武冈市农村地区心脑血管住院病例的时间序列预测分析

吴玉攀; 韦柳意; 王双; 陆姗; 胡博睿; 他福慧; 陈磊; 毛宗福

doi:10.16462/j.cnki.zhjbkz.2019.02.020

武冈市农村地区心脑血管住院病例的时间序列预测分析

doi: 10.16462/j.cnki.zhjbkz.2019.02.020

吴玉攀¹,
韦柳意¹,
王双¹,
陆姗²,
胡博睿¹,
他福慧²,
陈磊²,
毛宗福^{1, 2, ,}

1.
430071 武汉市, 武汉大学健康学院全球健康系
2.
430072 武汉市, 武汉大学全球健康研究中心

基金项目:

中组部全国党建研究会、原国家卫计委基层卫生司联合委托重点课题 (2017) 53

详细信息

通讯作者:
毛宗福, E-mail: zfmao@126.com

中图分类号: R45;R13
计量
- 文章访问数: 252
- HTML全文浏览量: 153
- PDF下载量: 27
- 被引次数: 0
出版历程
- 收稿日期: 2018-09-17
- 修回日期: 2018-11-19
- 刊出日期: 2019-02-10

A time-series prediction and analysis on rural inpatient with cardio-cerebrovascular disease in Wugang

1.
School of Health Sciences, Wuhan University, Wuhan 430071, China
2.
Global Health Institute, Wuhan University, Wuhan 430072, China

Funds:

The National Party Building Research Association of the Central Organization Department and the Primary Health Department of the former National Health and Family Planning Commission jointly commissioned a key project (2017) 53

More Information

Corresponding author: MAO Zong-fu, E-mail: zfmao@126.com

摘要

摘要: 目的建立武冈市农村地区心脑血管疾病（cardio-cerebrovascular disease，CVD）住院病例的预测模型，并对CVD住院病例的变化趋势进行预测分析，为医院合理配置CVD科室医疗资源提供参考依据。方法利用Stata 14.0软件对武冈市2013年1月~2016年12月农村地区CVD住院人次月度数据构建季节性自回归移动平均混合模型（seasonal autoregressive integrated moving average model，SARIMA），并对2017年武冈市农村地区CVD住院病例进行预测分析。结果通过模型构建最终拟合的CVD住院病例预测模型为SARIMA（2，1，1）x（0，1，0）₁₂。Ljung-Box Q检验结果显示残差序列为白噪音序列（Q=11.12，P=0.680），说明所建模型拟合度较好，且2017年的预测结果与观测结果基本一致，总体相对误差在-1.2%左右。预测结果显示，夏季为每年CVD住院高峰期。结论 SARIMA模型可以对武冈市CVD住院病例进行较准确的短期预测，医院可以根据不同月份CVD就医需求合理配置院内CVD科室医疗资源。
- 心脑血管 /
- 时间序列分析 /
- 自回归综合移动平均模型 /
- 季节性 /
- 预测
Abstract: Objective To establish a predictive model for inpatients of cardio-cerebrovascular disease in rural areas of Wugang through time series analysis, and predict the changing trend of cardio-cerebrovascular disease, so as to offer guidance for the health care resources allocation and prevention and control of cardio-cerebrovascular disease. Methods The seasonal autoregressive integrated moving average model (SARIMA) was constructed based on the monthly number of cases of cardio-cerebrovascular disease in rural areas from January 2013 to December 2016 by Stata 14.0 software, and the predictive effect of the model was verified with the monthly number of inpatients of cardio-cerebrovascular disease in 2017. Results The final fitting model of inpatients of cardio-cerebrovascular disease was SARIMA (2, 1, 1)×(0, 1, 0)₁₂. The residual sequence of the model was diagnosed. Results of Ljung-Box Q test showed that the residual sequence was white noise sequence (Q=11.12, P=0.68). In addition, the 2017 forecast was basically consistent with the observations, the overall relative error was around -1.2%. The results showed that the summer was the peak period of cardiovascular and cerebrovascular hospitalization. Conclusion SARIMA model can accurately predict the number of inpatients of cardio-cerebrovascular disease in Wugang, which can provide data support for the hospital administrator to rationally allocate medical resources in the cardiovascular according to the needs of cardio-cerebrovascular treatment in different months.
- Cardio-cerebrovascular disease /
- Time series analysis /
- Autoregressive comprehensive moving average model /
- Seasonality /
- Prediction

HTML全文

图 1 武冈市2013-2016年心脑血管住院病例的时间分布序列图

Figure 1. The series diagram of cardio-cerebrovascular inpatients in Wugang from 2013 to 2016

下载: 全尺寸图片幻灯片

图 2 原始序列作周期为12的一阶季节性差分后的自相关图、偏自相关图

Figure 2. Autocorrelation figure and partial autocorrelation figure of the sequence after two times differencing

