Automated assessment of balance: A neural network approach based on large-scale balance function data
Balance impairment (BI) is an important cause of falls in the elderly. However, the existing balance estimation system needs to measure a large number of items to obtain the balance score and balance level, which is less efficient and redundant. In this context, we aim at building a model to automat...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-09-01
|
Series: | Frontiers in Public Health |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2022.882811/full |
_version_ | 1798031809130266624 |
---|---|
author | Jingsong Wu Jingsong Wu Yang Li Yang Li Lianhua Yin Youze He Tiecheng Wu Chendong Ruan Xidian Li Jianhuang Wu Jianhuang Wu Jing Tao Jing Tao |
author_facet | Jingsong Wu Jingsong Wu Yang Li Yang Li Lianhua Yin Youze He Tiecheng Wu Chendong Ruan Xidian Li Jianhuang Wu Jianhuang Wu Jing Tao Jing Tao |
author_sort | Jingsong Wu |
collection | DOAJ |
description | Balance impairment (BI) is an important cause of falls in the elderly. However, the existing balance estimation system needs to measure a large number of items to obtain the balance score and balance level, which is less efficient and redundant. In this context, we aim at building a model to automatically predict the balance ability, so that the early screening of large-scale physical examination data can be carried out quickly and accurately. We collected and sorted out 17,541 samples, each with 61-dimensional features and two labels. Moreover, using this data a lightweight artificial neural network model was trained to accurately predict the balance score and balance level. On the premise of ensuring high prediction accuracy, we reduced the input feature dimension of the model from 61 to 13 dimensions through the recursive feature elimination (RFE) algorithm, which makes the evaluation process more streamlined with fewer measurement items. The proposed balance prediction method was evaluated on the test set, in which the determination coefficient (R2) of balance score reaches 92.2%. In the classification task of balance level, the metrics of accuracy, area under the curve (AUC), and F1 score reached 90.5, 97.0, and 90.6%, respectively. Compared with other competitive machine learning models, our method performed best in predicting balance capabilities, which is especially suitable for large-scale physical examination. |
first_indexed | 2024-04-11T20:03:33Z |
format | Article |
id | doaj.art-6bc5a4c983c641a0856b4a6f3e161dd4 |
institution | Directory Open Access Journal |
issn | 2296-2565 |
language | English |
last_indexed | 2024-04-11T20:03:33Z |
publishDate | 2022-09-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Public Health |
spelling | doaj.art-6bc5a4c983c641a0856b4a6f3e161dd42022-12-22T04:05:27ZengFrontiers Media S.A.Frontiers in Public Health2296-25652022-09-011010.3389/fpubh.2022.882811882811Automated assessment of balance: A neural network approach based on large-scale balance function dataJingsong Wu0Jingsong Wu1Yang Li2Yang Li3Lianhua Yin4Youze He5Tiecheng Wu6Chendong Ruan7Xidian Li8Jianhuang Wu9Jianhuang Wu10Jing Tao11Jing Tao12College of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou, ChinaFujian Collaborative Innovation Center for Rehabilitation Technology, Fuzhou, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Science, Shenzhen, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaCollege of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou, ChinaCollege of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou, ChinaFujian Collaborative Innovation Center for Rehabilitation Technology, Fuzhou, ChinaCollege of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou, ChinaCollege of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Science, Shenzhen, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaCollege of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou, ChinaFujian Collaborative Innovation Center for Rehabilitation Technology, Fuzhou, ChinaBalance impairment (BI) is an important cause of falls in the elderly. However, the existing balance estimation system needs to measure a large number of items to obtain the balance score and balance level, which is less efficient and redundant. In this context, we aim at building a model to automatically predict the balance ability, so that the early screening of large-scale physical examination data can be carried out quickly and accurately. We collected and sorted out 17,541 samples, each with 61-dimensional features and two labels. Moreover, using this data a lightweight artificial neural network model was trained to accurately predict the balance score and balance level. On the premise of ensuring high prediction accuracy, we reduced the input feature dimension of the model from 61 to 13 dimensions through the recursive feature elimination (RFE) algorithm, which makes the evaluation process more streamlined with fewer measurement items. The proposed balance prediction method was evaluated on the test set, in which the determination coefficient (R2) of balance score reaches 92.2%. In the classification task of balance level, the metrics of accuracy, area under the curve (AUC), and F1 score reached 90.5, 97.0, and 90.6%, respectively. Compared with other competitive machine learning models, our method performed best in predicting balance capabilities, which is especially suitable for large-scale physical examination.https://www.frontiersin.org/articles/10.3389/fpubh.2022.882811/fullneural networksmachine learningfeature selectionbalanceautomated assessment |
spellingShingle | Jingsong Wu Jingsong Wu Yang Li Yang Li Lianhua Yin Youze He Tiecheng Wu Chendong Ruan Xidian Li Jianhuang Wu Jianhuang Wu Jing Tao Jing Tao Automated assessment of balance: A neural network approach based on large-scale balance function data Frontiers in Public Health neural networks machine learning feature selection balance automated assessment |
title | Automated assessment of balance: A neural network approach based on large-scale balance function data |
title_full | Automated assessment of balance: A neural network approach based on large-scale balance function data |
title_fullStr | Automated assessment of balance: A neural network approach based on large-scale balance function data |
title_full_unstemmed | Automated assessment of balance: A neural network approach based on large-scale balance function data |
title_short | Automated assessment of balance: A neural network approach based on large-scale balance function data |
title_sort | automated assessment of balance a neural network approach based on large scale balance function data |
topic | neural networks machine learning feature selection balance automated assessment |
url | https://www.frontiersin.org/articles/10.3389/fpubh.2022.882811/full |
work_keys_str_mv | AT jingsongwu automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata AT jingsongwu automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata AT yangli automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata AT yangli automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata AT lianhuayin automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata AT youzehe automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata AT tiechengwu automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata AT chendongruan automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata AT xidianli automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata AT jianhuangwu automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata AT jianhuangwu automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata AT jingtao automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata AT jingtao automatedassessmentofbalanceaneuralnetworkapproachbasedonlargescalebalancefunctiondata |