Article(id=1322608156249800990, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1322608013010120712, articleNumber=null, orderNo=null, doi=10.20043/j.cnki.MPM.202505216, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1747065600000, receivedDateStr=2025-05-13, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793263957320, onlineDateStr=2026-10-29, pubDate=1762704000000, pubDateStr=2025-11-10, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793263957320, onlineIssueDateStr=2026-10-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793263957320, creator=13701087609, updateTime=1793263957320, updator=13701087609, issue=Issue{id=1322608013010120712, tenantId=1146029695717560320, journalId=1227665162245664772, year='2025', volume='52', issue='21', pageStart='3841', pageEnd='4032', issueExtLink='null', onlineDate='null', pubDate='1762704000000', pubDateStr='2025-11-10', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793263923169, creator='13701087609', updateTime=1793264266929, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1322609454932149086, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1322608013010120712, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1322609454932149087, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1322608013010120712, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=3893, endPage=3899, ext={EN=ArticleExt(id=1322608158338564387, articleId=1322608156249800990, tenantId=1146029695717560320, journalId=1227665162245664772, language=EN, title=Application of LSTM-Informer model in the prediction of pulmonary tuberculosis incidence, columnId=1240413921954295836, journalTitle=Modern Preventive Medicine, columnName=Epidemiology and Statistical Methods, runingTitle=null, highlight=null, articleAbstract=
Objective

To explore the application of the advanced LSTM-Informer model in predicting and early warning of pulmonary tuberculosis incidence, providing a reference for relevant authorities to formulate prevention and control measures, and offering new methodologies and insights for forecasting other infectious diseases.

Methods

Pulmonary tuberculosis incidence data for Jining City from January 1, 2010, to December 31, 2022, were obtained from the National Notifiable Disease Reporting System (NNDRS). Monthly incidence rates were calculated by integrating demographic data from the Jining Statistical Yearbook (2010—2022). The final 12, 18, and 24 months of data were used as test sets to evaluate model performance, with the remaining data constituting the training set. The LSTM-Informer model was constructed and its reliability assessed through comparison with standalone LSTM and Informer models.

Results

The predictive performance of the three models across different forecast horizons was evaluated using error metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and the Coefficient of Determination(R2). Results demonstrated that the LSTM-Informer model consistently outperformed the single models. In the prediction of the 12-month length, the MSE of the model was 0.028, which was 59.4% lower than that of LSTM, the MAE value of 0.155 was 34.0% lower than that of LSTM, and the R2 value was 0.850. When the forecast horizon extended to 18 months, the model maintained a stable MAPE of 0.104 and an R2 of 0.808. Even at the 24-month horizon, the LSTM-Informer model retained significant advantages(R2=0.782).

Conclusion

Compared to single models, the LSTM-Informer model, leveraging both local and global feature extraction, significantly enhances prediction accuracy for medium-to-long-term forecasts. It shows considerable promise for providing novel theoretical support and reference for developing pulmonary tuberculosis incidence early-warning systems locally.

, authors=Qing-lin LI1, 2, Jin-ming SU1, 2, Shu-yue YANG1, 2, Yu-min LIANG3, Wen-guo JIANG3, Wei LIU3, Ling XUE1, Wen-jun WANG2, authorsList=Qing-lin LI, Jin-ming SU, Shu-yue YANG, Yu-min LIANG, Wen-guo JIANG, Wei LIU, Ling XUE, Wen-jun WANG, authorCompany=null, correspAuthors=Wen-jun WANG, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1322608169336029515, articleId=1322608156249800990, tenantId=1146029695717560320, journalId=1227665162245664772, language=CN, title=LSTM-Informer模型在肺结核发病率预测中的应用, columnId=1228016567632462653, journalTitle=现代预防医学, columnName=流行病与统计方法, runingTitle=null, highlight=null, articleAbstract=
目的

探究前沿模型长短期记忆神经网络(long short-term memory,LSTM)-Informer在肺结核病率预测预警中的应用,为相关部门制定防治措施提供参考,同时为其他传染病的预测提供新的方法和思路。

方法

通过《国家传染病网络直报系统》获得济宁市2010年1月1日—2022年12月31日肺结核发病资料,并结合《济宁市统计年鉴2010—2022》计算月度发病率数据;分别以数据最后12、18和24个月为测试集用于模型效果评价,其余为训练集构建LSTM-Informer模型并与LSTM、Informer单一模型进行比较,测试组合模型的可靠性。

结果

使用均方误差(mean squared error,MSE)、均方根误差(root mean squared error,RMSE)、平均绝对误差(mean absolute error,MAE)、平均绝对百分比误差(mean absolute percentage error,MAPE)和决定系数(R2)误差指标对比三个模型在不同预测时间下肺结核发病趋势中的预测效能。结果显示,LSTM-Informer模型性能均优于单一模型,在12个月长度的预测中,该模型MSE为0.028,较LSTM降低了59.4%,MAE值0.155,较LSTM减少34.0%,R2值为0.850;当时间延长至18个月时,其MAPE指标稳定在0.104,R2值为0.808;在24个月预测长度下,LSTM-Informer模型仍可以保持较好的优势(R2=0.782)。

结论

对比单一模型来看,基于局部-全局特征提取的LSTM-Informer模型在中长期预测中明显提高了预测精度,有望为当地肺结核发病预警系统提供新的理论支持与参考。

, authors=李青林1, 2, 苏金铭1, 2, 杨舒越1, 2, 梁玉民3, 姜文国3, 刘伟3, 薛玲1, 王文军2, authorsList=李青林, 苏金铭, 杨舒越, 梁玉民, 姜文国, 刘伟, 薛玲, 王文军, authorCompany=null, correspAuthors=王文军, authorNote=

李青林(1998—),男,硕士在读,研究方向:传染病流行病学,疾病预防与控制

, correspAuthorsNote=
王文军,E-mail:
, copyrightStatement=本刊刊出的所有文章不代表中华预防医学会和本刊编委会的观点,除非特别声明。, copyrightOwner=中华预防医学会和四川大学华西公共卫生学院, extLink=null, articleAbsUrl=null, sourceXml=iS0D90ibjWtKcEmL87uo3w==, magXml=gDqIEpszsuw2ATrvwe6zVQ==, pdfUrl=null, pdf=w8rScLBq2vPYPdzwVUTm6A==, pdfFileSize=1129540, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=5rbOgKyoKZujkRdbjQDDUg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=qemXA5uz7FWoBk+704je6A==, mapNumber=null, fund=null)}, authors=[Author(id=1322608171479318868, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608171743560023, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608171479318868, language=EN, stringName=Qing-lin LI, firstName=Qing-lin, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608171814863192, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608171479318868, language=CN, stringName=李青林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.华北理工大学公共卫生学院,河北 唐山 063210
2.潍坊护理职业学院,山东 潍坊 261000, bio={"content":"

