Academic Journal of Computing & Information Science, 2023, 6(13); doi: 10.25236/AJCIS.2023.061318.
Weihan Wang1, Wenjing Li2
1Maynooth International Engineering College, Fuzhou University, Fuzhou, Fujian, 350112, China
2Software College, Taiyuan University of Technology, Taiyuan, Shanxi, 030000, China
As a cerebrovascular disease, the number of stroke patients in China has always ranked first in the world, affecting people's life safety. It is very important to predict the population of stroke to prevent stroke and control the number of stroke patients. Different from the conventional method of regression model prediction, this paper uses random forest classification model to predict stroke patients from the perspective of machine learning model. In order to get a model with higher accuracy, this paper adjusts the parameters of cross-validation, classification evaluation and so on to get the optimal model. Experiments have shown that random forest has an improved accuracy rate of 1.9% to 27% compared to other machine learning models. The model can reduce the medical cost, improve the prevention system, and the model ideas can be used to predict similar diseases, and has a certain degree of simulation.
stroke, population prediction, machine learning, random forest, parameter regulation
Weihan Wang, Wenjing Li. Study on the environmental influence factors of stroke itself based on random forest. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 13: 120-126. https://doi.org/10.25236/AJCIS.2023.061318.
[1] Lin X , Zeng D , Cheng L ,et al.Study on the influence factors of music piracy in china based on SEM model[C]//International Conference on Service Systems & Service Management. IEEE, 2015. DOI:10.1109/ICSSSM.2015.7170311.
[2] Wang X. Correlation between cerebral apoplexy incidence and meteorological environment factors in Shenyang area [J]. Chinese Clinical Rehabilitation, 2006(36):12-13.
[3] Hou Yumei, Zhang Chenyang, Su Yanlin. Prediction of ischemic stroke risk based on support vector machine [J]. Modern Preventive Medicine, 2019, 46(15):2692-2695+2700. (in Chinese)
[4] PEI Zehua, Ge Miao, Li Hao et al. Study on environmental factors affecting HDL-C in middle-aged and elderly people in China based on random forest model [J]. Journal of Geoinformation Science, 2002, 24(07):1286-1300.
[5] Yan Guanghua, Chen Xi, Zhang Yun. Study on the Distribution Pattern and Influencing Factors of Shrinking Cities in Northeast China Based on Random Forest Model. Geographical Science, 2021, 41(05):880-889. DOI:10.13249/j.cnki.sgs.
[6] Guan Jun, Zhang Shaopeng, Ren Yue et al. Spatial and temporal differentiation and influencing factors evolution of agricultural net carbon sinks in China based on random forest model [J/OL]. China environmental science: 1-13 [2023-10-19]. https://doi.org/10.19674/j. cnki.issn1000-6923. 20230928.002.
[7] Ling Xiaodan, Wang Luoqi, Zhao Keli et al. Study on spatial distribution characteristics of soil available nutrients in Pecan forest based on random forest method [J/OL]. Acta ecologica sinica, 2024 (02): 1-14 [2023-10-19]. HTTP: / / https://doi.org/10.20103/j.stxb.202301130090.