Wide & Deep Learning Model을 이용한 노인의 우울증 예측
Prediction of Depression in Older Adults Using Wide & Deep Learning Model
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: This study aims to suggest a depression prediction model using variables indirectly related to depression, which helps determine whether the target is depressed. Methods: This study using Korea Institute for Health and Social Affairs (KIHSA)’s 2011, 2014, 2017 National Survey of Older Kore- ans, and the total number of subjects of the study is 30,571 elderly people 65 years of age or older. Results: The analysis way is deep learning especially Wide & Deep Learning model that separately learns simple data and complex data. The dependent variable is depression, and the independent variable is a total of 30 variables related to personal attributes, economic status, human relationships, health status, health behavior, and life satisfaction. As a result of the main study, all the independent variables used were found to be correlated with depression, performance of Wide & Deep model is 77.9% accuracy, 65.7% recall, 73.8% precision, 85.5% specificity, 69.5% F1-score, 85.3% AUROC, 90.0% AUPRC. Conclusions: It is expected that it will be helpful for the welfare of the elderly by searching for depressed patients at a lower cost and searching for potential depressed patients who want to hide their depression.
Abstract
Objectives: This study aims to suggest a depression prediction model using variables indirectly related to depression, which helps determine whether the target is depressed. Methods: This study using Korea Institute for Health and Social Affairs (KIHSA)’s 2011, 2014, 2017 National Survey of Older Kore- ans, and the total number of subjects of the study is 30,571 elderly people 65 years of age or older. Results: The analysis way is deep learning especially Wide & Deep Learning model that separately learns simple data and complex data. The dependent variable is depression, and the independent variable is a total of 30 variables related to personal attributes, economic status, human relationships, health status, health behavior, and life satisfaction. As a result of the main study, all the independent variables used were found to be correlated with depression, performance of Wide & Deep model is 77.9% accuracy, 65.7% recall, 73.8% precision, 85.5% specificity, 69.5% F1-score, 85.3% AUROC, 90.0% AUPRC. Conclusions: It is expected that it will be helpful for the welfare of the elderly by searching for depressed patients at a lower cost and searching for potential depressed patients who want to hide their depression.
참고문헌 (22)
- "2020 Senior citizen statistics. Press release (2020.09.28.)"[URL]
- The aging world: 2015. U.S. census bureau, international population reports, "He W", U.S. Government Publishing Office, ~ (2016)
- Epidemiologic study of geriatric depression in an urban area in Korea, "Lee MS", Korean Association for Geriatric Psychiatry, 154~163 (2000)
- A fact sheet of statistics on suicide with information on treatments and suicide prevention, "National Institute of Mental Health", National Institute of Mental Health, ~ (2010)
- Jeon HJ, "Lifetime prevalence and correlates of suicidal ideation, plan, and single and multiple attempts in a Korean nationwide study", J Nerv Ment Dis, 198(9), pp.643~646 (2010)[DOI]
- 허준수, "노인의 우울에 영향을 미치는 요인에 관한 연구", 정신건강과 사회복지, (13), pp.7~35 (2002), 한국정신건강사회복지학회
- 김은령, "만성 관절염 노인환자의 주관적 건강상태와 우울 간의 관계에 미치는 사회적 자본의 상호작용 효과", 보건과 사회과학, (33), pp.59~83 (2013), 한국보건사회학회
- 박재규, "한국 성인 남녀의 우울증 변화에 영향을 미치는 요인 분석", 보건과 사회과학, (29), pp.99~128 (2011), 한국보건사회학회
- Ware JE, "The assessment of health status: Application of social science to clinical medicine and health policy", pp.204~228 (1989), Rutgers University Press
- 오영희, "우리나라 노인의 주관적 건강인식과 신체적 및 정신적 기능상태의 관련성 연구", 한국노년학, 26(3), pp.461~476 (2006), 한국노년학회
- 남연희, "노인의 주관적인 건강상태에 영향을 미치는 요인에 관한 연구", 한국가족복지학, 16(4), pp.145~162 (2011), 한국아동가족복지학회
- Johnson RJ, "The structure of health status among older adults: disease, disability, functional limitation, and perceived health", J Health Soc Behav, 34, pp.105~121 (1993)
- Fehir JS, "Self-rated health status, self efficacy, motivation, and selected demographics as determinants of health-promoting life style", pp.1989
- Greenberg SA, "The geriatric depression scale(GDS)", Best Pract Nurs Care Older Adults, 4, pp.1~2 (2012)
- Graham JW, "Missing data analysis : making it work in the real world", Ann Rev Psychol, 60, pp.549~576 (2009)[DOI]
- Ron K, "A study of cross-validation and bootsrap for accuracy estimation and model selection", Proceedings of the 14th International Joint Conference on Artificial Intelligence, pp.1137~1145 (1995)
- Cheng HT, "Wide & Deep Learning for recommender systems", DLRS 2016: Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, pp.7~10 (2016)
- Hoffer E, "Train longer, generalize better: closing the generalization gap in large batch training of neural networks", Proceedings of the 31st International Conference on Neural Information Processing System, pp.1729~1739 (2017)
- Beom-Seok SEO, "A Study on the Prediction Model of the Elderly Depression", 산경연구논집, 11(7), pp.29~40 (2020), 한국유통과학회
- Kim JH, "A predicting depression among senior citizens using smart-toy interaction data", Proceedings of the Korean Information Science Society Conference, pp.136~138 (2020)
- 강상경, "Andersen 모형을 이용한 노인 우울 예측요인", 노인복지연구, (49), pp.7~30 (2010), 한국노인복지학회[DOI]
- Su D, "Use of machine learning approach to predict depression in the elderly in China : a longitudinal study", J Affect Disord, 282, pp.289~298 (2021)[DOI]