李青林(1998—),男,硕士在读,研究方向:传染病流行病学,疾病预防与控制

"}, bioImg=null, bioContent=

李青林(1998—),男,硕士在读,研究方向:传染病流行病学,疾病预防与控制

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608169797402956, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=1., ext=[AuthorCompanyExt(id=1322608169809985869, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China), AuthorCompanyExt(id=1322608169814180174, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学公共卫生学院,河北 唐山 063210)]), AuthorCompany(id=1322608171332518223, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=2., ext=[AuthorCompanyExt(id=1322608171340906832, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171332518223, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.潍坊护理职业学院,山东 潍坊 261000)])]), Author(id=1322608171881972058, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608171982635357, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608171881972058, language=EN, stringName=Jin-ming SU, firstName=Jin-ming, middleName=null, lastName=SU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608172070715742, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608171881972058, language=CN, stringName=苏金铭, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.华北理工大学公共卫生学院,河北 唐山 063210
2.潍坊护理职业学院,山东 潍坊 261000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608169797402956, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=1., ext=[AuthorCompanyExt(id=1322608169809985869, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China), AuthorCompanyExt(id=1322608169814180174, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学公共卫生学院,河北 唐山 063210)]), AuthorCompany(id=1322608171332518223, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=2., ext=[AuthorCompanyExt(id=1322608171340906832, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171332518223, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.潍坊护理职业学院,山东 潍坊 261000)])]), Author(id=1322608172213322080, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608172297208163, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608172213322080, language=EN, stringName=Shu-yue YANG, firstName=Shu-yue, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608172590809444, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608172213322080, language=CN, stringName=杨舒越, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.华北理工大学公共卫生学院,河北 唐山 063210
2.潍坊护理职业学院,山东 潍坊 261000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608169797402956, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=1., ext=[AuthorCompanyExt(id=1322608169809985869, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China), AuthorCompanyExt(id=1322608169814180174, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学公共卫生学院,河北 唐山 063210)]), AuthorCompany(id=1322608171332518223, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=2., ext=[AuthorCompanyExt(id=1322608171340906832, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171332518223, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.潍坊护理职业学院,山东 潍坊 261000)])]), Author(id=1322608172657918311, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608172741804393, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608172657918311, language=EN, stringName=Yu-min LIANG, firstName=Yu-min, middleName=null, lastName=LIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608173056377195, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608172657918311, language=CN, stringName=梁玉民, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.济宁市疾病预防控制中心, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608171412210001, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=3., ext=[AuthorCompanyExt(id=1322608171420598610, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171412210001, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.济宁市疾病预防控制中心)])]), Author(id=1322608173123486061, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608173194789231, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608173123486061, language=EN, stringName=Wen-guo JIANG, firstName=Wen-guo, middleName=null, lastName=JIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608173425475952, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608173123486061, language=CN, stringName=姜文国, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.济宁市疾病预防控制中心, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608171412210001, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=3., ext=[AuthorCompanyExt(id=1322608171420598610, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171412210001, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.济宁市疾病预防控制中心)])]), Author(id=1322608173488390514, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608173572276596, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608173488390514, language=EN, stringName=Wei LIU, firstName=Wei, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608173630996853, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608173488390514, language=CN, stringName=刘伟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.济宁市疾病预防控制中心, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608171412210001, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=3., ext=[AuthorCompanyExt(id=1322608171420598610, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171412210001, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.济宁市疾病预防控制中心)])]), Author(id=1322608173853294967, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608173932986745, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608173853294967, language=EN, stringName=Ling XUE, firstName=Ling, middleName=null, lastName=XUE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608174004289914, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608173853294967, language=CN, stringName=薛玲, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.华北理工大学公共卫生学院,河北 唐山 063210, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608169797402956, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=1., ext=[AuthorCompanyExt(id=1322608169809985869, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China), AuthorCompanyExt(id=1322608169814180174, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学公共卫生学院,河北 唐山 063210)])]), Author(id=1322608174104953212, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=7, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wwjun1973@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322608175761703294, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608174104953212, language=EN, stringName=Wen-jun WANG, firstName=Wen-jun, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608175845589376, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608174104953212, language=CN, stringName=王文军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.潍坊护理职业学院,山东 潍坊 261000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608171332518223, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=2., ext=[AuthorCompanyExt(id=1322608171340906832, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171332518223, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.潍坊护理职业学院,山东 潍坊 261000)])])], keywords=[Keyword(id=1322608175946252673, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=EN, orderNo=1, keyword=Pulmonary tuberculosis), Keyword(id=1322608176017555842, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=EN, orderNo=2, keyword=Deep learning), Keyword(id=1322608176088859011, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=EN, orderNo=3, keyword=LSTM-Informer model), Keyword(id=1322608176181133700, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=EN, orderNo=4, keyword=Forecasting), Keyword(id=1322608176395043205, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=CN, orderNo=1, keyword=肺结核), Keyword(id=1322608176504095110, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=CN, orderNo=2, keyword=深度学习), Keyword(id=1322608176567009671, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=CN, orderNo=3, keyword=LSTM-Informer模型), Keyword(id=1322608176772530568, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=CN, orderNo=4, keyword=预测)], refs=[Reference(id=1322608178500583828, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2020, volume=144, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Dornelas moreira J, Rodrigues Silva H, de Paulo Coelho Peixoto de Toledo V, journalName=Microbial Pathogenesis, refType=null, unstructuredReference=Dornelas moreira J, Rodrigues Silva H, de Paulo Coelho Peixoto de Toledo V, et al. Microparticles in the pathogenesis of TB: Novel perspectives for diagnostic and therapy management of Mycobacterium tuberculosis infection [J]. Microbial Pathogenesis, 2020, 144: 104176., articleTitle=Microparticles in the pathogenesis of TB: Novel perspectives for diagnostic and therapy management of Mycobacterium tuberculosis infection, refAbstract=null), Reference(id=1322608178605441429, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=7, pageStart=681, pageEnd=684, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=康万里, 李恬静, 王赛赛, journalName=中国防痨杂志, refType=null, unstructuredReference=康万里,李恬静,王赛赛, 等. 全国活动性肺结核报告发病率变动趋势及预测研究 [J]. 