Development Of Fall Risk Clustering Algorithm In Older People

Wong, Kam Kang (2020) Development Of Fall Risk Clustering Algorithm In Older People. Final Year Project, UTAR.

Preview

PDF Download (1746Kb) | Preview

Abstract

Falls are serious problem which lead to negative consequences on the quality of life especially for older people. Most falls are caused by the interaction of multiple risk factors. However, manual analysis in big and complex medical data to analyse the fall risk factor are time consuming with high processing cost. Therefore, the aim of this study is to develop a clustering-based fall risk algorithm which can provide assistances for clinician in management of falls. The proposed algorithm consists of several stages, includes data pre-processing, feature selection, feature extraction, clustering and characteristic interpretation. This study employed Malaysian Elders Longitudinal Research (MELoR) dataset. A total of 1279 subjects and 9 variables from dataset (1411 subjects and 139 variables) are selected for clustering. t-Distributed Stochastic Neighbour Embedding (t-SNE) for feature extraction and K-means clustering algorithm achieved the highest performance in clustering, which grouping the subjects into Low (13%), Intermediate A (19%), Intermediate B (21%) and High (31%) fall risk group. In comparison, older people with higher fall risk have slower gait, imbalance, weaker muscle strength, with cardiovascular disorder, poorer performance in cognitive test, and advancing age. This is supported by the finding in literature review. To concluded, the proposed fall risk clustering algorithm is capable to group those subjects that have similar features. It presents a potential as assessment tool in management of falls.

Actions (login required)