Journal of Korean Biological Nursing Science

Korean society of Biological Nursing Science (한국기초간호학회)
권호 표지
DOI QR코드

DOI QR Code

Development of a fall prediction model for community-dwelling older adults in South Korea using machine learning: a secondary data analysis

머신러닝을 이용한 한국 지역사회 거주 노인의 낙상 예측 모형 구축: 2차 분석 연구

  • Received : 2024.08.27
  • Accepted : 2024.11.01
  • Published : 2024.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: This study aimed to develop a fall prediction model for community-dwelling older adults using machine learning. Methods: The present study was conducted with a secondary data analysis that used data from the 2020 national survey of older Koreans. Among 10,097 participants, data 177 were excluded due to incompleteness and 9,920 were included in the final analysis. Because of data imbalance, upsampling was performed to increase the number of individuals who fell. Forty-five independent variables for fall prediction were selected based on the fall risk factors from previous studies and univariate statistical analysis. The data were split into training and testing sets at an 80:20 ratio. Three machine learning algorithms-logistic regression, random forest, and artificial neural network-were used to develop a fall prediction model. Results: The random forest model outperformed the others, with an area under the curve of .91, accuracy of .94, precision of .94, recall of .74, and F1 score of .83. An analysis of feature importance revealed that satisfaction with health condition, visual difficulty, instrumental activities of daily living, performance of 400m walk, and cognitive ability were the top five features for fall prediction. Conclusion: The fall prediction model developed using machine learning demonstrated high model performance, implying its suitability for use as a primary screening tool for fall risk. Subjective satisfaction with one's health should be considered as an important factor in predicting falls in community-dwelling older adults. It is necessary for community health nurses to reinforce positive health awareness by continuous disease management and physical function improvement for older adults to prevent falls.

Keywords

Acknowledgement

This work was supported by Inha University Research Grant INHA-71603-1.