中国防痨杂志, 2022, 44 (7): 681-684., articleTitle=全国活动性肺结核报告发病率变动趋势及预测研究, refAbstract=null), Reference(id=1322608180266385815, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=7, pageStart=681, pageEnd=684, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Kang WL, Li TJ, Wang SS, journalName=Chinese Journal of Antituberculosis, refType=null, unstructuredReference=Kang WL, Li TJ, Wang SS, et al. Study on the trend and prediction of reported incidence of National active pulmonary tuberculosis in China [J]. Chinese Journal of Antituberculosis, 2022, 44 (7): 681-684. (In Chinese), articleTitle=Study on the trend and prediction of reported incidence of National active pulmonary tuberculosis in China, refAbstract=null), Reference(id=1322608180559987096, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2020, volume=107, issue=1, pageStart=113, pageEnd=118, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=Koeken VACM, Verrall AJ, Ardiansyah E, journalName=Journal of Leukocyte Biology, refType=null, unstructuredReference=Koeken VACM, Verrall AJ, Ardiansyah E, et al. IL-32 and its splice variants are associated with protection against Mycobacterium tuberculosis infection and skewing of Th1/Th17 cytokines [J]. Journal of Leukocyte Biology, 2020, 107 (1): 113-118., articleTitle=IL-32 and its splice variants are associated with protection against Mycobacterium tuberculosis infection and skewing of Th1/Th17 cytokines, refAbstract=null), Reference(id=1322608180648067481, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2018, volume=9, issue=null, pageStart=1107, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=Fan L, Li DF, Zhang SJ, journalName=Frontiers in Microbiology, refType=null, unstructuredReference=Fan L, Li DF, Zhang SJ, et al. Parallel tests using culture, xpert MTB/RIF, and SAT-TB in sputum plus bronchial alveolar lavage fluid significantly increase diagnostic performance of Smear-Negative pulmonary tuberculosis [J]. Frontiers in Microbiology, 2018, 9: 1107., articleTitle=Parallel tests using culture, xpert MTB/RIF, and SAT-TB in sputum plus bronchial alveolar lavage fluid significantly increase diagnostic performance of Smear-Negative pulmonary tuberculosis, refAbstract=null), Reference(id=1322608180715176346, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=11, pageStart=1388, pageEnd=1394, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=崔灵绸, 石海萍, journalName=中国防痨杂志, refType=null, unstructuredReference=崔灵绸,石海萍. 某高校5起肺结核聚集性疫情特征分析 [J]. 中国防痨杂志, 2024, 46 (11): 1388-1394., articleTitle=某高校5起肺结核聚集性疫情特征分析, refAbstract=null), Reference(id=1322608180979417499, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=11, pageStart=1388, pageEnd=1394, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Cui LC, Shi HP, journalName=Chinese Journal of Antituberculosis, refType=null, unstructuredReference=Cui LC, Shi HP. Analysis of characteristics of 5 pulmonary tuberculosis cluster epidemics in a university [J]. Chinese Journal of Antituberculosis, 2024, 46 (11): 1388-1394. (In Chinese), articleTitle=Analysis of characteristics of 5 pulmonary tuberculosis cluster epidemics in a university, refAbstract=null), Reference(id=1322608181059109276, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2022, volume=34, issue=22, pageStart=19615, pageEnd=19627, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=Vernikou S, Lyras A, Kanavos A, journalName=Neural Computing & Applications, refType=null, unstructuredReference=Vernikou S, Lyras A, Kanavos A. Multiclass sentiment analysis on COVID-19-related tweets using deep learning models [J]. Neural Computing & Applications, 2022, 34 (22): 19615-19627., articleTitle=Multiclass sentiment analysis on COVID-19-related tweets using deep learning models, refAbstract=null), Reference(id=1322608181159772573, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=高建树, 郝世宇, 党一诺, journalName=中国药师, refType=null, unstructuredReference=高建树,郝世宇,党一诺, 等. 基于长短期记忆网络- Transformer模型参数优化的锂离子电池剩余使用寿命预测 [J/OL]. 中国药师:1-7 [2025-09-15]. http://kns.cnki.net/kcms/detail/42.1626.R.20200508.0915.002.html., articleTitle=基于长短期记忆网络- Transformer模型参数优化的锂离子电池剩余使用寿命预测, refAbstract=null), Reference(id=1322608181432402334, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=Gao JS, Hao SY, Dang YN, journalName=Automot Eng, refType=null, unstructuredReference=Gao JS, Hao SY, Dang YN, et al. Prediction of remaining service life of lithium-ion batteries based on Optimization of long-term and short-term memory network-Transformer model parameters [J/OL]. Automot Eng: 1-7 [2025-09-15]. http://kns.cnki.net/kcms/detail/42.1626.R.20200508.0915.002.html., articleTitle=Prediction of remaining service life of lithium-ion batteries based on Optimization of long-term and short-term memory network-Transformer model parameters, refAbstract=null), Reference(id=1322608181499511199, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=6, pageStart=30, pageEnd=35, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=余琼芳, 杨鹏飞, 唐高峰, journalName=工矿自动化, refType=null, unstructuredReference=余琼芳,杨鹏飞,唐高峰. 基于LSTM-Informer模型的液压支架压力时空多步长预测 [J]. 工矿自动化, 2024, 50 (6): 30-35., articleTitle=基于LSTM-Informer模型的液压支架压力时空多步长预测, refAbstract=null), Reference(id=1322608181575008672, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=6, pageStart=30, pageEnd=35, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=Yu QF, Yang PF, Tang GF, journalName=Industry and Mine Automation, refType=null, unstructuredReference=Yu QF, Yang PF, Tang GF. Spatiotemporal multi-step prediction of hydraulic support pressure based on LSTM-Informer model [J]. Industry and Mine Automation, 2024, 50 (6): 30-35. (In Chinese), articleTitle=Spatiotemporal multi-step prediction of hydraulic support pressure based on LSTM-Informer model, refAbstract=null), Reference(id=1322608181814084001, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2025, volume=21, issue=7, pageStart=6, pageEnd=10, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=杨玥, 左卫兵, journalName=电脑知识与技术, refType=null, unstructuredReference=杨玥,左卫兵. 基于GAT-Informer模型的河南省空气污染物浓度预测 [J]. 电脑知识与技术, 2025, 21 (7): 6-10., articleTitle=基于GAT-Informer模型的河南省空气污染物浓度预测, refAbstract=null), Reference(id=1322608181914747298, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2025, volume=21, issue=7, pageStart=6, pageEnd=10, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=Yang Y, Zuo WB, journalName=Computer Knowledge and Technology, refType=null, unstructuredReference=Yang Y, Zuo WB. Prediction of air pollutant concentration in Henan Province Based on gat informer model [J]. Computer Knowledge and Technology, 2025, 21 (7): 6-10. (In Chinese), articleTitle=Prediction of air pollutant concentration in Henan Province Based on gat informer model, refAbstract=null), Reference(id=1322608182011216291, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2021, volume=122, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=Li L, Jiang YW, Huang BQ, journalName=Journal of Biomedical Informatics, refType=null, unstructuredReference=Li L, Jiang YW, Huang BQ. Long-term prediction for temporal propagation of seasonal influenza using Transformer-based model [J]. Journal of Biomedical Informatics, 2021, 122: 103894., articleTitle=Long-term prediction for temporal propagation of seasonal influenza using Transformer-based model, refAbstract=null), Reference(id=1322608182304817572, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2023, volume=13, issue=1, pageStart=9955, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=Er S, Yang SH, Zhao T, journalName=Scientific Reports, refType=null, unstructuredReference=Er S, Yang SH, Zhao T. County augmented transformer for COVID-19 state hospitalizations prediction [J]. Scientific Reports, 2023, 13 (1): 9955., articleTitle=County augmented transformer for COVID-19 state hospitalizations prediction, refAbstract=null), Reference(id=1322608182443229606, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2012, volume=35, issue=12, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=Zhou H, Zhang S, Peng J, journalName=arXiv, refType=null, unstructuredReference=Zhou H, Zhang S, Peng J, et al. Informer: beyond efficient transformer for long sequence Time-Series forecasting [J]. arXiv, 2012, 35 (12): 1-8., articleTitle=Informer: beyond efficient transformer for long sequence Time-Series forecasting, refAbstract=null), Reference(id=1322608182665527719, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=Anonym , journalName=null, refType=null, unstructuredReference=Anonym . User2Vec: A novel representation for the information of the social networks for stock market predict [2025-09-15]. https://www.citexs.com/allSearchDetail?wid=4382940705., articleTitle=User2Vec: A novel representation for the information of the social networks for stock market predict, refAbstract=null), Reference(id=1322608182753608104, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2022, volume=10, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=Khan DM, Ali M, Iqbal N, journalName=Front Public Health, refType=null, unstructuredReference=Khan DM, Ali M, Iqbal N, et al. Short-Term prediction of COVID-19 using novel hybrid ensemble empirical mode decomposition and error trend seasonal model [J]. Front Public Health, 2022, 10: 922795., articleTitle=Short-Term prediction of COVID-19 using novel hybrid ensemble empirical mode decomposition and error trend seasonal model, refAbstract=null), Reference(id=1322608184754291113, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2022, volume=12, issue=4, pageStart=202, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=19, authorNames=Guo JQ, Wan BX, Zheng SY, journalName=Biosensors-BASEL, refType=null, unstructuredReference=Guo JQ, Wan BX, Zheng SY, et al. A teenager physical fitness evaluation model based on 1D-CNN with LSTM and wearable running PPG recordings [J]. Biosensors-BASEL, 2022, 12 (4): 202., articleTitle=A teenager physical fitness evaluation model based on 1D-CNN with LSTM and wearable running PPG recordings, refAbstract=null), Reference(id=1322608185165332906, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2019, volume=30, issue=5, pageStart=11, pageEnd=14, url=null, language=null, rfNumber=[16], rfOrder=20, authorNames=王淑平, 杜敏, 罗建伟, journalName=公共卫生与预防医学, refType=null, unstructuredReference=王淑平,杜敏,罗建伟, 等. GM(1,1)模型与LSTM神经网络在肺结核发病数预测中的应用 [J]. 