Development Of Fall Risk Clustering Algorithm In Older People

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 p...

Full description

Bibliographic Details
Main Author: Wong, Kam Kang
Format: Final Year Project / Dissertation / Thesis
Published: 2020
Subjects:
Online Access:http://eprints.utar.edu.my/4219/
http://eprints.utar.edu.my/4219/1/1606589_FYP_report_%2D_KAM_KANG_WONG.pdf
_version_ 1848886102514991104
author Wong, Kam Kang
author_facet Wong, Kam Kang
author_sort Wong, Kam Kang
building UTAR Institutional Repository
collection Online Access
description 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.
first_indexed 2025-11-15T19:33:09Z
format Final Year Project / Dissertation / Thesis
id utar-4219
institution Universiti Tunku Abdul Rahman
institution_category Local University
last_indexed 2025-11-15T19:33:09Z
publishDate 2020
recordtype eprints
repository_type Digital Repository
spelling utar-42192021-08-11T13:23:51Z Development Of Fall Risk Clustering Algorithm In Older People Wong, Kam Kang TJ Mechanical engineering and machinery 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. 2020 Final Year Project / Dissertation / Thesis NonPeerReviewed application/pdf http://eprints.utar.edu.my/4219/1/1606589_FYP_report_%2D_KAM_KANG_WONG.pdf Wong, Kam Kang (2020) Development Of Fall Risk Clustering Algorithm In Older People. Final Year Project, UTAR. http://eprints.utar.edu.my/4219/
spellingShingle TJ Mechanical engineering and machinery
Wong, Kam Kang
Development Of Fall Risk Clustering Algorithm In Older People
title Development Of Fall Risk Clustering Algorithm In Older People
title_full Development Of Fall Risk Clustering Algorithm In Older People
title_fullStr Development Of Fall Risk Clustering Algorithm In Older People
title_full_unstemmed Development Of Fall Risk Clustering Algorithm In Older People
title_short Development Of Fall Risk Clustering Algorithm In Older People
title_sort development of fall risk clustering algorithm in older people
topic TJ Mechanical engineering and machinery
url http://eprints.utar.edu.my/4219/
http://eprints.utar.edu.my/4219/1/1606589_FYP_report_%2D_KAM_KANG_WONG.pdf