Cargando…

Predicting the Swallow-Related Quality of Life of the Elderly Living in a Local Community Using Support Vector Machine

Background and Objectives: This study developed a support vector machine (SVM) algorithm-based prediction model with considering influence factors associated with the swallowing quality-of-life as the predictor variables and provided baseline information for enhancing the swallowing quality of elder...

Descripción completa

Detalles Bibliográficos
Autor principal: Byeon, Haewon
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6862249/
https://www.ncbi.nlm.nih.gov/pubmed/31684165
http://dx.doi.org/10.3390/ijerph16214269
_version_ 1783471510501982208
author Byeon, Haewon
author_facet Byeon, Haewon
author_sort Byeon, Haewon
collection PubMed
description Background and Objectives: This study developed a support vector machine (SVM) algorithm-based prediction model with considering influence factors associated with the swallowing quality-of-life as the predictor variables and provided baseline information for enhancing the swallowing quality of elderly people’s lives in the future. Methods and Material: This study sampled 142 elderly people equal to or older than 65 years old who were using a senior welfare center. The swallowing problem associated quality of life was defined by the swallowing quality-of-life (SWAL-QOL). In order to verify the predictive power of the model, this study compared the predictive power of the Gaussian function with that of a linear algorithm, polynomial algorithm, and a sigmoid algorithm. Results: A total of 33.9% of the subjects decreased in swallowing quality-of-life. The swallowing quality-of-life prediction model for the elderly, based on the SVM, showed both preventive factors and risk factors. Risk factors were denture use, experience of using aspiration in the past one month, being economically inactive, having a mean monthly household income <2 million KRW, being an elementary school graduate or below, female, 75 years old or older, living alone, requiring time for finishing one meal on average ≤15 min or ≥40 min, having depression, stress, and cognitive impairment. Conclusions: It is necessary to monitor the high-risk group constantly in order to maintain the swallowing quality-of-life in the elderly based on the prevention and risk factors associated with the swallowing quality-of-life derived from this prediction model.
format Online
Article
Text
id pubmed-6862249
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-68622492019-12-05 Predicting the Swallow-Related Quality of Life of the Elderly Living in a Local Community Using Support Vector Machine Byeon, Haewon Int J Environ Res Public Health Article Background and Objectives: This study developed a support vector machine (SVM) algorithm-based prediction model with considering influence factors associated with the swallowing quality-of-life as the predictor variables and provided baseline information for enhancing the swallowing quality of elderly people’s lives in the future. Methods and Material: This study sampled 142 elderly people equal to or older than 65 years old who were using a senior welfare center. The swallowing problem associated quality of life was defined by the swallowing quality-of-life (SWAL-QOL). In order to verify the predictive power of the model, this study compared the predictive power of the Gaussian function with that of a linear algorithm, polynomial algorithm, and a sigmoid algorithm. Results: A total of 33.9% of the subjects decreased in swallowing quality-of-life. The swallowing quality-of-life prediction model for the elderly, based on the SVM, showed both preventive factors and risk factors. Risk factors were denture use, experience of using aspiration in the past one month, being economically inactive, having a mean monthly household income <2 million KRW, being an elementary school graduate or below, female, 75 years old or older, living alone, requiring time for finishing one meal on average ≤15 min or ≥40 min, having depression, stress, and cognitive impairment. Conclusions: It is necessary to monitor the high-risk group constantly in order to maintain the swallowing quality-of-life in the elderly based on the prevention and risk factors associated with the swallowing quality-of-life derived from this prediction model. MDPI 2019-11-03 2019-11 /pmc/articles/PMC6862249/ /pubmed/31684165 http://dx.doi.org/10.3390/ijerph16214269 Text en © 2019 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Byeon, Haewon
Predicting the Swallow-Related Quality of Life of the Elderly Living in a Local Community Using Support Vector Machine
title Predicting the Swallow-Related Quality of Life of the Elderly Living in a Local Community Using Support Vector Machine
title_full Predicting the Swallow-Related Quality of Life of the Elderly Living in a Local Community Using Support Vector Machine
title_fullStr Predicting the Swallow-Related Quality of Life of the Elderly Living in a Local Community Using Support Vector Machine
title_full_unstemmed Predicting the Swallow-Related Quality of Life of the Elderly Living in a Local Community Using Support Vector Machine
title_short Predicting the Swallow-Related Quality of Life of the Elderly Living in a Local Community Using Support Vector Machine
title_sort predicting the swallow-related quality of life of the elderly living in a local community using support vector machine
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6862249/
https://www.ncbi.nlm.nih.gov/pubmed/31684165
http://dx.doi.org/10.3390/ijerph16214269
work_keys_str_mv AT byeonhaewon predictingtheswallowrelatedqualityoflifeoftheelderlylivinginalocalcommunityusingsupportvectormachine