下载: 全尺寸图片幻灯片

图 3 武冈市2013-2017年心脑血管住院病例数拟合和预测情况

Figure 3. The observations and predicted values of cardio-cerebrovascular inpatients in Wugang from 2013 to 2017

下载: 全尺寸图片幻灯片

表 1 备选模型的参数估计

Table 1. The estimation of model parameters

	SARIMA(2，1，1)(0，1，0)₁₂			SARIMA(2，1，0)(0，1，0)₁₂
	B值	Z值	P值	B值	Z值	P值
AR1	-0.67	-3.68	<0.001	-0.91	-5.20	<0.001
AR2	-0.57	-3.44	0.001	-0.65	-4.30	<0.001
Ma1	-0.99	-3.09	0.002	-	-	-

下载: 导出CSV

表 2 2017年武冈市农村心脑血管住院病例实际值与预测值的结果比较

Table 2. Comparison between predicted and actual values of rural cardio-cerebrovascular inpatients in Wugang in 2017

月份	实际值	预测值	绝对误差	相对误差
1	741	808	67	0.090
2	84	731	-114	-0.135
3	1 007	938	-69	-0.069
4	980	899	-81	-0.083
5	902	989	87	0.096
6	1 044	979	-65	-0.062
7	1 112	1 065	-47	-0.042
8	991	939	-52	-0.052
9	879	1 016	137	0.156
10	911	938	27	0.030
11	968	954	-14	-0.014
12	915	982	67	0.073
合计	11 295	11 240	-55	-0.012

下载: 导出CSV

参考文献(16)

