ARIMA-SVM组合模型在肺结核发病预测中的应用

摘要/Abstract

摘要： 目的: 研究ARIMA-SVM组合模型在内蒙古鄂尔多斯市肺结核发病预测中的应用,为制定肺结核防控策略提供参考。方法: 以内蒙古鄂尔多斯市2010—2023年肺结核月发病数据作为训练集,2024年1—12月的肺结核发病数作为验证集,建立ARIMA模型、SVM模型与ARIMA-SVM组合模型,并对三种模型的预测精度和建模效果进行分析与评价。结果: ARIMA-SVM组合模型数据拟合RMSE、MAPE分别为15.56、5.87%,模型预测RMSE、MAPE分别为 6.48、2.75%,拟合和预测效果均优于单一的ARIMA模型与SVM模型。结论: ARIMA-SVM组合模型能较好地拟合和预测内蒙古鄂尔多斯市肺结核的月发病数,可为该病的监测和防控工作提供依据。

关键词: 肺结核, ARIMA, SVM, 组合模型, 预测

刘敏, 祁丹, 石峰, 李兵, 郝瑞霞, 王东, 白俊. ARIMA-SVM组合模型在肺结核发病预测中的应用[J]. 中国防痨杂志, 2025, 47(S1): 21-25.

参考文献 31

[1]	World Health Organization.Global tuberculosis report 2024 [R].https://www.who.int/teams/global-tuberculosis-programme/tb-reports/global-tuberculosis-report-2024.
[2]	国家疾病预防控制局. 2023年全国法定传染病疫情概况. https://www.ndcpa.gov.cn/jbkzzx/c100016/second/content/content_1836299733133275136.html.
[3]	宋媛媛, 李涛, 夏辉, et al.1997—2023年全国肺结核报告发病流行病学特征[J]. 中国防痨杂志, 2024, 46(10):1198-208. DOI:10.19982/j.issn.1000-6621.20240382.
[4]	Yang SX, Xu HF, Mao YJ, et al.Predicting the Number of Reported Pulmonary Tuberculosis in Guiyang, China, Based on Time Series Analysis Techniques. Comput Math Methods Med. 2022;2022:7828131. DOI:10.1155/2022/7828131.
[5]	Chen S, Wang X, Zhao J, et al.Application of the ARIMA Model in Forecasting the Incidence of Tuberculosis in Anhui During COVID-19 Pandemic from 2021 to 2022. Infect Drug Resist. 2022;15:3503-3512. DOI:10.2147/IDR.S367528.
[6]	任嘉豪, 徐洁, 杨海燕. ARIMA及Holt-Winters指数平滑模型在河南省肺结核流行趋势预测中的应用[J]. 郑州大学学报(医学版), 2022, 57(06):756-60. DOI:10.13705/j.issn.1671-6825.2022.02.040.
[7]	杨美涛, 王彦丁, 李志强, et al.ARIMA-SVM组合模型在肺结核发病趋势预测中的应用[J]. 现代预防医学, 2023, 50(11):1921-6. DOI:10.20043/j.cnki.MPM.202210101.
[8]	Yang E, Zhang H, Guo X, et al.A multivariate multi-step LSTM forecasting model for tuberculosis incidence with model explanation in Liaoning Province, China. BMC Infect Dis. 2022;22(1):490. DOI:10.1186/s12879-022-07462-8.
[9]	Chen J, Liu L, Huang J, et al.LSTM-Based Prediction Model for Tuberculosis Among HIV-Infected Patients Using Structured Electronic Medical Records: A Retrospective Machine Learning Study. [J] Multidiscip Healthc. 2024;17:3557-3573. DOI:10.2147/JMDH.S467877.
[10]	Wang M, Pan J, Li X, et al.ARIMA and ARIMA-ERNN models for prediction of pertussis incidence in mainland China from 2004 to 2021. BMC Public Health. 2022;22(1):1447. DOI:10.1186/s12889-022-13872-9.
[11]	Zheng Y, Zhang L, Wang C, et al.Predictive analysis of the number of human brucellosis cases in Xinjiang, China. Sci Rep. 2021;11(1):11513. DOI:10.1038/s41598-021-91176-5.
[12]	Chiong R, Fan Z, Hu Z, et al.Using an improved relative error support vector machine for body fat prediction. Comput Methods Programs Biomed. 2021;198:105749. DOI:10.1016/j.cmpb.2020.105749.
[13]	Pushpa B, Baskaran B, Vivekanandan S,et al.Liver fat analysis using optimized support vector machine with support vector regression. Technol Health Care. 2023;31(3):867-886. DOI:10.3233/THC-220254.
[14]	Mane SS, Shrotriya P.Current Epidemiology of Pediatric Tuberculosis. Indian [J] Pediatr. 2024;91(7):711-716. DOI:10.1007/s12098-023-04910-4.
[15]	Fei H, Yinyin X, Hui C, et al.The impact of the COVID-19 epidemic on tuberculosis control in China. Lancet Reg Health West Pac. 2020;3:100032. DOI:10.1016/j.lanwpc.2020.100032.
