Original Article

The Prediction Models for High-Risk Population of Stroke Based on Logistic Regressive Analysis and Lightgbm Algorithm Separately

Abstract

Background: We aimed to investigate the high-risk factors of stroke through logistic regressive analysis and using LightGBM algorithm separately. The results of the two models were compared for instructing the prevention of stroke.

Methods: Samples of residents older than 40 years of age were collected from two medical examination centers in Jiaxing, China from 2018 to 2019. Among the total 2124 subjects, 1059 subjects were middle-aged people (40-59 years old) and 1065 subjects were elder-aged people (≥60 years old). Their demographic characteristics, medical history, family history, eating habits etc. were recorded and separately input into logistic regressive analysis and LightGBM algorithm to build the prediction models of high-risk population of stroke. Four values including F1 score, accuracy, recall rate and AUROC were compared between the two models.

Results: The risk factors of stroke were positively correlated with age, while negatively correlated with the frequency of fruit consumption and taste preference. People with low-salt diet were associated with less risk of stroke than those with high-salt diet, and male had higher stroke risk than female. Meanwhile, the risk factors were positively correlated with the frequency of alcohol consumption in the middle-aged group, and negatively correlated with the education level in the elder-aged group. Furthermore, the four values from LightGBM were higher than those from logistic regression, except for the recall value of the middle-aged group.

Conclusion: Age, gender, family history of hypertension and diabetes, the frequency of fruit consumption, alcohol and dairy products, taste preference, and education level could as the risk predictive factors of stroke. The Model of using LightGBM algorithm is more accurate than that using logistic regressive analysis.

1. World Health Organization (2010). World Health Report 2010: Changing history.
2. Wang L, Liu J, Yang Y (2018). Essen-tials of report on the prevention for Chinese stroke 2017. Chin J Cerebrovasc Dis, 15(11):611-617.
3. Lee H, Nam YS, Lee KM (2015). Develop-ment-assistance Strategies for Stroke in Low- and Middle-income Countries. J Korean Med Sci, 30(Suppl 2):139-142.
4. Chhabra M, Sharma A, Ajay KR, et al (2019). Assessment of risk factors, cost of treatment and therapy outcome in stroke patients: evidence from cross-sectional study. Expert Rev Pharmacoecon Outcomes Res, 19(5):575-580.
5. Guo L, Hu R, Gong W, et al (2017). Re-search progress on risk factors of stroke. Chin J Gerontol, 37(17):4413-4416.
6. National Health Commission of the Peo-ple’s Republic of China. (2013). Technical Specification for Stroke Screening and Prevention. Chinese Journal of the Frontiers of Medical Science (Electronic Version), 5(09):44-50.
7. Zhao D, Liu J, Wang W, et al (2008). Epi-demiological Transition of Stroke in Chi-na Twenty-One-Year Observational Study from the Sino-MONICA-Beijing Project. Stroke, 39(6):1668-74.
8. Wieberdink R G, Ikram M A, Hofman A, et al (2012). Trends in stroke incidence rates and stroke risk factors in Rotterdam, the Netherlands from 1990 to 2008. Eur J Epidemiol, 27(4):287-95.
9. Yu W, Yan Y, Jiang C (2010). Logistic analy-sis of epidemiological characteristics and risk factors of stroke in Shijiazhuang City. Hebei Medical Journal, 32(017):2433-2434.
10. Wang S, Wang Z, Ma Z, et al (2016). The role of estrogen in ischemic stroke. Pre-vent Treat Cardil Cerebr Vasc Dis, 16(6):459-461.
11. Sohrabji F, Okoreeh A, Panta A (2019). Sex hormones and stroke: Beyond estrogens. Horm Behav, 111:87-95.
12. Feigin VL, Roth GA, Naghavi M, et al (2016). Global burden of stroke and risk factors in 188 countries, during 1990-2013: a systematic analysis for the Global Burden of Disease Study 2013. Lancet Neurol, 15(9):913-924.
13. Harada W, Miyauchi S, Higashihara T, et al (2016). Visit-to-visit blood pressure vari-ability and classes of antihypertensive agents; associations with artery remodel-ing and the risk of stroke. Curr Pharm Des, 22(3):383-389.
14. Deng X L, Liu Z, Wang C, et al (2017). In-sulin resistance in ischemic stroke. Metab Brain Dis, 32(5):1323-1334.
15. Zhang D, Han W (2018). Research progress on prevalence and risk factors of stroke in China. World Latest Med Inf, 18(80):128-129.
16. Iso H, Baba S, Mannami T, et al (2004). Al-cohol Consumption and Risk of Stroke among Middle-Aged Men: The JPHC Study Cohort I. Stroke, 35(5):1124-9.
17. Xu X, Zhao L, Fang H, et al (2016). [Status of alcohol drinking among aged 15 and above in China in 2010-2012]. Wei Sheng Yan Jiu, 45(4):534-567.
18. Larsson S C, Virtamo J, Wolk A (2012). Dairy Consumption and Risk of Stroke in Swedish Women and Men. Stroke, 43(7):1775-80.
19. Dalmeijer GW, Struijk EA, Van der Schouw YT, et al (2013). Dairy intake and coro-nary heart disease or stroke-A popula-tion-based cohort study. Int J Cardiol, 167(3):925-9.
20. Abbott RD, Curb JD, Rodriguez BL, et al (1996). Effect of dietary calcium and milk consumption on risk of thromboembolic stroke in older middle-aged men. The Honolulu Heart Program. Stroke, 27 (5):813-8.
21. Yang Z, Lv X, Xiao X, et al (2019). Analysis on consumption structure and trend of dairy products in China-a dairy con-sumption survey based on 3000 consum-ers in 6 typical cities. Chin Dairy, (9):23-27.
Files
IssueVol 51 No 5 (2022) QRcode
SectionOriginal Article(s)
DOI https://doi.org/10.18502/ijph.v51i5.9415
Keywords
Stroke Logistic regressive analysis LightGBM algorithm Prediction

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
1.
Xue Y, Chen S, Zhang M, Cai X, Zheng J, Wang S, Chen Y. The Prediction Models for High-Risk Population of Stroke Based on Logistic Regressive Analysis and Lightgbm Algorithm Separately. Iran J Public Health. 2022;51(5):999-1009.