The Journal of the Convergence on Culture Technology (문화기술의 융합)

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

Machine Learning-based Elderly Health Prediction with Various Factors of Elderly

다양한 노인 생활 지표를 활용한 기계학습 기반 노인 건강 요인 예측

  • 아잠 (가천대학교 IT융합공학과(컴퓨터공학전공)) ;
  • 이재형 (가천대학교 IT융합공학과(컴퓨터공학전공)) ;
  • 윤유림 (가천대학교 컴퓨터공학부(컴퓨터공학전공))
  • Received : 2024.08.20
  • Accepted : 2024.11.10
  • Published : 2024.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

The quality of life, frailty, economic activity, and other indicators are crucial for assessing older adults' overall well-being and health status. A comprehensive evaluation using this information helps predict the health status of older adults. This study aims to apply and compare machine learning-based prediction models for comprehensive health indicators of community-dwelling older adults. Utilizing data from 4,652 individuals provided by the Aging Research Panel, we assessed various machine learning techniques to fit the predictor variables. Our findings reveal that the LightGBM Regression model performed the best, with an RMSE of 5.082 and an MSE of 25.83. The Gradient Boosting model best predicted current health status, with an RMSE of 0.588 and an R-Square of 0.456. Additionally, the Random Forest model showed strong performance in predicting economic activity participation among older adults. These machine learning-based models offer valuable insights for evaluating health status and predicting economic activity participation, highlighting the importance of employing diverse methodologies for comprehensive predictions.

노인들의 삶의 질, 악력, 경제활동 등 다양한 지표들은 그들의 종합적인 복지와 건강 상태를 반영한다. 이러한 정보를 활용한 종합적인 평가는 노인의 건강 상태를 예측하는 데 유용하다. 본 연구에서는 지역사회 거주 노인의 건강을 예측하는 종합적인 지표에 대해 기계학습 기반 예측 모델을 적용하고 비교하는 것을 목표로 한다. 고령화연구패널에서 제공하는 4652명의 데이터를 활용하여 예측 변수에 맞게 다양한 머신러닝 기법을 사용하여 각 모델을 평가하였다. 그 결과, 악력 예측에는 LightGBM Regression 모형이 RMSE 5.082, MSE 25.83로 가장 우수한 성능을 보였으며, 현재 건강 상태 예측에서는 Gradient Boosting이 RMSE 0.588과 R-Square 0.456로 가장 좋은 성과를 보였다. 한편 고령층의 경제활동 참여에 대한 예측 결과는 Random Forest 모델이 우수함을 드러냈다. 이러한 기계학습 기반 예측 모델은 노인의 건강 상태 평가와 경제활동 참여 예측에 대한 방향성을 제시하며, 종합적인 예측을 위해 다양한 방법론을 수행하여야 함을 시사한다.

Keywords

Acknowledgement

이 논문은 정부(과학기술정보통신부, 교육부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(No.2022R1F1A1066017, NRF-2022S1A5C2A07090938)

