A Study on the Prediction Model of the Elderly Depression
1
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
Purpose: In modern society, many urban problems are occurring, such as aging, hollowing out old city centers and polarization within cities. In this study, we intend to apply big data and machine learning methodologies to predict depression symptoms in the elderly population early on, thus contributing to solving the problem of elderly depression. Research design, data and methodology: Machine learning techniques used random forest and analyzed the correlation between CES-D10 and other variables, which are widely used worldwide, to estimate important variables. Dependent variables were set up as two variables that distinguish normal/depression from moderate/severe depression, and a total of 106 independent variables were included, including subjective health conditions, cognitive abilities, and daily life quality surveys, as well as the objective characteristics of the elderly as well as the subjective health, health, employment, household background, income, consumption, assets, subjective expectations, and quality of life surveys. Results: Studies have shown that satisfaction with residential areas and quality of life and cognitive ability scores have important effects in classifying elderly depression, satisfaction with living quality and economic conditions, and number of outpatient care in living areas and clinics have been important variables. In addition, the results of a random forest performance evaluation, the accuracy of classification model that classify whether elderly depression or not was 86.3%, the sensitivity 79.5%, and the specificity 93.3%. And the accuracy of classification model the degree of elderly depression was 86.1%, sensitivity 93.9% and specificity 74.7%. Conclusions: In this study, the important variables of the estimated predictive model were identified using the random forest technique and the study was conducted with a focus on the predictive performance itself. Although there are limitations in research, such as the lack of clear criteria for the classification of depression levels and the failure to reflect variables other than KLoSA data, it is expected that if additional variables are secured in the future and high-performance predictive models are estimated and utilized through various machine learning techniques, it will be able to consider ways to improve the quality of life of senior citizens through early detection of depression and thus help them make public policy decisions.
Abstract
Purpose: In modern society, many urban problems are occurring, such as aging, hollowing out old city centers and polarization within cities. In this study, we intend to apply big data and machine learning methodologies to predict depression symptoms in the elderly population early on, thus contributing to solving the problem of elderly depression. Research design, data and methodology: Machine learning techniques used random forest and analyzed the correlation between CES-D10 and other variables, which are widely used worldwide, to estimate important variables. Dependent variables were set up as two variables that distinguish normal/depression from moderate/severe depression, and a total of 106 independent variables were included, including subjective health conditions, cognitive abilities, and daily life quality surveys, as well as the objective characteristics of the elderly as well as the subjective health, health, employment, household background, income, consumption, assets, subjective expectations, and quality of life surveys. Results: Studies have shown that satisfaction with residential areas and quality of life and cognitive ability scores have important effects in classifying elderly depression, satisfaction with living quality and economic conditions, and number of outpatient care in living areas and clinics have been important variables. In addition, the results of a random forest performance evaluation, the accuracy of classification model that classify whether elderly depression or not was 86.3%, the sensitivity 79.5%, and the specificity 93.3%. And the accuracy of classification model the degree of elderly depression was 86.1%, sensitivity 93.9% and specificity 74.7%. Conclusions: In this study, the important variables of the estimated predictive model were identified using the random forest technique and the study was conducted with a focus on the predictive performance itself. Although there are limitations in research, such as the lack of clear criteria for the classification of depression levels and the failure to reflect variables other than KLoSA data, it is expected that if additional variables are secured in the future and high-performance predictive models are estimated and utilized through various machine learning techniques, it will be able to consider ways to improve the quality of life of senior citizens through early detection of depression and thus help them make public policy decisions.