References

  1. Moreland B, Kakara R, Henry A. Trends in nonfatal falls and fall-related injuries among adults aged ≥ 65 years - United States, 2012-2018. Morbidity and Mortality Weekly Report. 2020;69(27):875-881. https://doi.org/10.15585/mmwr.mm6927a5
  2. Suh M, Kim DH, Cho I, Ham OK. Age and gender differences in fall-related factors affecting community-dwelling older adults. The Journal of Nursing Research. 2023;31(2):e270. https://doi.org/10.1097/jnr.0000000000000545
  3. Centers for Disease Control and Prevention. About older adult fall prevention 2024 [Internet]. Atlanta: Centers for Disease Control and Prevention; 2024 [cited 2024 Aug 5]. Available from: https://www.cdc.gov/falls/about/index.html
  4. Juel K, Sørensen J, Brønnum-Hansen H. Risk factors and public health in Denmark. Scandinavian Journal of Public Health. 2008;36(Suppl 1):11-227. https://doi.org/10.1177/1403494808097590
  5. Song J, Lee E. Health-related quality of life of elderly women with fall experiences. International Journal of Environmental Research and Public Health. 2021;18(15):7804. https://doi.org/10.3390/ijerph18157804
  6. Gade GV, Jørgensen MG, Ryg J, Riis J, Thomsen K, Masud T, et al. Predicting falls in community-dwelling older adults: a systematic review of prognostic models. BMJ Open. 2021;11(5):e044170. https://doi.org/10.1136/bmjopen-2020-044170
  7. National Institute for Health and Care Excellence. Falls in older people: assessing risk and prevention. London: National Institute for Health and Care Excellence; 2024 Jun 12 [cited 2024 Aug 5]. Available from: https://www.nice.org.uk/guidance/cg161
  8. Yun ES. Fall prediction model for community-dwelling elders based on gender. Journal of Korean Academy of Nursing. 2012;42(6):810-818. https://doi.org/10.4040/jkan.2012.42.6.810
  9. Park NJ, Shin YS. Predictors of accidental falls in the community-dwelling elderly by age. Journal of Korean Academy of Community Health Nursing. 2019;30(2):141-149. https://doi.org/10.12799/jkachn.2019.30.2.141
  10. Zhang L, Wang Y, Niu M, Wang C, Wang Z. Machine learning for characterizing risk of type 2 diabetes mellitus in a rural Chinese population: the Henan Rural cohort study. Scientific Reports. 2020;10(1):4406. https://doi.org/10.1038/s41598-020-61123-x
  11. Hyun JK. Prediction of diabetic neuropathy using machine learning techniques. The Journal of Korean Diabetes. 2022;23(4):238-244. https://doi.org/10.4093/jkd.2022.23.4.238
  12. Lam FMH, Leung JCS, Kwok TCY. The clinical potential of frailty indicators on identifying recurrent fallers in the community: The Mr. Os and Ms. OS cohort study in Hong Kong. Journal of the American Medical Directors Association. 2019;20(12):1605-1610. https://doi.org/10.1016/j.jamda.2019.06.019
  13. Makino K, Lee S, Bae S, Chiba I, Harada K, Katayama O, et al. Simplified decision-tree algorithm to predict falls for community-dwelling older adults. Journal of Clinical Medicine. 2021;10(21):5184. https://doi.org/10.3390/jcm10215184
  14. Thapa R, Garikipati A, Shokouhi S, Hurtado M, Barnes G, Hoffman J, et al. Predicting falls in long-term care facilities: machine learning study. Journal of Medical Internet Research Aging. 2022;5(2):e35373. https://doi.org/10.2196/35373
  15. Lee Y, Kim S, Hwang N, Im J, Joo B, Namgoong E, et al. 2020 national survey of older Koreans. Policy report. Seoul: Ministry of Health and Welfare; 2020 Report No.: 11-1352000-000672-12.
  16. Lee CK. Factors influencing falls in the community-dwelling elderly: data from the 2020 national survey of older people: a secondary analysis study. Journal of Korean Gerontological Nursing. 2023;25(3):320-331. https://doi.org/10.17079/jkgn.2023.00094
  17. World Health Organization. Medication safety in polypharmacy. Technical report. Geneva: World Health Organization; 2019 Nov. Report No.: WHO-UHC-SDS-2019.11.
  18. Zhang F, Ferrucci L, Culham E, Metter EJ, Guralnik J, Deshpande N. Performance on five times sit-to-stand task as a predictor of subsequent falls and disability in older persons. Journal of Aging and Health. 2013;25(3):478-492. https://doi.org/10.1177/0898264313475813
  19. Lee YH, Han GS, Yoon SJ, Lee YK, Kim CH, Kim JL, et al. The development of physical functioning scale for community-dwelling older persons. Journal of Preventive Medicine and Public Health. 2002;35(4):359-374.
  20. Posner BM, Jette AM, Smith KW, Miller DR. Nutrition and health risks in the elderly: the nutrition screening initiative. American Journal of Public Health. 1993;83(7):972-978. https://doi.org/10.2105%2Fajph.83.7.972 https://doi.org/10.2105%2Fajph.83.7.972