[1]	王妮, 吴炳义, 武继磊, 等. 2012年山东省心脑血管疾病死亡状况及去死因期望寿命研究[J]. 中华疾病控制杂志, 2017, 21(09): 917-920. DOI: 10.16462/j.cnki.zhjbkz.2017.09.014. Wang N, Wu BY, Wu JL, et al. Distribution of cardiocerebral vascular disease death and its life expectancy eliminating causes of death in Shandong Province in 2012[J]. Chin J Dis Control Prev, 2017, 21(09): 917-920. DOI: 10.16462/j.cnki.zhjbkz.2017.09.014.
[2]	World Health Organization. World health statistics 2018[EB/OL]. (2018-3-28)[2018-12-15] http://www.who.int/iris/bistream/handle/10665/272596/9789241565585eng.pdf?ua=1.
[3]	陈伟伟, 高润霖, 刘力生, 等. 《中国心血管病报告2017》概要[J]. 中国循环杂志, 2018, 33(1): 1-8. DOI: 10.3969/j.issn.1000-3614.2018.01.001. Chen WW, Gao RL, Liu LS, et al. Summary of China Cardiovascular Disease Report 2017[J]. Chin Circul J, 2018, 33(01): 1-8. DOI: 10.3969/j.issn.1000-3614.2018.01.001.
[4]	李小升, 马春柳, 雷海科, 等. SARIMA模型在医院门诊量预测中的应用[J]. 中国病案, 2013, 14(3): 37-40. DOI: 10.3969/j.issn.1672-2566.2013.03.019. Li XS, Ma CL, Lei HK, et al. Applications of SARIMA Model on Predicting Outpatients Quantity[J]. Chinese Medical Record, 2013, 14(3): 37-40. DOI: 10.3969/j.issn.1672-2566.2013.03.019.
[5]	马翠荣, 杨婕, 余小金. 江苏省2006-2014年城乡未成年人跌倒病例的时间序列预测分析[J]. 中华疾病控制杂志, 2018, 22(2): 122-125, 137. DOI: 10.16462/j.cnki.zhjbkz.2018.02.005. Ma CR, Yang J, Yu XJ, et al. The fall injury cases of urban and rural areas for minors in Jiangsu Province: a time-series prediction and analysis, 2006-2014[J]. Chin J Dis Control Prev, 2018, 22(2): 122-125, 137. DOI: 10.16462/j.cnki.zhjbkz.2018.02.005.
[6]	易静, 杜昌廷, 王润华, 等. 自回归求和移动平均季节乘积模型在结核病发病率预测中的应用[J]. 中华预防医学杂志, 2007, 41(2): 118-121. DOI: 10.3760/j.issn:0253-9624.2007.02.009. Yi J, Du CT, Wang RH, et al. Applications of multiple seasonal autoregressive integrated moving average (ARIMA) model on predictive incidence of tuberculosis[J]. Chin J Prev Med, 2007, 41(02): 118-121. DOI: 10.3760/j.issn:0253-9624.2007.02.009.
[7]	王芳, 柴宗举, 刘雯, 等. 出血性脑卒中发病趋势及时间序列分析[J]. 中国老年学杂志, 2013, 33(17): 4128-4130. DOI: 10.3969/j.issn.1005-9202.2013.17.012. Wang F, Chai ZJ, Liu W, et al. Incidence trend and time series analysis of hemorrhagic stroke[J]. Chin J Ger, 2013, 33(17): 4128-4130. DOI: 10.3969/j.issn.1005-9202.2013.17.012.
[8]	谷少华, 陆蓓蓓, 边国林, 等. 大气可吸入颗粒物对心血管疾病急救人次的短期影响[J]. 环境与职业医学, 2016, 33(10): 965-969. DOI: 10.13213/j.cnki.jeom.2016.16140. Gu SH, Lu BB, Bian GL, et al. Short-Term Effect of Inhalable Particulate Matters on Emergency Ambulance Dispatches for Cardiovascular Diseases[J]. Journal of Environmental & Occupational Medine, 2016, 33(10): 965-969. DOI: 10.13213/j.cnki.jeom.2016.16140.
[9]	张霞, 刘起勇. 高温热浪对心脑血管病影响研究进展[J]. 中国公共卫生, 2014, 30(2): 242-243. DOI: 10.11847/zgggws2014-30-02-38. Zhang X, Liu QY. Research on the effects of high temperature heat waves on cardiovascular and cerebrovascular diseases[J]. Chinese Journal of Public Health, 2014, 30(2): 242-243. DOI: 10.11847/zgggws2014-30-02-38.
[10]	刘方, 张金良, 陆晨. 北京市气温与脑卒中发病关系的时间序列研究[J]. 中华流行病学杂志, 2004(11): 48-52. DOI: 10.3760/j.issn:0254-6450.2004.11.011. Liu F, Zhang JL, Lu C. The relationship of temperature and stroke incidence in Beijing: a time-series study[J]. Chin J Epidemiol, 2004(11): 48-52. DOI: 10.3760/j.issn:0254-6450.2004.11.011.
[11]	常倩, 叶云杰, 汪庆庆, 等. 南京市大气污染物与居民心脑血管疾病死亡的相关性[J]. 环境与职业医学, 2017, 34(12): 1041-1045. DOI: 10.13213/j.cnki.jeom.2017.17433. Chang Q, Ye YJ, Wang QQ, et al. Correlation between air pollutants and cardio-cerebrovascular mortality in Nanjing[J]. Journal of Environmental & Occupational Medine, 2017, 34(12): 1041-1045. DOI: 10.13213/j.cnki.jeom.2017.17433.
[12]	许安阳, 张丽娟, 李觉, 等. 上海市温度和大气污染对居民心血管疾病门急诊人数的影响[J]. 同济大学学报(医学版), 2017, 38(01): 114-118, 123. DOI: 10.16118/j.1008-0392.2017.01.024. Xu AY, Zhang LJ, Li j, et al. Effects of temperature and air pollution on outpatient and emergency visits for cardiovascular diseases in Shanghai[J]. Journal of Tongji University (Medical Science), 2017, 38(01): 114-118, 123. DOI: 10.16118/j.1008-0392.2017.01.024.
[13]	Yang J, Zhou M, Ou CQ, et al. Seasonal variations of temperature-related mortality burden from cardiovascular disease and myocardial infarction in China[J]. Environ Pollut, 2017, 5(224): 400-406. DOI: 10.1016/j.envpol.2017.02.020.
[14]	顾恺, 何红. 高血压患者夏季和冬季动态血压监测值的差异[J]. 中华高血压杂志, 2016, 24(6): 578-580. DOI: 10.16439/j.cnki.1673-7245.2016.06.019. Gu K, He H. Differences between summer and winter ambulatory blood pressure monitoring values in patients with hypertension[J]. Chinese Journal of Hypertension, 2016, 24(6): 578-580. DOI: 10.16439/j.cnki.1673-7245.2016.06.019.
[15]	吕阳, 王志盟, 陈滨. 室内空气环境与高龄者心脑血管疾病关联性研究进展[J]. 建筑科学, 2018, 34(2): 124-130. DOI: 10.13614/j.cnki.11-1962/tu.2018.02.21. Lv Y, Wang ZM, Chen B. A review of the Relationship between Indoor Air Environment and Cardiovascular and Cerebrovascular Disease in the Elderly[J]. Building Science, 2018, 34(2): 124-130. DOI: 10.13614/j.cnki.11-1962/tu.2018.02.21.
[16]	廉恒丽, 俞剑琴, 傅映晖. ARIMA与SARIMA模型在医院门诊人次与出院人次预测中的应用[J]. 中国医院统计, 2017, 24(02): 81-84. DOI: 10.3969/j.issn.1006-5253.2017.02.001. Liang HL, Yu JQ, Fu YH. Application of ARIMA and SARIMA model in predicting hospital outpatients and discharges[J]. Chinese Journal of Hospital Statistics, 2017, 24(02): 81-84. DOI: 10.3969/j.issn.1006-5253.2017.02.001.