes can lead to a tailor-made treatment that can significantly improve the post-stroke quality of life of a person. This scoping review aimed to summarize studies that use Artificial Intelligence (AI) for the prediction of language and cognition rehabilitation outcomes and the need to use AI in this domain. This study followed the PRISMA-ScR guidelines for two databases, Scopus and PubMed. The results, which are measured with several metrics depending on the task, regression, or classification, present encouraging outcomes as they can predict the cognitive functionality of post-stroke patients with relative precision. Among the results of the paper are the identification of the most effective Machine Learning (ML) algorithms, and the identification of the key factors that influence rehabilitation outcomes. The majority of studies focus on aphasia and present high performance achieving up to 97% recall and 91.4% precision. The main limitations of the studies were the small subject population and the lack of an external dataset. However, effective ML algorithms along with explainability are expected to become among the most prominent solutions for precision medicine due to their ability to overcome non-linearities on data and provide insights and transparent predictions that can help healthcare professionals make more informed and accurate decisions.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.