Improved clustering techniques for paediatric cerebral palsy gait assessment during rehabilitation

Abstract

The gait abnormality may be the cause of various diseases like foot drop, lower back trembling, and osteoarthritis in the human body. The causes may affect body performance. The problem may be solved if we notice it between the ages of 2 and 20. Today's medical research struggles to identify normality and abnormality in children at a young age. The gait abnormalities depend on a complex neurological condition called cerebral palsy. The article proposes an improved fuzzy C-mean-PSO technique and also defines selection criteria for gait patterns, such as optimal number identification gait profiles, mean square error, silhouette coefficient, and Dunn index. The researcher used 156 patients’ data from the available O’Malley gait dataset for experimental purposes. We partitioned 156 patients into 5 different combinations. In the first two combinations, we applied conventional methods, and the next three employed proposed methods. Finally, we found the 91.6% CPI (Cluster Purity Index), that is greater than existing techniques. In the future, we can perform the proposed methods on various datasets. The findings indicate that employing clustering-based gait profiles improved fuzzy C-mean-PSO optimised using these methods can aid in measuring clinical rehabilitation for children with cerebral palsy.