公共卫生与预防医学, 2019, 30 (5): 11-14., articleTitle=GM(1,1)模型与LSTM神经网络在肺结核发病数预测中的应用, refAbstract=null), Reference(id=1322608185236636075, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2019, volume=30, issue=5, pageStart=11, pageEnd=14, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=Wang SP, Du M, Luo JW, journalName=Journal of Public Health and Preventive Medicine, refType=null, unstructuredReference=Wang SP, Du M, Luo JW, et al. Application of GM(1,1)model and LSTM neural network in predicting the incidence of pulmonary tuberculosis [J]. Journal of Public Health and Preventive Medicine, 2019, 30 (5): 11-14. (In Chinese), articleTitle=Application of GM(1,1)model and LSTM neural network in predicting the incidence of pulmonary tuberculosis, refAbstract=null), Reference(id=1322608185307939244, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2022, volume=20, issue=null, pageStart=5364, pageEnd=5377, url=null, language=null, rfNumber=[17], rfOrder=22, authorNames=Wang L, Zhang XD, Tang JW, journalName=Computational and Structural Biotechnology Journal, refType=null, unstructuredReference=Wang L, Zhang XD, Tang JW, et al. Machine learning analysis of SERS fingerprinting for the rapid determination of Mycobacterium tuberculosis infection and drug resistance [J]. Computational and Structural Biotechnology Journal, 2022, 20: 5364-5377., articleTitle=Machine learning analysis of SERS fingerprinting for the rapid determination of Mycobacterium tuberculosis infection and drug resistance, refAbstract=null), Reference(id=1322608185588957613, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=14, url=null, language=null, rfNumber=[18], rfOrder=23, authorNames=陈迁任, 全航, 胡鹏, journalName=特种油气藏, refType=null, unstructuredReference=陈迁任,全航,胡鹏. 基于Informer算法的间开气井产气量预测方法 [J/OL]. 特种油气藏, 1-14 [2025-09-15]. https://link.cnki.net/urlid/21.1357.TE.20250114.1829.014., articleTitle=基于Informer算法的间开气井产气量预测方法, refAbstract=null), Reference(id=1322608185656066478, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=14, url=null, language=null, rfNumber=[18], rfOrder=24, authorNames=Chen QR, Quan H, Hu P, journalName=Spec Oil Gas Reserv, refType=null, unstructuredReference=Chen QR, Quan H, Hu P. Gas production prediction method of open gas wells based on informer algorithm [J/OL]. Spec Oil Gas Reserv, 1-14 [2025-09-15]. https://link.cnki.net/urlid/21.1357.TE.20250114.1829.014. (In Chinese), articleTitle=Gas production prediction method of open gas wells based on informer algorithm, refAbstract=null), Reference(id=1322608186012582319, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2025, volume=11, issue=1, pageStart=135, pageEnd=149, url=null, language=null, rfNumber=[19], rfOrder=25, authorNames=曹建文, 委兴宝, 杨裔, journalName=大数据, refType=null, unstructuredReference=曹建文,委兴宝,杨裔, 等. 基于时间序列的非周期预测模型 [J]. 大数据, 2025, 11 (1): 135-149., articleTitle=基于时间序列的非周期预测模型, refAbstract=null), Reference(id=1322608186100662704, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2025, volume=11, issue=1, pageStart=135, pageEnd=149, url=null, language=null, rfNumber=[19], rfOrder=26, authorNames=Cao JW, Wei XB, Yang Y, journalName=Big Data Research, refType=null, unstructuredReference=Cao JW, Wei XB, Yang Y, et al. Model for non-periodic time series prediction [J]. Big Data Research, 2025, 11 (1): 135-149. (In Chinese), articleTitle=Model for non-periodic time series prediction, refAbstract=null), Reference(id=1322608186507510193, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2022, volume=20, issue=1, pageStart=524, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=27, authorNames=Xie H, Chen ZJ, Deng JC, journalName=Journal of Translational Medicine, refType=null, unstructuredReference=Xie H, Chen ZJ, Deng JC, et al. Automatic segmentation of the gross target volume in radiotherapy for lung cancer using transresSEUnet 2.5D Network [J]. Journal of Translational Medicine, 2022, 20 (1): 524., articleTitle=Automatic segmentation of the gross target volume in radiotherapy for lung cancer using transresSEUnet 2.5D Network, refAbstract=null), Reference(id=1322608186855637426, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2024, volume=55, issue=2, pageStart=330, pageEnd=336, url=null, language=null, rfNumber=[21], rfOrder=28, authorNames=易海波, 高兴红, 罗果, journalName=四川大学学报(医学版), refType=null, unstructuredReference=易海波,高兴红,罗果, 等. 结核分枝杆菌Rv3432c蛋白的原核表达与生物信息学分析 [J]. 四川大学学报(医学版), 2024, 55 (2): 330-336., articleTitle=结核分枝杆菌Rv3432c蛋白的原核表达与生物信息学分析, refAbstract=null), Reference(id=1322608187283456435, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2024, volume=55, issue=2, pageStart=330, pageEnd=336, url=null, language=null, rfNumber=[21], rfOrder=29, authorNames=Yi HB, Gao XH, Luo G, journalName=J Sichuan Univ(Med Sci), refType=null, unstructuredReference=Yi HB, Gao XH, Luo G, et al. Prokaryotic expression and bioinformatics analysis of rv3432c protein of Mycobacterium tuberculosis [J]. J Sichuan Univ(Med Sci), 2024, 55 (2): 330-336. (In Chinese), articleTitle=Prokaryotic expression and bioinformatics analysis of rv3432c protein of Mycobacterium tuberculosis, refAbstract=null), Reference(id=1322608187388314036, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=30, authorNames=李忠奇, journalName=null, refType=null, unstructuredReference=李忠奇. 气象因素及空气污染物与肺结核发病风险的关联研究 [D]. 南京:南京医科大学, 2023., articleTitle=气象因素及空气污染物与肺结核发病风险的关联研究, refAbstract=null), Reference(id=1322608189414162869, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=31, authorNames=Li ZQ, journalName=null, refType=null, unstructuredReference=Li ZQ. Association study of meteorological factors and air pollutants with the risk of pulmonary tuberculosis [D]. Nanjing: Nanjing Medical University, 2023. (In Chinese), articleTitle=Association study of meteorological factors and air pollutants with the risk of pulmonary tuberculosis, refAbstract=null)], funds=[Fund(id=1322608178206982547, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, awardId=2024-2-29, language=CN, fundingSource=健康山东建设揭榜攻关面上项目(2024-2-29), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322608169797402956, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=1., ext=[AuthorCompanyExt(id=1322608169809985869, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China), AuthorCompanyExt(id=1322608169814180174, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学公共卫生学院,河北 唐山 063210)]), AuthorCompany(id=1322608171332518223, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=2., ext=[AuthorCompanyExt(id=1322608171340906832, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171332518223, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.潍坊护理职业学院,山东 潍坊 261000)]), AuthorCompany(id=1322608171412210001, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=3., ext=[AuthorCompanyExt(id=1322608171420598610, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171412210001, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.济宁市疾病预防控制中心)])], figs=[ArticleFig(id=1322608176885776777, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=EN, label=Figure 1, caption=Principle framework of Informer model, figureFileSmall=/zdaPXycEpPuXrbDrUFsMw==, figureFileBig=5rbOgKyoKZujkRdbjQDDUg==, tableContent=null), ArticleFig(id=1322608176952885642, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=CN, label=图1, caption=Informer模型的原理框架, figureFileSmall=/zdaPXycEpPuXrbDrUFsMw==, figureFileBig=5rbOgKyoKZujkRdbjQDDUg==, tableContent=null), ArticleFig(id=1322608177347150219, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=EN, label=Figure 2, caption=Time sequence diagram of pulmonary tuberculosis incidence in Jining City from 2010 to 2022, figureFileSmall=txO2SH13gb4tFE48C9VdRA==, figureFileBig=Uf4QXboHH9w9zcBxfGEEnQ==, tableContent=null), ArticleFig(id=1322608177636557196, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=CN, label=图2, caption=2010—2022年济宁市肺结核发病率时序图, figureFileSmall=txO2SH13gb4tFE48C9VdRA==, figureFileBig=Uf4QXboHH9w9zcBxfGEEnQ==, tableContent=null), ArticleFig(id=1322608177720443277, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=EN, label=Figure 3, caption=Comparison of prediction effects of various models, figureFileSmall=JkXFtUjPHqKxswkzuYcwyw==, figureFileBig=SEIwOeY2T/4prTy6gzIfYQ==, tableContent=null), ArticleFig(id=1322608177795940750, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=CN, label=图3, caption=各模型预测效果对比

