Physical Therapy Rehabilitation Science

  • 제12권2호
  • /
  • Pages.80-91
  • /
  • 2023
  • /
  • 2287-7576(pISSN)
  • /
  • 2287-7584(eISSN)
물리치료재활과학회 (korean Academy of Physical Therapy Rehabilitation Science)
권호 표지
DOI QR코드

DOI QR Code

A Comparative Study of Predictive Factors for Hypertension using Logistic Regression Analysis and Decision Tree Analysis

  • SoHyun Kim (Department of Integrative Medicine, The Graduate School, Nambu University) ;
  • SungHyoun Cho (Department of Physical Therapy, Nambu University)
  • 투고 : 2023.02.07
  • 심사 : 2023.04.11
  • 발행 : 2023.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Objective: The purpose of this study is to identify factors that affect the incidence of hypertension using logistic regression and decision tree analysis, and to build and compare predictive models. Design: Secondary data analysis study Methods: We analyzed 9,859 subjects from the Korean health panel annual 2019 data provided by the Korea Institute for Health and Social Affairs and National Health Insurance Service. Frequency analysis, chi-square test, binary logistic regression, and decision tree analysis were performed on the data. Results: In logistic regression analysis, those who were 60 years of age or older (Odds ratio, OR=68.801, p<0.001), those who were divorced/widowhood/separated (OR=1.377, p<0.001), those who graduated from middle school or younger (OR=1, reference), those who did not walk at all (OR=1, reference), those who were obese (OR=5.109, p<0.001), and those who had poor subjective health status (OR=2.163, p<0.001) were more likely to develop hypertension. In the decision tree, those over 60 years of age, overweight or obese, and those who graduated from middle school or younger had the highest probability of developing hypertension at 83.3%. Logistic regression analysis showed a specificity of 85.3% and sensitivity of 47.9%; while decision tree analysis showed a specificity of 81.9% and sensitivity of 52.9%. In classification accuracy, logistic regression and decision tree analysis showed 73.6% and 72.6% prediction, respectively. Conclusions: Both logistic regression and decision tree analysis were adequate to explain the predictive model. It is thought that both analysis methods can be used as useful data for constructing a predictive model for hypertension.

키워드

과제정보

이 성과는 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(No. 2022R1F1A1067604).

