Evaluation of daily number of new ischemic stroke cases in a hospital in Chengdu based on machine learning and meteorological factors_West China Medical Journal

Authors：

WANG Mingxu ¹ , ZHANG Haitao ² ,  XIONG Yao ² , WANG Zi ¹ , YAO Yi ¹ , CHEN Yuhao ³ , WANG Lu ¹

1. School of Mathematics, Southwest Jiaotong University, Chengdu, Sichuan 610097, P. R. China;
2. Department of Neurology, the Third People’s Hospital of Chengdu & the Affiliated Hospital of Southwest Jiaotong University, Chengdu, Sichuan 610041, P. R. China;
3. School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, Sichuan 610097, P. R. China;

Corresponding author：

XIONG Yao, Email: 350960109@qq.com

Keywords：

Ischemic stroke; prediction of incidence; meteorological factors; machine learning model

DOI：

10.7507/1002-0179.202205042

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To evaluate the predictive effect of three machine learning methods, namely support vector machine (SVM), K-nearest neighbor (KNN) and decision tree, on the daily number of new patients with ischemic stroke in Chengdu. Methods The numbers of daily new ischemic stroke patients from January 1st, 2019 to March 28th, 2021 were extracted from the Third People’s Hospital of Chengdu. The weather and meteorological data and air quality data of Chengdu came from China Weather Network in the same period. Correlation analyses, multinominal logistic regression, and principal component analysis were used to explore the influencing factors for the level of daily number of new ischemic stroke patients in this hospital. Then, using R 4.1.2 software, the data were randomly divided in a ratio of 7∶3 (70% into train set and 30% into validation set), and were respectively used to train and certify the three machine learning methods, SVM, KNN and decision tree, and logistic regression model was used as the benchmark model. F1 score, the area under the receiver operating characteristic curve (AUC) and accuracy of each model were calculated. The data dividing, training and validation were repeated for three times, and the average F1 scores, AUCs and accuracies of the three times were used to compare the prediction effects of the four models. Results According to the accuracies from high to low, the prediction effects of the four models were ranked as SVM (88.9%), logistic regression model (87.5%), decision tree (85.9%), and KNN (85.1%); according to the F1 scores, the models were ranked as SVM (66.9%), KNN (62.7%), decision tree (59.1%), and logistic regression model (57.7%); according to the AUCs, the order from high to low was SVM (88.5%), logistic regression model (87.7%), KNN (84.7%), and decision tree (71.5%). Conclusion The prediction result of SVM is better than the traditional logistic regression model and the other two machine learning models.

Citation： WANG Mingxu, ZHANG Haitao, XIONG Yao, WANG Zi, YAO Yi, CHEN Yuhao, WANG Lu. Evaluation of daily number of new ischemic stroke cases in a hospital in Chengdu based on machine learning and meteorological factors. West China Medical Journal, 2023, 38(2): 233-239. doi: 10.7507/1002-0179.202205042 Copy