注:A为预测12个月各模型效果对比,B为预测18个月各模型效果对比,C为预测24个月各模型效果对比。

, figureFileSmall=JkXFtUjPHqKxswkzuYcwyw==, figureFileBig=SEIwOeY2T/4prTy6gzIfYQ==, tableContent=null), ArticleFig(id=1322608177867243919, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=EN, label=Table 1, caption=

Introduction and settings of important parameters of Informer model

, figureFileSmall=null, figureFileBig=null, tableContent=
名称参数意义解释常用取值本研究取值
batch_size批次大小,每次迭代中用于更新模型参数的样本数量32~51232
d_model模型隐藏的特征,用于设置输入和输出的特征维度32~12832
n_heads多头自注意力机制中注意力头的数量2/4/6/84
e_layers编码器层数1/2/31
d_layers解码器层数1/2/31
d_ff前馈网络维度,编码器/解码器内部全连接层的扩展维度32~12832
learnin_rate学习率,模型控制参数更新步长的超参数0.000 1~0.010.001
dropout丢弃概率,在训练中以某种概率忽略部分神经元,防止过拟合0.1~0.60.3
train_epochs训练次数,整个数据集被模型用来训练的次数50~1 000500
), ArticleFig(id=1322608177951130000, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=CN, label=表1, caption=

Informer 模型重要参数介绍及设置

, figureFileSmall=null, figureFileBig=null, tableContent=
名称参数意义解释常用取值本研究取值
batch_size批次大小,每次迭代中用于更新模型参数的样本数量32~51232
d_model模型隐藏的特征,用于设置输入和输出的特征维度32~12832
n_heads多头自注意力机制中注意力头的数量2/4/6/84
e_layers编码器层数1/2/31
d_layers解码器层数1/2/31
d_ff前馈网络维度,编码器/解码器内部全连接层的扩展维度32~12832
learnin_rate学习率,模型控制参数更新步长的超参数0.000 1~0.010.001
dropout丢弃概率,在训练中以某种概率忽略部分神经元,防止过拟合0.1~0.60.3
train_epochs训练次数,整个数据集被模型用来训练的次数50~1 000500
), ArticleFig(id=1322608178039210385, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=EN, label=Table 2, caption=