참고문헌

  1. Doyle AE. Hypertension and vascular disease. Am J Hypertens. 1991;4(2):103-106. https://doi.org/10.1093/ajh/4.2.103S
  2. Samadian F, Dalili N, Jamalian A. Lifestyle Modifications to Prevent and Control Hypertension. Iran J Kidney Dis. 2016;10(5):237-63.
  3. Wu L, Yang S, He Y, Liu M, Wang Y, Wang J, et al. Association between passive smoking and hypertension in Chinese non-smoking elderly women. Hypertens Res. 2017;40(4):399-404. https://doi.org/10.1038/hr.2016.162
  4. Wang Y, Yao Y, Chen Y, Zhou J, Wu Y, Fu C, et al. Association between Drinking Patterns and Incident Hypertension in Southwest China. Int J Res Public Health. 2022;19(7):3801
  5. Kulkarni S, O'Farrell I, Erasi M, Kochar MS. Stress and hypertension. WMJ. 1998;97(11):34-8.
  6. Byeon HW, Cho SH. The Predictive Modeling of Middle-aged Hypertension using Integrated Method of Decision Tree and Neural Network. AJMAHS. 2015;5(2):9-18. https://doi.org/10.14257/AJMAHS.2015.04.25
  7. ou Y, Teng W, Wang J, Ma G, Ma A, Wang J, et al. Hypertension and physical activity in middle-aged and older adults in China. Sci Rep. 2018;8(1):16098.
  8. Kim HS, Jung SH, Park SK. Decision-Tree Analysis to Predict Blood Pressure Control Status among Hypertension Patients Taking Antihypertensive Medications. J Korean Biol Nurs Sci. 2019;21(1):85-97. https://doi.org/10.7586/jkbns.2019.21.1.85
  9. Zhao H, Zhang X, Xu Y, Gao L, Ma Z, Sun Y, et al. Predicting the Risk of Hypertension Based on Several Easy-to-Collect Risk Factors: A Machine Learning Method. Front Public Health. 2021;9:619429.
  10. Anh DT, Takakura H, Asai M, Ueda N, Shojaku H. Application of machine learning in the diagnosis of vestibular disease. Sci Rep. 2022;12(1):20805.
  11. Dritsas E, Trigka M. Machine Learning Methods for Hypercholesterolemia Long-Term Risk Prediction. Sensors (Basel). 2022;22(14):5365.
  12. Heo J, Yoon JG, Park H, Kim YD, Nam HS, Heo JH. Machine Learning-Based Model for Prediction of Outcomes in Acute Stroke. Stroke. 2019;50(5):1263-5. https://doi.org/10.1161/STROKEAHA.118.024293
  13. Lee YW, Choi JW, Shin EH. Machine learning model for predicting malaria using clinical information. Comput Biol Med. 2021;129:104151.
  14. Kwon TW, Koo YH. Comparative Analysis of Prediction Taekwondo Trainee's Defection using Decision Tree and Logistic Regression. KSSS. 2008;17(2):71-83.
  15. Park MH, Choi SR, Shin AM, Koo CH. Analysis of the Characteristics of the Older Adults with Depression Using Data Mining Decision Tree Analysis. J Korean Acad Nurs. 2013;43(1):1-10. https://doi.org/10.4040/jkan.2013.43.1.1
  16. Choi JH, Seo DS. Decision Trees and Its Applications. JKOS. 1999;4(1):61-83.
  17. Open Data. Korea Health Panel Annual Data 2019 [Internet]. Sejong and Won ju: Korea Institute for Health and Social Affiairs and National Health Insurance Service; 2020 [cited 2023 Feburary 4]. Available from: https://www.khp.re.kr:444/web/notice/board/view.do?bbsid=53&seq=2832
  18. Rhee EJ. Current status of obesity treatment in Korea: based on the 2020 Korean Society for the Study of Obesity guidelines for obesity management. J Korean Med Assoc. 2022;65(7):388-92. https://doi.org/10.5124/jkma.2022.65.7.388
  19. Barsasella D, Bah K, Mishra P, Uddin M, Dhar E, Suryani DL, et al. A Machine Learning Model to Predict Length of Stay and Mortality among Diabetes and Hypertension Inpatients. Medicina (Kaunas). 2022;58(11):1568.
  20. Oh TS, Kim DK, Won CW, Kim SY, Jeong EJ, Yang JS, et al. A Machine-Learning-Based Risk Factor Analysis for Hypertension: Korea National Health and Nutrition Examination Survey 2016-2019. KJFP. 2022;12(3):173-8. https://doi.org/10.21215/kjfp.2022.12.3.173
