Publication:
Predicting MIRA Patients’ Performance Using Virtual Rehabilitation Programme by Decision Tree Modelling

Simple item page
dc.contributor.authorZainal N.en_US
dc.contributor.authorAl-Hadi I.A.A.-Q.en_US
dc.contributor.authorGhaleb S.M.en_US
dc.contributor.authorHussain H.en_US
dc.contributor.authorIsmail W.en_US
dc.contributor.authorAldailamy A.Y.en_US
dc.date.accessioned2024-05-29T01:55:38Z
dc.date.available2024-05-29T01:55:38Z
dc.date.issued2021
dc.description.abstractAn effective rehabilitation procedure is required to successfully manage the disabilities caused by diseases such as stroke, spinal cord injury (SCI), traumatic brain injury (TBI), and cerebral palsy (CP). In this regard, Medical Interactive Recovery Assistant (MIRA) platform proffers virtual rehabilitation through exergames. Virtual reality therapy (VRT) has recently gained attention for upper limb rehabilitation due to its positive impacts on patients’ performance. VRT is a modern interactive application that integrates computer software with hardware devices to create an interactive virtual environment when playing different types of games and exercises (exergames). The output of playing the game generates statistical features (parameters) reflecting the patients’ performance. However, physiotherapists who manage the input settings of exergames according to specific movements cannot easily predict the future performance of the patients based on their observations. Thus, this study proposes a decision tree model to predict MIRA patients’ future performance for three difficulty levels (easy, medium and hard) with respect to their previous/last session records. Patients’ data in the previous/last session are used to determine the prediction values according to the proposed model. This helps physiotherapists to monitor and also predict their patients’ progress using certain prediction values. Results prove the efficiency of the proposed decision tree-based statistical tool for prediction in medical monitoring applications. © 2021, Springer Nature Switzerland AG.en_US
dc.identifier.doi10.1007/978-3-030-47411-9_24
dc.identifier.epage462
dc.identifier.issn21984182
dc.identifier.scopus2-s2.0-85087555646
dc.identifier.spage451
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85087555646&doi=10.1007%2f978-3-030-47411-9_24&partnerID=40&md5=32675f2b819e5163b7b03dfa95311c7a
dc.identifier.urihttps://oarep.usim.edu.my/handle/123456789/9732
dc.identifier.volume295
dc.languageEnglish
dc.language.isoen_USen_US
dc.publisherSpringeren_US
dc.relation.ispartofStudies in Systems, Decision and Controlen_US
dc.sourceScopus
dc.subjectDecision treeen_US
dc.subjectExergameen_US
dc.subjectRehabilitationen_US
dc.subjectVirtual reality therapyen_US
dc.titlePredicting MIRA Patients’ Performance Using Virtual Rehabilitation Programme by Decision Tree Modellingen_US
dspace.entity.typePublication

Files

Collections

Scopus