1.	Wu S, Wu B, Liu M, et al. Stroke in China: advances and challenges in epidemiology, prevention, and management. Lancet Neurol, 2019, 18(4): 394-405.
2.	Tsai CF, Thomas B, Sudlow CL, et al. epidemiology of stroke and its subtypes in Chinese vs white populations. Neurology, 2013, 81(3): 264-272.
3.	王旭. 沈阳地区脑卒中发病与气象环境因素的相关性. 中国临床康复, 2006, 10(36): 12-13.
4.	汪宏莉, 韩延柏, 梯正之. 日本广岛市脑卒中发病与气象条件关系. 中国公共卫生, 2009, 25(5): 606-607.
5.	方万里, 马利娟. 宁波地区脑卒中发病规律与气象诱因统计分析. 中国卫生统计, 2014, 31(1): 137-138.
6.	王克英, 崔甍甍, 张进军. 气象因素对脑血管疾病急性发病影响的病例交叉研究. 中国全科医学, 2015, 18(22): 2662-2666.
7.	Huang K, Liang F, Yang X, et al. Long term exposure to ambient fine particulate matter and incidence of stroke: prospective cohort study from the China-PAR project. BMJ, 2019, 367: l6720.
8.	董继元, 陈永聪, 张本忠, 等. 兰州市气温对脑卒中发病的滞后效应研究. 气候变化研究进展, 2017, 13(4): 366-374.
9.	程学伟, 韩兆洲. 市域脑卒中疾病与气象因素的关系及预测. 气象, 2018, 44(6): 837-843.
10.	中华医学会神经病学分会, 中华医学会神经病学分会脑血管病学组. 中国急性缺血性脑卒中诊治指南 2018. 中华神经科杂志, 2018, 51(9): 666-682.
11.	Shin DW, Yoon JE, Hwang HW, et al. Numbers of stroke patients and stroke subtypes according to highest and lowest daily temperatures in Seoul. J Clin Neurol, 2016, 12(4): 476-481.
12.	王临池, 葛锡泳, 陆艳. 大气中 NO₂ 和 SO₂ 对苏州市居民脑卒中. 中国预防医学杂志, 2019, 20(9): 817-821.
13.	周玉庆, 袁洪, 黄志军, 等. 长沙市大气污染物与脑卒中急诊关系的病例交叉研究. 环境与健康杂志, 2014, 31(9): 764-768.
14.	郝宇, 费占洋, 张轩, 等. 北京地区脑梗死发病与干支运气及气象因子的关联性研究. 北京中医药大学学报, 2014, 37(8): 556-558.
15.	Butland BK, Atkinson RW, Crichton S, et al. Air pollution and the incidence of ischaemic and haemorrhagic stroke in the South London Stroke Register: a case-cross-over analysis. J Epidemiol Community Health, 2017, 71(7): 707-712.
16.	Wing JJ, Adar SD, Sánchez BN, et al. Ethnic differences in ambient air pollution and risk of acute ischemic stroke. Environ Res, 2015, 143(Pt A): 62-67.
17.	Kim J, Yoon K, Choi JC, et al. The association between wind-related variables and stroke symptom onset: a case-crossover study on Jeju Island. Environ Res, 2016, 150: 97-105.
18.	黄德生, 关鹏, 周宝森. Logistic 回归模型拟合 SARS 发病及流行特征. 中国公共卫生, 2003, 19(6): T1-T2.
19.	Alaka SA, Menon BK, Brobbey A, et al. Functional outcome prediction in ischemic stroke: a comparison of machine learning algorithms and regression models. Front Neurol, 2020, 11: 889.
20.	Ottenbacher KJ, Smith PM, Illig SB, et al. Comparison of logistic regression and neural networks to predict rehospitalization in patients with stroke. J Clin Epidemiol, 2001, 54(11): 1159-1165.
21.	丁少华, 陈宇辰, 殷信道, 等. 构建急性脑卒中机械取栓治疗后预后预测模型的研究. 磁共振成像, 2021, 12(8): 11-14, 21.
22.	张丽娜, 李国春, 周学平, 等. 基于支持向量机的急性出血性脑卒中早期预后模型的建立与评价. 南京医科大学学报(自然科学版), 2016, 36(1): 80-84.
23.	王海东, 张璐, 王洁, 等. C5. 0 决策树与 RBF 神经网络模型用于急性缺血性脑卒中出血性转化的风险预测性能比较. 中华疾病控制杂志, 2019, 23(2): 228-233.
24.	Zhu M, Chen WH, Hiedes JP, et al. The K-nearest neighbor algorithm predicted rehabilitation potential better than current Clinical Assessment Protocol. J Clin Epidemiol, 2007(60): 1015-1021.