참고문헌 (31)
- Bae, S. W., "A Comparative Study on the Prediction of Housing Price Using Machine Learning", Doctor, pp.2019
- 배성우, "CES-D 척도(The Center for Epidemiologic Studies-Depression Scale)의 요인구조 분석: 확인적 요인분석 방법의 적용", 보건과 사회과학, 18, pp.134~155 (2005), 한국보건사회학회
- Breiman, L., "Random forests", Machine Learning, 45, pp.5~ (2001)
- 예우지엔, "개선된 휴리스틱 규칙 및 의사 결정 트리 분석을 이용한 P2P 트래픽 분류 기법", 한국컴퓨터정보학회논문지, 19(3), pp.45~54 (2014), 한국컴퓨터정보학회
- Choi, J. H., "Application of Data Mining Decision Tree", Statistical Analysis Study, 4(1), pp.62~ (1999)
- Choi, P. S., "A Model for the Employment Prediction of College Graduates Using Machine Learning Technique", Job Competency Development Research, 21(1), pp.35~36 (2018)
- "Cognitive Computing and Machine Learning" (2019)[URL]
- Trevor, H., "The element of statistical learning", pp.305~585 (2009), Springer
- "Statistic of National Concerned Diseases-Depression" (2019)[URL]
- 허만세, "한국어판 축약형 CES-D 척도의 측정불변성 검증", 정신건강과 사회복지, 43(2), pp.313~339 (2015), 한국정신건강사회복지학회
- Jeong, I. Y., "A Study on the Causal Model of Preparing for the Elderly and Suicide of Middle and Middle-aged People: Focused on the Intermediary Effects of Social Participation, Social Support, Stress, and Depression", Doctor, pp.2015
- Myers, J. K., "One-Month Prevalence of Mental Disorders in the United States", Arch Gen Psychiatry, 45, pp.977~986 (1988)
- The 6th Basic Survey of the Aging Research Panel (KLoSA) in 2016, "KEIS", ~ (2016)
- KEIS, "2018 Aging Research Panel User Guide", ~ (2019)
- 김봉정, "노인의 우울증에 영향을 미치는 요인: 국민건강영양조사 제7기 자료", 보건정보통계학회지, 45(2), pp.165~172 (2020), 한국보건정보통계학회[DOI]
- Kim, D. H., "A Study on the Relationship between Family Support, Self-respect, and Depression in which Older People are Late", Elderly Welfare Research, 136, pp.138~ (2009)
- Kim, D. J., "A Study on the Relationship between cognitive function and senile depression and senile stress", Journal of the Korean Society of Clinical Examination and Sciences, 51(1), pp.111~ (2019)
- Kim, I. J., "Deep Learning : New Trends in Machine Learning", Journal of the Korean Telecommunications Society, 31(11), pp.52~ (2014)
- 김정균, "랜덤 포레스트를 이용한 심전도 기반 생체 인증", 전자공학회논문지, 54(6), pp.100~105 (2017), 대한전자공학회
- Kim, J. W., "The Effects of Economic Stabilization and Retirement Income Security Policy on Mental Health", Doctor, pp.2017
- 고기동, "우리나라 노인에서 건강 위험 행동과 정신 건강과의 연관성: 고령화 연구 패널(KLoSA)", Annals of geriatric medicine and research, 16(2), pp.66~73 (2012), 대한노인병학회[DOI]
- 김성진, "기업신용등급 예측을 위한 랜덤 포레스트의 응용", 산업혁신연구, 32(1), pp.187~211 (2016), 산업개발연구소[DOI]
- 김태호, "CART분석을 이용한 신도시지역의 지하철 역세권 설정에 관한 연구", 한국철도학회논문집, 11(3), pp.216~224 (2008), 한국철도학회
- Mitchell, M., "Machine Learning" (1997), McGraw-Hill
- Na, D. Y., "A Study on the Smart Farm Technology for Animal Welfare based on IoT using Machine Learning Algorithm", Doctor, pp.2019
- Irwin, M. R., "Screening for Depression in the Older Adult : Criterion Validity of the 10Item Center for Epidemiological Studies Depression Scale(CES-D)", Archives of Internal Medicine, 159(15), pp.1701~1704 (1999)
- Epidemiological Survey on the Actual Condition of Mental Diseases, "Ministry of Health and Welfare", 83~ (2006)
- 박준혁, "한국의 우울증 역학에 대한 고찰", 대한의사협회지, 54(4), pp.362~369 (2011), 대한의사협회
- Russell, D., "Living alone and depressive symptoms : The influence of gender, physical disability, and social support among Hispanic and non-Hispanic older adults", Journal of Gerontology Series B : Psychological Science and Social Sciences, 64(1), pp.95~104 (2009)
- 유현실, "A Study on Technology Acceptance of Elderly living Alone in Smart City Environment: Based on AI Speaker", 산경연구논집, 11(2), pp.41~48 (2020), 한국유통과학회
- 유진은, "랜덤 포레스트: 의사결정나무의 대안으로서의 데이터 마이닝 기법", 교육평가연구, 28(2), pp.427~448 (2015), 한국교육평가학회