Comparison of model performance under different prediction lengths

, figureFileSmall=null, figureFileBig=null, tableContent=
时间(月)模型MSERMSEMAEMAPER2值
12LSTM0.0690.2640.2350.1870.623
Informer0.0440.2110.1790.1250.759
LSTM-Informer0.0280.1660.1550.1150.850
18LSTM0.0770.2780.2360.1780.437
Informer0.0320.1790.1470.1030.767
LSTM-Informer0.0260.1620.1400.1040.808
24LSTM0.1130.3360.2680.1950.001
Informer0.0310.1770.1450.0930.722
LSTM-Informer0.0250.1570.1320.0930.782
), ArticleFig(id=1322608178106319250, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, language=CN, label=表2, caption=

不同预测长度下的模型性能比较

, figureFileSmall=null, figureFileBig=null, tableContent=
时间(月)模型MSERMSEMAEMAPER2值
12LSTM0.0690.2640.2350.1870.623
Informer0.0440.2110.1790.1250.759
LSTM-Informer0.0280.1660.1550.1150.850
18LSTM0.0770.2780.2360.1780.437
Informer0.0320.1790.1470.1030.767
LSTM-Informer0.0260.1620.1400.1040.808
24LSTM0.1130.3360.2680.1950.001
Informer0.0310.1770.1450.0930.722
LSTM-Informer0.0250.1570.1320.0930.782
)], attaches=null, journal=Journal(id=1227664546253402114, delFlag=0, nameCn=现代预防医学, nameEn=Modern Preventive Medicine, nameHistory1=null, nameHistory2=null, issn=1003-8507, eissn=null, cn=51-1365/R, coden=null, periodic=3, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=IeiuPXEZi6AA+k0VfvoiOQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Modern Preventive Medicine, journalRemark=null, publicationField=null, createdTime=1770627636734, updatedTime=1788949112281, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=X, firstLetterEn=X, subjectCode=Medical and Pharmaceutical Sciences, subjectName=null, subjectCodeEn=Medical and Pharmaceutical Sciences, subjectNameEn=null, picCn=IeiuPXEZi6AA+k0VfvoiOQ==, picEn=/9iTl8/ndms4tBz1fL28Pg==, jcr=null, cjcr=null, exts=[JournalExt(id=1304510385713861624, language=CN, name=现代预防医学, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788949112585, updatedTime=1788949112585, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://xdyfyxzz.paperopen.com/#/regist, submissionEditorUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionReviewUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304510385772581881, language=EN, name=Modern Preventive Medicine, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788949112599, updatedTime=1788949112599, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://xdyfyxzz.paperopen.com/#/regist, submissionEditorUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionReviewUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1227665162245664772, websiteList=[Website(id=1227687234141352800, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227665162245664772, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/xdyfyx/CN, language=CN, createTime=1770633045945, createBy=18614031015, updateTime=1770633090526, updateBy=18614031015, name=现代预防医学-中文, tplId=1146099689490845704, title=现代预防医学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1227687735088051072, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=articleTextType, value=kx, createTime=1770633165380, updateTime=1770633165380, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735071273853, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=banner, value=null, createTime=1770633165376, updateTime=1770633165376, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735113216899, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=grayFlag, value=0, createTime=1770633165386, updateTime=1770633165386, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735062885244, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=logo, value=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/file/pic?fileId=/XB5plC0xuykmQnycvtyrw==, createTime=1770633165374, updateTime=1770633165374, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735125799813, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=minRunFlag, value=0, createTime=1770633165389, updateTime=1770633165389, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735083856767, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/file/pic, createTime=1770633165379, updateTime=1770633165379, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735121605508, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=silenceFlag, value=0, createTime=1770633165388, updateTime=1770633165388, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735079662462, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770633165378, updateTime=1770633165378, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735096439681, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=themeColor, value=null, createTime=1770633165382, updateTime=1770633165382, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735104828290, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=themeStyle, value=null, createTime=1770633165384, updateTime=1770633165384, creator=18614031015, updator=18614031015)]), Website(id=1227687234338485094, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227665162245664772, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/xdyfyx/EN, language=EN, createTime=1770633045992, createBy=18614031015, updateTime=1770633115374, updateBy=18614031015, name=现代预防医学-英文, tplId=1146101810881728533, title=Modern Preventive Medicine, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1227687709129507332, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=articleTextType, value=kx, createTime=1770633159191, updateTime=1770633159191, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709108535809, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=banner, value=null, createTime=1770633159186, updateTime=1770633159186, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709167256071, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=grayFlag, value=0, createTime=1770633159200, updateTime=1770633159200, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709095952896, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=logo, value=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/file/pic?fileId=/XB5plC0xuykmQnycvtyrw==, createTime=1770633159183, updateTime=1770633159183, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709179838985, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=minRunFlag, value=0, createTime=1770633159203, updateTime=1770633159203, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709121118723, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/file/pic, createTime=1770633159189, updateTime=1770633159189, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709171450376, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=silenceFlag, value=0, createTime=1770633159201, updateTime=1770633159201, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709112730114, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770633159187, updateTime=1770633159187, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709133701637, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=themeColor, value=null, createTime=1770633159192, updateTime=1770633159192, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709154673158, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=themeStyle, value=null, createTime=1770633159197, updateTime=1770633159197, creator=18614031015, updator=18614031015)])], journalTitle=现代预防医学, weixinUrl=null, journalUrl=http://xdyfyxzz.paperopen.com/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Modern Preventive Medicine, journalPhotoCn=IeiuPXEZi6AA+k0VfvoiOQ==, journalPhotoEn=/9iTl8/ndms4tBz1fL28Pg==, journalFirstLetter=X, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/10.20043/j.cnki.MPM.202505216, detailUrlEn=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/10.20043/j.cnki.MPM.202505216, pdfUrlCn=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/PDF/10.20043/j.cnki.MPM.202505216, pdfUrlEn=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/PDF/10.20043/j.cnki.MPM.202505216, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1762704000000, fullTextJson=null, articleText=null, reference=null)
收藏切换
LSTM-Informer模型在肺结核发病率预测中的应用
收藏切换
PDF下载
李青林 1, 2 , 苏金铭 1, 2 , 杨舒越 1, 2 , 梁玉民 3 , 姜文国 3 , 刘伟 3 , 薛玲 1 , 王文军 2
现代预防医学 | 流行病与统计方法 2025,52(21): 3893-3899
收起
收藏切换
现代预防医学 |流行病与统计方法 2025 , 52 (21) : 3893 -3899
LSTM-Informer模型在肺结核发病率预测中的应用
全屏
[Author(id=1322608171479318868, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608171743560023, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608171479318868, language=EN, stringName=Qing-lin LI, firstName=Qing-lin, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608171814863192, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608171479318868, language=CN, stringName=李青林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.华北理工大学公共卫生学院,河北 唐山 063210
2.潍坊护理职业学院,山东 潍坊 261000, bio={"content":"

