머신 러닝을 활용한 고령층의 구강건강평가지수 (Geriatric Oral Health Assessment Index) 예측 모델 개발*
Development of a Machine Learning-Based Predictive Model for the Geriatric Oral Health Assessment Index (GOHAI) in Older Adults
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
= Abstract = Objective: This study aimed to classify oral health status into two categories “low” and “high” based on the geriatric oral health assessment index score, and to develop a predictive model using various machine learning algorithms. Methods: This study utilized data from the 9th wave of the korean longitudinal study of aging, comprising a total of 6,057 participants. Data analysis was performed using IBM SPSS Statistics (version 26.0) and RStudio (version 4.5.0). Results: The analysis of the correlations between GOHAI and related variables among the study participants showed that GOHAI scores were significantly associated with activity limitation (r=-0.354, p<0.001), age (r=-0.270, p<0.001), presence of depression (r=-0.069, p<0.05), and presence of diabetes (r=-0.105, p<0.001). Among these factors, activity limitation had the greatest impact on GOHAI scores (β =-0.270, p<0.001). Conclusion: This study highlights the need to develop various programs that enable individuals to self-assess and manage their health status based on subjective indicators such as the geriatric oral health assessment index, and anticipates that the predictive model can serve as a practical field tool for the early identification of those at risk for poor oral health.
Abstract
= Abstract = Objective: This study aimed to classify oral health status into two categories “low” and “high” based on the geriatric oral health assessment index score, and to develop a predictive model using various machine learning algorithms. Methods: This study utilized data from the 9th wave of the korean longitudinal study of aging, comprising a total of 6,057 participants. Data analysis was performed using IBM SPSS Statistics (version 26.0) and RStudio (version 4.5.0). Results: The analysis of the correlations between GOHAI and related variables among the study participants showed that GOHAI scores were significantly associated with activity limitation (r=-0.354, p<0.001), age (r=-0.270, p<0.001), presence of depression (r=-0.069, p<0.05), and presence of diabetes (r=-0.105, p<0.001). Among these factors, activity limitation had the greatest impact on GOHAI scores (β =-0.270, p<0.001). Conclusion: This study highlights the need to develop various programs that enable individuals to self-assess and manage their health status based on subjective indicators such as the geriatric oral health assessment index, and anticipates that the predictive model can serve as a practical field tool for the early identification of those at risk for poor oral health.