  21. Vasan RS, Beiser A, Seshadri S, Larson MG, Kannel WB, D'Agostino RB, et al. Residual lifetime risk for developing hypertension in middle-aged women and men: The Framingham Heart Study. JAMA. 2002;287(8):1003-10. https://doi.org/10.1001/jama.287.8.1003
  22. Ghanbari J, Mohammadpoorasl A, Jahangiry L, Farhangi MA, Amirzadeh J, Ponnet K. Subgroups of lifestyle patterns among hypertension patients: a latent-class analysis. BMC Med Res methodol. 2018;18(1):127.
  23. Kim SI, Woo SJ, Jung YH. Factors Related to Hypertension Patients' Quality of Life: The 7th Korean National Health and Nutrition Examination (1st Year, 2016). Leisure Activity Types and Depressive Symptoms among Middle-Aged People Living Alone JKSSCHE. 2020;21(1):61-74.
  24. Kwon MS, Noh GY, Jang JH. A study on relationships between health literacy, disease-related knowledge and compliance to medical recommendations in patients with hypertension. J Korean Pubilc Health Nurs. 2013;27(1):190-202.
  25. Kang EN, Kim HJ, Kim YS. Leisure Activity Types and Depressive Symptoms among Middle-Aged People Living Alone. HSWR. 2017;37(2):184-215.
  26. Jeon DJ, Kim SH, Park SH, Yoon HJ, Kim SG, Kim JH. The Prevalence and Psychosocial Correlates of Depressive Symptoms in Patients with Hypertension. J Korean Soc Biol Ther Psychiatry. 2019;25(3):213-21.
  27. Ramezankhani A, Azizi F, Hadaegh F. Associations of marital status with diabetes, hypertension, cardiovascular disease and all-cause mortality: a long term follow-up study. PLoS One. 2019;14(4):e0215593.
  28. Tuoyire DA, Ayetey H. Gender differences in the association between marital status and hypertension in Ghana. J Biosoc Sci. 2019;51(3):313-34. https://doi.org/10.1017/S0021932018000147
  29. Lipowicz A, Lopuszanska M. Marital differences in blood pressure and the risk of hypertension among Polish men. Eur J epidemiol. 2005;20(5):421-7. https://doi.org/10.1007/s10654-005-1752-x
  30. Boutcher YN, Boutcher SH. Exercise intensity and hypertension: what's new? Journal of human hypertension. J Hum Hypertens. 2017;31(3):157-64. https://doi.org/10.1038/jhh.2016.62
  31. Ruivo JA, Alcantara P. Hypertension and exercise. Rev Port Cardiol. 2012;31(2):151-8. https://doi.org/10.1016/j.repc.2011.12.012
  32. Day E, Rudd JHF. Alcohol use disorders and the heart. Addiction. 2019;114(9):1670-8. https://doi.org/10.1111/add.14703
  33. Sleight P. Smoking and hypertension. Clin Exp Hypertens. 1993;15(6):1181-92. https://doi.org/10.3109/10641969309037104
  34. Choi JH, Park JH, Choi BG. Association between Education Level and Hypertension in Korean Adults Over 30 Years Old: Korea National Health and Nutrition Examination Survey 2019. KJFP. 2022;12(4):247-53. https://doi.org/10.21215/kjfp.2022.12.4.247
  35. Sohn K. Relationship of smoking to hypertension in a developing country. Glob Heart. 2018;13(4):285-92. https://doi.org/10.1016/j.gheart.2018.01.004
  36. Lee HS, Kwun IS, Kwon CS. Prevalence of Hypertension and Related Risk Factors of the Older Residents in Andong Rural Area. JKSFSN. 2009; 38(7):852-61. https://doi.org/10.3746/jkfn.2009.38.7.852
  37. Eom JS, Lee TR, Park SJ, Ahn YJ, Chung YJ. The risk factors of the pre-hypertension and hypertension of rural inhabitants in Chungnam-do. J Nutr Health. 2008;41(8):742-53.
  38. Lee HJ, Lee HS, Lee YN, Jang YA, Moon JJ, Kim CI. Nutritional environment influences hypertension in the middle-aged Korean adults-Based on 1998 & 2001 National Health and Nutrition Survey. Korean J Community Nutr. 2007;12(3):272-83.
  39. Ambrose JA, Barua RS. The pathophysiology of cigarette smoking and cardiovascular disease: an update. Journal of the American College of Cardiology. J Am Coll Cardiol. 2004;43(10):1731-7. https://doi.org/10.1016/j.jacc.2003.12.047