References

  1. J. Min, "Effect of Social Engagement on Self-rated Health Trajectory among Korean Older Adults," Health and Social Welfare Review, 2013. 33(4): p. 105-123.
  2. S. M. Park, "Effects of Health Status on Life-Satisfaction of the Elderly -Focusing on the mediating and moderating effects of social activities and economic activities-," Journal of Welfare for the Aged, 2011. 53: p. 305-332. doi: 10.21194/kjgsw..53.201109.291
  3. K. Son and K. Kim, "Analysis of the Effects of Self-Perceived Health on Life Satisfaction and Mediating Effect of Social Activities of the Elderly by Age Group", The Journal of the Korea Contents Association, 2020. 20(7): p. 127-138. doi: 10.5392/JKCA.2020.20.07. 127
  4. W. Yoon, "The effects of usual source of care on Health-behaviors of chronic disease patients," Master dissertation, Seoul National University, 2014.
  5. C. Kim, "Characteristics of geriatric diseases," The Korean Journal of Medicine, 2006. 71(2): p. 844-847.
  6. https://survey.keis.or.kr/klosa/klosa04.jsp
  7. S. Kim, "Confidence, Happiness and Relationahip of the Participation Leisure Activities," Korea Sport Research 2006. 17(5): p. 561-571.
  8. S. H. Kim, "Benefits of Volunteering to Physical health, Depression, Social Support, and Meaning in Life among Older Adults," Journal of the Korea Gerontological Society, 2013. 33(1): p. 53-66.
  9. K. Pynnonen, et al., "Does social activity decrease risk for institutionalization and mortality in older people?" Journals of Gerontology Series B: Psychological Sciences and Social Sciences, 2012. 67(6): p. 765-774. doi: 10.1093/geronb/gbs076
  10. P. A. Thomas, "Trajectories of social engagement and mortality in late life," Journal of Aging and Health, 2012. 24(4): p. 547-568. doi: 10.1177/0898264311432310
  11. H. S. Gweon, "The Effect of Social Participation on the Life Satisfaction of the Elderly -Focusing on the Mediating Effects of Depression and Self-reported Health-," Korean Journal of Human Ecology, 2009, 18(5): p. 995-1008
  12. H. G. Koenig, et al., "Does religious attendance prolong survival? A six-year follow-up study of 3,968 older adults," Journals of Gerontology Series A: Biomedical Sciences and Medical Sciences, 1999. 54(7): p. M370-M376. doi: 10.1093/gerona/54.7.m370
  13. S. K. Lutgendorf,et al., "Religious participation, interleukin-6, and mortality in older adults," Health Psychology, 2004. 23(5): p. 465. doi: 10.1037/0278-6133.23.5.465
  14. J. A. Burr, J. Tavares, and J.E. Mutchler, "Volunteering and hypertension risk in later life," Journal of Aging and Health, 2011. 23(1): p. 24-51. doi: 10.1177/0898264310388272
  15. T. Y. Lum, and E. Lightfoot, "The effects of volunteering on the physical and mental health of older people," Research on aging, 2005. 27(1): p. 31-55. doi: 10.1177/0164027504271349
  16. E. P. Sabin, "Social relationships and mortality among the elderly," Journal of Applied Gerontology, 1993. 12(1): p. 44-60. doi: 10.1177/073346489301200105
  17. M.-S. Kim and J.-W. Ko, "The Effect of the Elderly's Leasure Activity on Their Health and the Mediating Role of Family Support," Journal of Welfare for the Aged, 2013. 60: p. 35-54. doi: 10.21194/kjgsw..60.201306.35
  18. H.-R. Kim and K.-W. Lee, "The Relationship between the Participation of the Female Elderly in the Leisure Activity, and Physical Health and a Sense of Happiness," Journal of Sport and Leisure Studies, 2008. 34: p. 671-680
  19. B. Kye, "Population aging, socioeconomic development and social inequality," Economy and Society, 2015. 106: p. 41-72.
  20. Y.-S. Koh, "A Exploratory Study on the Digital Aging Policies as Solutions for a Aging Society," Journal of Digital Convergence, 2016. 14(11): p. 115-123. doi: 10.14400/JDC.2016.14.11.115
  21. Y. Choi and Y. Yoon, "Data Preprocessing for Predictiong Sarcopenia Based on Machine Learning," The Journal of the Convergence on Culture Technology, 2023. 9(3): p. 737-744. doi: 10.17703/JCCT.2023.9.3.737
  22. E. Frank, M. A. Hall and I. H. Witten, The WEKA Workbench. Online Appendix for "Data Mining: Practical Machine Learning Tools and Techniques", Morgan Kaufmann, Fourth Edition, 2016.
  23. P. J. Kim, "An analytical study on automatic classification of domestic journal articles using random forest," Journal of the Korean Society for Information Management, 2019. 36(2): p. 57-77. doi: 10.3743/KOSIM.2019.36.2.057
  24. P. S. M. Reddy, "Decision tree regressor compared with random forest regressor for house price prediction in mumbai," Journal of Survey in Fisheries Sciences, 2023. 10(1S): p. 2323-2332. doi: 10.17762/sfs.v10i1S.465
  25. M. Kang, "How Design Elements of a Social Q&A Site Influence New Users' Continuance Behavior: An Application of Logistic Regression and XGBoost Techniques," Knowledge Management Research, 2023. 24(2): p. 161-183. doi: 10.15813/kmr.2023.24.2.008
  26. J.-H. Kim, "Machine Learning Classifier Models for Predicting Sarcopenia in the Elderly Based on Physical Factors," medRxiv, 2023: p. 2023.05. 03.23288546.
  27. K. Yongcharoenchaiyasit et al., "Gradient Boosting Based Model for Elderly Heart Failure, Aortic Stenosis, and Dementia Classification," IEEE Access, 2023. 11: p. 48677-48696. doi: 10.1109/ACCESS.2023.3276468
  28. S. Badgujar and A.S. Pillai. "Fall detection for elderly people using machine learning," in 2020 11th international conference on computing, communication and networking technologies (ICCCNT). 2020. IEEE. doi: 10.1109/ICCCNT49239.2020.9225494
  29. J. Wolfson et al., "A Naive Bayes machine learning approach to risk prediction using censored, time-to-event data," Statistics in medicine, 2015. 34(21): p. 2941-2957. doi: 10.1002/sim.6526
  30. J. H. Shin, B. Lee, and K.S. Park, "Detection of abnormal living patterns for elderly living alone using support vector data description," IEEE Transactions on Information Technology in Biomedicine, 2011. 15(3): p. 438-448. doi: 10.1109/TITB.2011.2113352
  31. X. Song et al. "Comparison of machine learning techniques with classical statistical models in predicting health outcomes," in MEDINFO 2004. 2004. IOS Press. doi: 10.3233/978-1-60750-949-3-736