[16]	Li T, Du X, Kang J, et al.Patient, Diagnosis, and Treatment Delays Among Tuberculosis Patients Before and During COVID-19 Epidemic - China, 2018-2022. China CDC Wkly. 2023;5(12):259-265. DOI:10.46234/ccdcw 2023.047.
[17]	Bie S, Hu X, Zhang H, et al.Influential factors and spatial-temporal distribution of tuberculosis in mainland China. Sci Rep. 2021;11(1):6274. DOI:10.1038/s41598-021-85781-7.
[18]	张鑫, 郎胜利, 白国辉, et al.2011—2020年内蒙古自治区肺结核疫情监测分析[J]. 中国防痨杂志, 2022, 44(12):1256-61.DOI:10.19982/j.issn.1000-6621.20220211.
[19]	Li XX, Wang LX, Zhang H, et al.Seasonal variations in notification of active tuberculosis cases in China, 2005-2012. PLoS One. 2013;8(7):e68102. DOI:10.1371/journal.pone.0068102.
[20]	Koh GC, Hawthorne G, Turner AM, Kunst H, Dedicoat M.Tuberculosis incidence correlates with sunshine: an ecological 28-year time series study. PLoS One. 2013;8(3):e57752. DOI:10.1371/journal.pone.0057752.
[21]	Thorpe LE, Frieden TR, Laserson KF, Wells C, Khatri GR.Seasonality of tuberculosis in India: is it real and what does it tell us?. Lancet. 2004;364(9445):1613-1614. DOI:10.1016/S0140-6736(04)17316-9.
[22]	Wang M, Kong W, He B, et al.Vitamin D and the promoter methylation of its metabolic pathway genes in association with the risk and prognosis of tuberculosis. Clin Epigenetics. 2018;10(1):118. DOI:10.1186/s13148 -018-0552-6.
[23]	Liu Q, Li Z, Ji Y, et al.Forecasting the seasonality and trend of pulmonary tuberculosis in Jiangsu Province of China using advanced statistical time-series analyses. Infect Drug Resist. 2019;12:2311-2322. DOI:10.2147/IDR. S207809.
[24]	Zhao D, Zhang H, Cao Q, et al.The research of ARIMA, GM(1,1), and LSTM models for prediction of TB cases in China. PLoS One. 2022;17(2):e0262734. DOI:10.1371/journal.pone.0262734.
[25]	Gebregergs GB, Berhe G, Gebrehiwot KG, et al.Predicting Tuberculosis Incidence and Its Trend in Tigray, Ethiopia: A Reality-Counterfactual Modeling Approach. Infect Drug Resist. 2024;17:3241-3251. DOI:10.2147/IDR. S464787.
[26]	刘洋, 高燕琳, 史芸萍, et al.基于ARIMA模型和ARIMA-SVM组合模型的流行性感冒的发病预测研究[J]. 首都公共卫生, 2024, 18(04):195-200. DOI:10.16760/j.cnki.sdggws.2024.04.007.
[27]	Mao Q, Zhang K, Yan W, et al.Forecasting the incidence of tuberculosis in China using the seasonal auto- regressive integrated moving average (SARIMA) model. J Infect Public Health. 2018;11(5):707-712. DOI:10.1016 /j.jiph.2018.04.009.
[28]	Singh S, Parmar KS, Makkhan SJS, et al.Study of ARIMA and least square support vector machine (LS-SVM) models for the prediction of SARS-CoV-2 confirmed cases in the most affected countries. Chaos Solitons Fractals. 2020;139:110086. DOI:10.1016/j.chaos.2020.110086.
[29]	Wan Mohamad Nawi WIA, K Abdul Hamid AA, Lola MS, et al. Developing forecasting model for future pandemic applications based on COVID-19 data 2020-2022. PLoS One. 2023;18(5):e0285407. DOI:10.1371/ journal.pone.0285407.
[30]	Huang Z, Li H, Huang B.Regional Distribution of Non-human H7N9 Avian Influenza Virus Detections in China and Construction of a Predictive Model. [J] Vet Res. 2021;65(3):253-264. DOI:10.2478/jvetres-2021-0034.
[31]	Zhang C, Fu X, Zhang Y, et al.Epidemiological and time series analysis of haemorrhagic fever with renal syndrome from 2004 to 2017 in Shandong Province, China. Sci Rep. 2019;9(1):14644. DOI:10.1038/s41598-019 -50878-7.

