Metaverse physical therapy (MPT), an adjuvant technology for the rehabilitation of children with cerebral palsy (CP), has gained notoriety in the clinical field owing to its accessibility and because it provides motivation for rehabilitation. The aim is to compare the gross motor function and cardiopulmonary function, the activities of daily living, quality of life (QOL), and the perceived risk of coronavirus disease (COVID)-19 transmission between MPT and conventional physical therapy (CPT). A convenience sample of 26 children with CP (mean age, 11.23 ± 3.24 years, 14 females) were randomized into either the MPT or CPT group and received therapy three days/week for four weeks. Clinical outcomes included gross-motor-function measure 66 (GMFM-66), heart rate (HR), Borg-rating perceived exertion (BRPE), functional independence measure (FIM), pediatric QOL, and the risk of COVID-19 transmission. An analysis of variance showed that compared with CPT, MPT exerted positive effects on GMFM, HR, and BRPE. An independent t-test showed that compared with CPT, MPT exerted positive effects on the perceived transmission risk of COVID-19 but not on FIM and QOL. Our results provide promising therapeutic evidence that MPT improves gross motor function, cardiopulmonary function, and the risk of COVID-19 in children with CP.

Jongseok Hwang, PT, Ph.D.ㆍIl-Young Moon, PT, Ph.D.. KSPM 2023;18:11-9. https://doi.org/10.13066/kspm.2023.18.3.11

Jin-seok Lim, PT, BPT, Seo-hyun Kim, PT, BPT, Il-young Moon, PT, MSc, Chung-hwi Yi, PT, PhD. Phys. Ther. Korea 2021;28:200-7. https://doi.org/10.12674/ptk.2021.28.3.200

Cognitive impairment, which commonly occurs after stroke, adversely impacts rehabilitation outcomes. The administration of traditional screening tools such as the Mini-Mental State Examination (MMSE) can be challenging for patients with communication or motor limitations. This study aimed to determine whether routinely collected functional assessments can effectively predict cognitive impairment in stroke patients undergoing robotic-assisted gait training with the Lokomat system. In this retrospective analysis, data from 274 stroke patients who received Lokomat-based rehabilitation were examined. Patients with complete data on the MMSE, Fugl-Meyer Assessment (FMA), Modified Barthel Index (MBI), and Timed Up and Go (TUG) test were included in the final analysis. Cognitive impairment was defined as an MMSE score < 24. Five supervised machine learning models—logistic regression, decision tree, random forest, support vector machine (SVM), and XGBoost—were developed to classify cognitive status using FMA, MBI, and TUG as predictors. The performance of each model was assessed by the area under the curve (AUC), accuracy, sensitivity, and precision. Logistic regression demonstrated the highest predictive performance (AUC = 0.92, accuracy = 89.5%), followed by random forest (AUC = 0.88) and XGBoost (AUC = 0.87). FMA was identified as the most significant predictor in tree-based models. Patients classified as cognitively impaired exhibited significantly lower functional scores than their unimpaired counterparts (p < 0.001). Functional assessments routinely performed during stroke rehabilitation can provide a practical and accurate method for identifying cognitive impairment, especially when cognitive screening is constrained. These results support the incorporation of machine learning–based tools into clinical decision-making during robotic rehabilitation.