  40. Biddinger KJ, Emdin CA, Haas ME, Wang M, Hindy G, Ellinor PT, et al. Association of Habitual Alcohol Intake With Risk of Cardiovascular Disease. JAMA netw open. 2022;5(3):e223849.
  41. Di Chiara T, Scaglione A, Corrao S, Argano C, Pinto A, Scaglione R. Education and hypertension: impact on global cardiovascular risk. Acta cardiol. 2017;72(5):507-13. https://doi.org/10.1080/00015385.2017.1297626
  42. Kim JE. Measuring the Level of Health Literacy and Influence Factors: Targeting the Visitors of a University Hospital's Outpatient Clinic. J Korean Clin Nurs Res. 2011;17(1):40-7.
  43. Diaz ME. Hypertension and obesity. J Hum Hypertens. 2002;16(1):18-22. https://doi.org/10.1038/sj.jhh.1001335
  44. Rahman M, Zaman MM, Islam JY, Chowdhury J, Ahsan HN, Rahman R, et al. Prevalence, treatment patterns, and risk factors of hypertension and pre-hypertension among Bangladeshi adults. Journal of human hypertension. J Hum Hypertens. 2018;32(5):334-48. https://doi.org/10.1038/s41371-017-0018-x
  45. Lee SH, Park YM, Han KD, Yang JH, Lee SW, Lee SS, et al. Obesity-related hypertension: Findings from The Korea National Health and Nutrition Examination Survey 2008-2010. PLoS one. 2020;15(4):e0230616.
  46. Leenen FH, McInnis NH, Fodor G. Obesity and the prevalence and management of hypertension in Ontario, Canada. Am J Hypertens. 2010;23(9):1000-6. https://doi.org/10.1038/ajh.2010.93
  47. Choi YH. Is self-rated Health a Sufficient Proxy for True Health? KJGSW. 2018;73(4):7-28. https://doi.org/10.21194/kjgsw.73.4.201812.7
  48. Chang DM, Park IS, Yang JH. Related Factors of Awareness, Treatment, and Control of Hypertension in Korea : Using the Fourth Korea National Health & Nutrition Examination Survey. J Digit Converge. 2013;3(5):6-7.
  49. Kim KY. Risk factors for hypertension in elderly people aged 65 and over, and adults under age 65. JKAIS. 2019;20(1):162-9.
  50. Yi YM, Park YH. Factors Related to Subjective Health Status in Community-Dwelling Older Adults Living Alone on Low Income. The J of Mus and Joint Health. 2022;29(3):205-17.
  51. Mitchell TM. Machine learning. 1st ed. New York: McGraw Hill; 2007.
  52. Lee HH, Chung SH, Choi EJ. A case study on machine learning applications and performance improvement in learning algorithm. J Digit Converge. 2016;14(2): 245-258. https://doi.org/10.14400/JDC.2016.14.2.245
  53. Huang X, Cao T, Chen L, Li J, Tan Z, Xu B, et al. Novel Insights on Establishing Machine Learning-Based Stroke Prediction Models Among Hypertensive Adults. Front Cardiovasc Med. 2022;9:901240.
  54. Shah W, Aleem M, Iqbal MA, Islam MA, Ahmed U, Srivastava G, et al. A Machine-Learning-Based System for Prediction of Cardiovascular and Chronic Respiratory Diseases. J Healthc Eng. 2021;2021:2621655.
  55. Park IS, Yong WS, Kim YM, Kang SH, Han JT. A development of a tailored follow up management model using the data mining technique on hypertension. KSS. 2008;21(4):639-47.
  56. Yoo JE. Random forests, an alternative data mining technique to decision tree. J Educ Evaluation. 2015;28(2):427-448.
  57. Uddin S, Khan A, Hossain ME, Moni MA. Comparing different supervised machine learning algorithms for disease prediction. BMC. 2019;19(1):281.
  58. Seo JD. Foreign Exchange Rate Forecasting Using the GARCH extended Random Forest Model. JIEB. 2016;29(5):1607-1628.
  59. Breiman L. Random forests. Machine learning. 2001;45:5-32. https://doi.org/10.1023/A:1010933404324
  60. Jeong SW, Lee MJ, Yoo SY. Machine Learning-based Stroke Risk Prediction using Public Big Data. J AdvNaving Technol. 2021;25(1):96-101.
  61. Hyun JK. Prediction of Diabetic Neuropathy Using Machine Learning Techniques. JKD. 2022;23(4):338-244