Mild Cognitive Impairment Prediction Model of Elderly in Korea Using Restricted Boltzmann Machine

제한된 볼츠만 기계학습 알고리즘을 이용한 우리나라 지역사회 노인의 경도인지장애 예측모형

  • Byeon, Haewon (Department of Speech Language Pathology, Honam University)
  • 변해원 (호남대학교 보건과학대학 언어치료학과)
  • Received : 2019.07.08
  • Accepted : 2019.08.20
  • Published : 2019.08.28


Early diagnosis of mild cognitive impairment (MCI) can reduce the incidence of dementia. This study developed the MCI prediction model for the elderly in Korea. The subjects of this study were 3,240 elderly (1,502 men, 1,738 women) aged 65 and over who participated in the Korean Longitudinal Survey of Aging (KLoSA) in 2012. Outcome variables were defined as MCI prevalence. Explanatory variables were age, marital status, education level, income level, smoking, drinking, regular exercise more than once a week, average participation time of social activities, subjective health, hypertension, diabetes Respectively. The prediction model was developed using Restricted Boltzmann Machine (RBM) neural network. As a result, age, sex, final education, subjective health, marital status, income level, smoking, drinking, regular exercise were significant predictors of MCI prediction model of rural elderly people in Korea using RBM neural network. Based on these results, it is required to develop a customized dementia prevention program considering the characteristics of high risk group of MCI.

JKOHBZ_2019_v9n8_248_f0001.png 이미지

Fig. 1. Concept of Restricted Boltzmann Machines [9]

JKOHBZ_2019_v9n8_248_f0002.png 이미지

Fig. 2. Input path of Restricted Boltzmann Machines [9]

JKOHBZ_2019_v9n8_248_f0003.png 이미지

Fig. 3. Weighted input path of Restricted Boltzmann Machines [9]

JKOHBZ_2019_v9n8_248_f0004.png 이미지

Fig. 4. ROC curve of Restricted Boltzmann Machines

Table 1. Characteristics of the subjects based on MCI, n(%)

JKOHBZ_2019_v9n8_248_t0001.png 이미지

Table 2. Relative importance of inputs

JKOHBZ_2019_v9n8_248_t0002.png 이미지


Supported by : National Research Foundation of Korea(NRF)


  1. Ministry of Health & Welfare. (2013). Nationwide Study on the Prevalence of Dementia in Korean Elders 2012. Sejong : Ministry of Health & Welfare.
  2. S. Kim. (2014). Analysis on Management Policies for the Dementia. Seoul : National Assembly Budget Office.
  3. P. Anand & B. Singh. (2013). A review on cholinesterase inhibitors for Alzheimer's disease. Archives of pharmacal research, 36(4), 375-399. DOI : 10.1007/s12272-013-0036-3.
  4. H. Byeon et al. (2015). Association of alcohol drinking with verbal and visuospatial memory impairment in older adults: Clinical Research Center for Dementia of South Korea (CREDOS) study. International Psychogeriatrics, 27(3), 455-461. DOI : 10.1017/S104161021400146X.
  5. H. A. Tuokko & D. F. Hultsch. (2013). Mild cognitive impairment: International perspectives. New York : Psychology Press.
  6. G. Cheng, C. Huang, H. Deng & H. Wang. (2012). Diabetes as a risk factor for dementia and mild cognitive impairment: a meta-analysis of longitudinal studies. Internal medicine journal, 42(5), 484-491. DOI : 10.1111/j.1445-5994.2012.02758.x.
  7. T. Etgen, D. Sander, H. Bickel & H. Forstl. (2011). Mild cognitive impairment and dementia: the importance of modifiable risk factors. Deutsches Arzteblatt International, 108(44), 743-750 DOI : 10.3238/arztebl.2011.0743.
  8. R. C. Petersen, B. Caracciolo, C. Brayne, S. Gauthier, V. Jelic & L. Fratiglioni. (2014). Mild cognitive impairment: a concept in evolution. Journal of internal medicine, 275(3), 214-228. DOI : 10.1111/joim.12190.
  9. Sky mind. (2019). Restricted Boltzmann Machines. Enterprise ML Platform.
  10. H. Larochelle, M. Mandel, R. Pascanu & Y. Bengio (2012). Learning algorithms for the classification restricted boltzmann machine. Journal of Machine Learning Research, 13, 643-669.
  11. Korea Labor Institute. (2014). Korean Longitudinal Survey of Ageing 2011. Sejong : Korea Labor Institute.
  12. D. W. Appel & T. K. Aldrich. (2003). Smoking cessation in the elderly. Clinics in geriatric medicine, 19(1), 77-100.