李青林(1998—),男,硕士在读,研究方向:传染病流行病学,疾病预防与控制

"}, bioImg=null, bioContent=

李青林(1998—),男,硕士在读,研究方向:传染病流行病学,疾病预防与控制

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608169797402956, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=1., ext=[AuthorCompanyExt(id=1322608169809985869, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China), AuthorCompanyExt(id=1322608169814180174, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学公共卫生学院,河北 唐山 063210)]), AuthorCompany(id=1322608171332518223, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=2., ext=[AuthorCompanyExt(id=1322608171340906832, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171332518223, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.潍坊护理职业学院,山东 潍坊 261000)])]), Author(id=1322608171881972058, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608171982635357, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608171881972058, language=EN, stringName=Jin-ming SU, firstName=Jin-ming, middleName=null, lastName=SU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608172070715742, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608171881972058, language=CN, stringName=苏金铭, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.华北理工大学公共卫生学院,河北 唐山 063210
2.潍坊护理职业学院,山东 潍坊 261000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608169797402956, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=1., ext=[AuthorCompanyExt(id=1322608169809985869, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China), AuthorCompanyExt(id=1322608169814180174, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学公共卫生学院,河北 唐山 063210)]), AuthorCompany(id=1322608171332518223, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=2., ext=[AuthorCompanyExt(id=1322608171340906832, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171332518223, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.潍坊护理职业学院,山东 潍坊 261000)])]), Author(id=1322608172213322080, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608172297208163, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608172213322080, language=EN, stringName=Shu-yue YANG, firstName=Shu-yue, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608172590809444, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608172213322080, language=CN, stringName=杨舒越, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.华北理工大学公共卫生学院,河北 唐山 063210
2.潍坊护理职业学院,山东 潍坊 261000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608169797402956, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=1., ext=[AuthorCompanyExt(id=1322608169809985869, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China), AuthorCompanyExt(id=1322608169814180174, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学公共卫生学院,河北 唐山 063210)]), AuthorCompany(id=1322608171332518223, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=2., ext=[AuthorCompanyExt(id=1322608171340906832, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171332518223, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.潍坊护理职业学院,山东 潍坊 261000)])]), Author(id=1322608172657918311, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608172741804393, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608172657918311, language=EN, stringName=Yu-min LIANG, firstName=Yu-min, middleName=null, lastName=LIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608173056377195, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608172657918311, language=CN, stringName=梁玉民, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.济宁市疾病预防控制中心, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608171412210001, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=3., ext=[AuthorCompanyExt(id=1322608171420598610, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171412210001, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.济宁市疾病预防控制中心)])]), Author(id=1322608173123486061, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608173194789231, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608173123486061, language=EN, stringName=Wen-guo JIANG, firstName=Wen-guo, middleName=null, lastName=JIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608173425475952, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608173123486061, language=CN, stringName=姜文国, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.济宁市疾病预防控制中心, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608171412210001, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=3., ext=[AuthorCompanyExt(id=1322608171420598610, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171412210001, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.济宁市疾病预防控制中心)])]), Author(id=1322608173488390514, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608173572276596, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608173488390514, language=EN, stringName=Wei LIU, firstName=Wei, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608173630996853, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608173488390514, language=CN, stringName=刘伟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.济宁市疾病预防控制中心, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608171412210001, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=3., ext=[AuthorCompanyExt(id=1322608171420598610, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171412210001, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.济宁市疾病预防控制中心)])]), Author(id=1322608173853294967, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322608173932986745, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608173853294967, language=EN, stringName=Ling XUE, firstName=Ling, middleName=null, lastName=XUE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608174004289914, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608173853294967, language=CN, stringName=薛玲, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.华北理工大学公共卫生学院,河北 唐山 063210, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608169797402956, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=1., ext=[AuthorCompanyExt(id=1322608169809985869, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China), AuthorCompanyExt(id=1322608169814180174, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608169797402956, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.华北理工大学公共卫生学院,河北 唐山 063210)])]), Author(id=1322608174104953212, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, orderNo=7, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wwjun1973@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322608175761703294, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608174104953212, language=EN, stringName=Wen-jun WANG, firstName=Wen-jun, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322608175845589376, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, authorId=1322608174104953212, language=CN, stringName=王文军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.潍坊护理职业学院,山东 潍坊 261000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322608171332518223, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, xref=2., ext=[AuthorCompanyExt(id=1322608171340906832, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1322608156249800990, companyId=1322608171332518223, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.潍坊护理职业学院,山东 潍坊 261000)])])]
李青林1, 2, 苏金铭1, 2, 杨舒越1, 2, 梁玉民3, 姜文国3, 刘伟3, 薛玲1, 王文军2
作者信息
  • 1.华北理工大学公共卫生学院,河北 唐山 063210
  • 2.潍坊护理职业学院,山东 潍坊 261000
  • 3.济宁市疾病预防控制中心
通讯作者:
王文军,E-mail:
作者简介:

李青林(1998—),男,硕士在读,研究方向:传染病流行病学,疾病预防与控制

Application of LSTM-Informer model in the prediction of pulmonary tuberculosis incidence
Qing-lin LI1, 2, Jin-ming SU1, 2, Shu-yue YANG1, 2, Yu-min LIANG3, Wen-guo JIANG3, Wei LIU3, Ling XUE1, Wen-jun WANG2
Affiliations
  • School of Public Health, North China University of Science and Technology, Tangshan, Hebei 063210, China
出版时间: 2025-11-10 doi: 10.20043/j.cnki.MPM.202505216
文章导航
收藏切换
目的

探究前沿模型长短期记忆神经网络(long short-term memory,LSTM)-Informer在肺结核病率预测预警中的应用,为相关部门制定防治措施提供参考,同时为其他传染病的预测提供新的方法和思路。

方法

通过《国家传染病网络直报系统》获得济宁市2010年1月1日—2022年12月31日肺结核发病资料,并结合《济宁市统计年鉴2010—2022》计算月度发病率数据;分别以数据最后12、18和24个月为测试集用于模型效果评价,其余为训练集构建LSTM-Informer模型并与LSTM、Informer单一模型进行比较,测试组合模型的可靠性。

结果

使用均方误差(mean squared error,MSE)、均方根误差(root mean squared error,RMSE)、平均绝对误差(mean absolute error,MAE)、平均绝对百分比误差(mean absolute percentage error,MAPE)和决定系数(R2)误差指标对比三个模型在不同预测时间下肺结核发病趋势中的预测效能。结果显示,LSTM-Informer模型性能均优于单一模型,在12个月长度的预测中,该模型MSE为0.028,较LSTM降低了59.4%,MAE值0.155,较LSTM减少34.0%,R2值为0.850;当时间延长至18个月时,其MAPE指标稳定在0.104,R2值为0.808;在24个月预测长度下,LSTM-Informer模型仍可以保持较好的优势(R2=0.782)。

结论

对比单一模型来看,基于局部-全局特征提取的LSTM-Informer模型在中长期预测中明显提高了预测精度,有望为当地肺结核发病预警系统提供新的理论支持与参考。

肺结核  /  深度学习  /  LSTM-Informer模型  /  预测
Objective

To explore the application of the advanced LSTM-Informer model in predicting and early warning of pulmonary tuberculosis incidence, providing a reference for relevant authorities to formulate prevention and control measures, and offering new methodologies and insights for forecasting other infectious diseases.