ARIMA-SVM组合模型在肺结核发病预测中的应用

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 31

相关文章 15

编辑推荐

Metrics

本文评价

友情链接

[1]	杜润泽, 艾尔帕提·玉素甫, 董士铭, 徐韬, 蔡晓宇, 王婷, 牙克甫·阿卜力孜, 盛伟斌, 买尔旦·买买提. Lasso-logistic回归在感染性脊柱炎鉴别诊断中的应用[J]. 中国防痨杂志, 2025, 47(S1): 1-4.
[2]	田琦, 李春杨. 抗病毒联合抗结核药物治疗艾滋病合并肺结核的临床疗效观察[J]. 中国防痨杂志, 2025, 47(S1): 9-11.
[3]	杜润泽, 董士铭, 艾尔帕提·玉素甫, 徐韬, 蔡晓宇, 王婷, 牙克甫·阿卜力孜, 盛伟斌, 买尔旦·买买提. 布鲁氏菌性脊柱炎的精确诊断：多因素Logistic回归预测模型的构建与验证[J]. 中国防痨杂志, 2025, 47(S1): 17-20.
[4]	李雅惠, 刘珂伟, 戈启萍, 杨晓丽, 王慧芳. 四例煤工尘肺合并非结核分枝杆菌感染临床特点分析[J]. 中国防痨杂志, 2025, 47(S1): 26-30.
[5]	周巍, 任鑫. 探讨多层螺旋CT在肺结核诊断和鉴别诊断中的临床应用价值[J]. 中国防痨杂志, 2025, 47(S1): 71-73.
[6]	李松柏. PLT和HCT对腹腔镜胆囊切除术患者术后并肺部感染的预测价值[J]. 中国防痨杂志, 2025, 47(S1): 121-124.
[7]	刘玲俊, 陈丹华. 预测性护理对预防重症医学科患者呼吸机相关性肺炎发生的作用[J]. 中国防痨杂志, 2025, 47(S1): 264-266.
[8]	苏莹莹, 黄鑫. 基于中西医结合模式的肺结核并发肺癌患者诊疗方案的优化与实践[J]. 中国防痨杂志, 2025, 47(S1): 390-392.
[9]	刘菊秀, 张建华, 温均筠, 姜晓双. 吉林市结核分枝杆菌耐药情况及趋势预测分析[J]. 中国防痨杂志, 2025, 47(3): 348-354.
[10]	赵悦, 王昊然, 程美锦, 王伟, 梁瑞霞, 黄海荣. 涂片阳性/Xpert阴性结果早期预测临床标本中存在非结核分枝杆菌的可靠性[J]. 中国防痨杂志, 2025, 47(1): 61-65.
[11]	夏焕荣, 樊江凤, 杜毓锋. 肺结核与可干预风险因素的关联：一项基于GWAS数据库的两样本孟德尔随机化研究[J]. 中国防痨杂志, 2024, 46(S2): 16-18.
[12]	赵佳慧. IFN-γ、IL-32结合KL-6水平在肺结核患者强化期治疗转归评估中的价值[J]. 中国防痨杂志, 2024, 46(S2): 19-21.
[13]	欧洪菊. 细胞因子联合外周血淋巴细胞亚群检测对鉴别肺结核及支原体肺炎的价值[J]. 中国防痨杂志, 2024, 46(S2): 25-27.
[14]	解慧, 吴娇娇. 痰涂片结核分枝杆菌检查和抗原胶体金法检验应用于肺结核的价值[J]. 中国防痨杂志, 2024, 46(S2): 32-34.
[15]	聂晓平, 韩梅, 杨松, 王乐乐, 李同心, 黄正谷, 高雯琬. CRISPR/Cas13a在肺结核诊断中的效能研究[J]. 中国防痨杂志, 2024, 46(S2): 35-37.