  21. Madley-Dowd P, Hughes R, Tilling K, Heron J. The proportion of missing data should not be used to guide decisions on multiple imputation. Journal of Clinical Epidemiology. 2019;110:63-73. https://doi.org/10.1016/j.jclinepi.2019.02.016
  22. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research. 2002;16:321-357. https://doi.org/10.48550/arXiv.1106.1813
  23. Lee JY, Jin Y, Piao J, Lee SM. Development and evaluation of an automated fall risk assessment system. International Journal for Quality in Health Care. 2016;28(2):175-182. https://doi.org/10.1093/intqhc/mzv122
  24. Kuhn M, Johnson K. Applied predictive modeling. New York: Springer; 2013.
  25. Hosmer Jr. DW, Lemeshow S, Sturdivant RX. Applied logistic regression. Hoboken: John Wiley & Sons; 2013.
  26. James G, Witten D, Hastie T, Tibshirani R. An introduction to statistical learning. New York: Springer; 2013.
  27. Lunetta KL, Hayward LB, Segal J, Van Eerdewegh P. Screening large-scale association study data: exploiting interactions using random forests. BMC Genetics. 2004;5:1-13. https://doi.org/10.1186/1471-2156-5-32
  28. Strobl C, Boulesteix AL, Zeileis A, Hothorn T. Bias in random forest variable importance measures: illustrations, sources and a solution. BMC Bioinformatics. 2007;8:1-21. https://doi.org/10.1186/1471-2105-8-25
  29. Miotto R, Wang F, Wang S, Jiang X, Dudley JT. Deep learning for healthcare: review, opportunities and challenges. Briefings in Bioinformatics. 2018;19(6):1236-1246. https://doi.org/10.1093/bib/bbx044
  30. Bengio Y, Courville A, Vincent P. Representation learning: a review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2013;35(8):1798-1828. https://doi.org/10.1109/tpami.2013.50
  31. Speiser JL, Callahan KE, Houston DK, Fanning J, Gill TM, Guralnik JM, et al. Machine learning in aging: an example of developing prediction models for serious fall injury in older adults. The Journals of Gerontology: Series A. 2021;76(4):647-654. https://doi.org/10.1093/gerona/glaa138
  32. Park SH, Choi YK, Hwang JH. Predictive validity of the STRATIFY for fall screening assessment in acute hospital setting: a meta-analysis. Korean Journal of Adult Nursing. 2015;27(5):559-571. http://doi.org/10.7475/kjan.2015.27.5.559
  33. Jahandideh S, Hutchinson AF, Bucknall TK, Considine J, Driscoll A, Manias E, et al. Using machine learning models to predict falls in hospitalised adults. International Journal of Medical Informatics. 2024;187:105436. https://doi.org/10.1016/j.ijmedinf.2024.105436
  34. Jun HJ, Choi JY. Factors influencing fall experiences among the older adults in community: using the 2021 community health survey. Korean Journal of Occupational Health Nursing. 2023;32(2):79-88. https://doi.org/10.5807/kjohn.2023.32.2.79
  35. Sun Y, Fan J. Fear of falling and self-rated health among elderly in communities. Chinese General Practice. 2020;23(14):1733-1739. https://doi.org/10.12114/j.issn.1007-9572.2019.00.561
  36. Ang GC, Low SL, How CH. Approach to falls among the elderly in the community. Singapore Medical Journal. 2020;61(3):116-121. https://doi.org/10.11622/smedj.2020029
  37. Seo D, Shon C. Factors influencing satisfaction on home visiting health care service of the elderly based on the degree of chronic diseases. Journal of the Korean Gerontological Society. 2021;41(2):271-284. https://doi.org/10.31888/JKGS.2021.41.2.271
  38. Park JH, Suh WS. The Effect of inpatient elderly patients' with chronic diseases on fall experience. Korean Journal of Hospital Management. 2021;26(4):29-37.
  39. Immonen M, Haapea M, Similä H, Enwald H, Keränen N, Kangas M, et al. Association between chronic diseases and falls among a sample of older people in Finland. BMC Geriatrics. 2020;20(1):225. https://doi.org/10.1186/s12877-020-01621-9
  40. Dormosh N, van de Loo B, Heymans MW, Schut MC, Medlock S, van Schoor NM, et al. A systematic review of fall prediction models for community-dwelling older adults: comparison between models based on research cohorts and models based on routinely collected data. Age and Ageing. 2024;53(7):afae131. https://doi.org/10.1093/ageing/afae131
  41. Park H, Satoh H, Miki A, Urushihara H, Sawada Y. Medications associated with falls in older people: systematic review of publications from a recent 5-year period. European Journal of Clinical Pharmacology. 2015;71(12):1429-1440. https://doi.org/10.1007/s00228-015-1955-3