Stroke causes a severe impact in daily life movements. It affects a static balance in the human who has an impaired balance of their movement control. Assessing the evaluation criteria can be superseded via the movement, especially the Berg Balance scale, which is the gold standard in the assessment, even bringing a motion detector. To evaluate the balance assessment in stroke patient body, the physiotherapist uses the statistical methods to analyze the data. This research proposes the classification algorithm for evaluating the balance in the body of stroke patients with muscle weakness condition. It improves the algorithm’s accuracy in data prediction for measuring the validity of regaining balance while standing. The dataset has three main factors, including personal information, a diagnosis from a physiotherapist, and the performance standing on the Nintendo Wii Fit Balance Board. By evaluating with various scenario of different amount of attributes, the dataset with three attributes has the highest accuracy rate. Classifying information is used as a guideline in assessing the information on how to regain a patient’s balance control during standing. The most accurate classification method is the Artificial Neural Network with accurate 93% of the times for prediction and classification.
Keywords
Stroke, Balance Assessment, Arti cial Neural Network, Nintendo Wii Fit Balance Board, Machine Learning
ECTI TRANSACTIONS ON COMPUTER INFORMATION TECHNOLOGY