1. Wu S, Wu B, Liu M, et al. Stroke in China: advances and challenges in epidemiology, prevention, and management. Lancet Neurol, 2019, 18(4): 394-405.
2. Tsai CF, Thomas B, Sudlow CL, et al. epidemiology of stroke and its subtypes in Chinese vs white populations. Neurology, 2013, 81(3): 264-272.
3. 王旭. 沈阳地区脑卒中发病与气象环境因素的相关性. 中国临床康复, 2006, 10(36): 12-13.
4. 汪宏莉, 韩延柏, 梯正之. 日本广岛市脑卒中发病与气象条件关系. 中国公共卫生, 2009, 25(5): 606-607.
5. 方万里, 马利娟. 宁波地区脑卒中发病规律与气象诱因统计分析. 中国卫生统计, 2014, 31(1): 137-138.
6. 王克英, 崔甍甍, 张进军. 气象因素对脑血管疾病急性发病影响的病例交叉研究. 中国全科医学, 2015, 18(22): 2662-2666.
7. Huang K, Liang F, Yang X, et al. Long term exposure to ambient fine particulate matter and incidence of stroke: prospective cohort study from the China-PAR project. BMJ, 2019, 367: l6720.
8. 董继元, 陈永聪, 张本忠, 等. 兰州市气温对脑卒中发病的滞后效应研究. 气候变化研究进展, 2017, 13(4): 366-374.
9. 程学伟, 韩兆洲. 市域脑卒中疾病与气象因素的关系及预测. 气象, 2018, 44(6): 837-843.
10. 中华医学会神经病学分会, 中华医学会神经病学分会脑血管病学组. 中国急性缺血性脑卒中诊治指南 2018. 中华神经科杂志, 2018, 51(9): 666-682.
11. Shin DW, Yoon JE, Hwang HW, et al. Numbers of stroke patients and stroke subtypes according to highest and lowest daily temperatures in Seoul. J Clin Neurol, 2016, 12(4): 476-481.
12. 王临池, 葛锡泳, 陆艳. 大气中 NO₂ 和 SO₂ 对苏州市居民脑卒中. 中国预防医学杂志, 2019, 20(9): 817-821.
13. 周玉庆, 袁洪, 黄志军, 等. 长沙市大气污染物与脑卒中急诊关系的病例交叉研究. 环境与健康杂志, 2014, 31(9): 764-768.
14. 郝宇, 费占洋, 张轩, 等. 北京地区脑梗死发病与干支运气及气象因子的关联性研究. 北京中医药大学学报, 2014, 37(8): 556-558.
15. Butland BK, Atkinson RW, Crichton S, et al. Air pollution and the incidence of ischaemic and haemorrhagic stroke in the South London Stroke Register: a case-cross-over analysis. J Epidemiol Community Health, 2017, 71(7): 707-712.
16. Wing JJ, Adar SD, Sánchez BN, et al. Ethnic differences in ambient air pollution and risk of acute ischemic stroke. Environ Res, 2015, 143(Pt A): 62-67.
17. Kim J, Yoon K, Choi JC, et al. The association between wind-related variables and stroke symptom onset: a case-crossover study on Jeju Island. Environ Res, 2016, 150: 97-105.
18. 黄德生, 关鹏, 周宝森. Logistic 回归模型拟合 SARS 发病及流行特征. 中国公共卫生, 2003, 19(6): T1-T2.
19. Alaka SA, Menon BK, Brobbey A, et al. Functional outcome prediction in ischemic stroke: a comparison of machine learning algorithms and regression models. Front Neurol, 2020, 11: 889.
20. Ottenbacher KJ, Smith PM, Illig SB, et al. Comparison of logistic regression and neural networks to predict rehospitalization in patients with stroke. J Clin Epidemiol, 2001, 54(11): 1159-1165.
21. 丁少华, 陈宇辰, 殷信道, 等. 构建急性脑卒中机械取栓治疗后预后预测模型的研究. 磁共振成像, 2021, 12(8): 11-14, 21.
22. 张丽娜, 李国春, 周学平, 等. 基于支持向量机的急性出血性脑卒中早期预后模型的建立与评价. 南京医科大学学报(自然科学版), 2016, 36(1): 80-84.
23. 王海东, 张璐, 王洁, 等. C5. 0 决策树与 RBF 神经网络模型用于急性缺血性脑卒中出血性转化的风险预测性能比较. 中华疾病控制杂志, 2019, 23(2): 228-233.
24. Zhu M, Chen WH, Hiedes JP, et al. The K-nearest neighbor algorithm predicted rehabilitation potential better than current Clinical Assessment Protocol. J Clin Epidemiol, 2007(60): 1015-1021.

West China Medical Journal

Evaluation of daily number of new ischemic stroke cases in a hospital in Chengdu based on machine learning and meteorological factors

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content