Methods

Pulmonary tuberculosis incidence data for Jining City from January 1, 2010, to December 31, 2022, were obtained from the National Notifiable Disease Reporting System (NNDRS). Monthly incidence rates were calculated by integrating demographic data from the Jining Statistical Yearbook (2010—2022). The final 12, 18, and 24 months of data were used as test sets to evaluate model performance, with the remaining data constituting the training set. The LSTM-Informer model was constructed and its reliability assessed through comparison with standalone LSTM and Informer models.

Results

The predictive performance of the three models across different forecast horizons was evaluated using error metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and the Coefficient of Determination(R2). Results demonstrated that the LSTM-Informer model consistently outperformed the single models. In the prediction of the 12-month length, the MSE of the model was 0.028, which was 59.4% lower than that of LSTM, the MAE value of 0.155 was 34.0% lower than that of LSTM, and the R2 value was 0.850. When the forecast horizon extended to 18 months, the model maintained a stable MAPE of 0.104 and an R2 of 0.808. Even at the 24-month horizon, the LSTM-Informer model retained significant advantages(R2=0.782).

Conclusion

Compared to single models, the LSTM-Informer model, leveraging both local and global feature extraction, significantly enhances prediction accuracy for medium-to-long-term forecasts. It shows considerable promise for providing novel theoretical support and reference for developing pulmonary tuberculosis incidence early-warning systems locally.

Pulmonary tuberculosis  /  Deep learning  /  LSTM-Informer model  /  Forecasting
李青林, 苏金铭, 杨舒越, 梁玉民, 姜文国, 刘伟, 薛玲, 王文军. LSTM-Informer模型在肺结核发病率预测中的应用. 现代预防医学, 2025 , 52 (21) : 3893 -3899 . DOI: 10.20043/j.cnki.MPM.202505216
Qing-lin LI, Jin-ming SU, Shu-yue YANG, Yu-min LIANG, Wen-guo JIANG, Wei LIU, Ling XUE, Wen-jun WANG. Application of LSTM-Informer model in the prediction of pulmonary tuberculosis incidence[J]. Modern Preventive Medicine, 2025 , 52 (21) : 3893 -3899 . DOI: 10.20043/j.cnki.MPM.202505216
肺结核是由结核分枝杆菌引发的严重慢性呼吸道传染病,主要通过飞沫传播[1]。作为我国法定乙类传染病,肺结核的发病率和死亡率一直位居乙类传染病前列,对人民身心健康造成了沉重的负担[2]。随着现代医学科学技术的不断发展与公众防控意识的提升,结核病的传播得到了一定程度的控制,但肺结核依然是当今世界的主要公共卫生问题之一[3-4]。因此,选择合适的预测方法和工具,对肺结核发生发展的规律做出准确预测,便成了疾病防控工作中不可缺少的一环。
肺结核具有潜伏周期长、病程迁延的特点,这使得疾病的传播和防控周期往往跨越数月乃至数年[5],而传统机器学习模型因受限于数据线性与平稳性的假设,更适合进行以短期、线性趋势为主的预测[6],不适合进行如肺结核这类需中长期预测的疾病。伴随着算法的不断完善和新算法的提出,深度学习技术在时间序列预测领域取得了快速发展。近年来,Transformer及其变体模型已成为时间序列预测领域的一个新热点,该模型拥有强大的序列建模能力和出色的长距离依赖关系捕捉能力[7],在疾病预测、电力工业、气象预测等领域均有出色的应用表现[8-9]。如Li运用Transformer模型对美国与日本流感的发病情况进行了预测,并与传统的自回归模型(autoregressive model, AR)和递归神经网络(recurrent neural network, RNN)模型进行了效果对比。结果显示,Transformer模型在长期预测中具有更好的预测表现[10]。Er等人[11]基于Transformer模型提出了一种County Augmented Transformer(CAT)的方法,用于COVID-19 导致的州级住院人数预测,同样取得了优于基线模型的效果,Transformer 系列模型在传染病预测领域正展现出卓越的应用潜力。Informer模型是基于Transformer架构的一种优化版本,在模型的设计上,Informer模型引入了概率稀疏自注意力机制、蒸馏操作和生成式解码器等内容,针对时序预测任务进行了优化改进,优化后的模型在进行长时间序列预测时明显比原模型更加高效和准确[12];但这种架构可能会导致模型在处理复杂的时间序列数据时,存在对周期性时间依赖特征与瞬态变化的感知表现欠佳的问题。而通过门控机制进行数据处理的长短期记忆神经网络(long short-term memory,LSTM),能够很好的捕捉时间序列数据中的短期波动动态关系[13]。为此,本研究结合LSTM与 Informer模型的优点,提出了一种改进型的 LSTM-Informer 模型。并与单一LSTM、Informer模型的预测效果进行比较,以便为肺结核的预警与防控提供参考和依据。
本研究通过《国家传染病网络直报系统》获得济宁市2010年1月1日—2022年12月31日肺结核发病资料,通过《济宁市统计年鉴(2010—2022)》获得济宁市人口信息。
本研究在数据清洗和整理时剔除了部分重复上报数据和信息不完整、不规范的无效数据。数据均通过严格的多级审核,未出现单位数值缺失的情况。此外,本研究在严格遵循时序数据预测的预处理规范下,采用了Min-Max归一化(范围[0,1])的方法来消除内部量纲干扰并提高模型的稳定性。
LSTM是一种基于RNN的深度学习模型。该模型采用了特殊的门控制机制与记忆单元系统,来解决传统RNN因长期依赖而导致的梯度消失或爆炸问题[14-16]。LSTM的核心在于其神经元内部的三门结构——遗忘门、输入门和输出门,遗忘门决定了在处理数据时,记忆单元应该遗忘哪些无关的信息,输入门决定了哪些新的信息流入记忆单元,输出门决定哪些信息特征被传递并最终输出[17]。这种三门协作的处理方式,可以有效调节信息的保留与遗忘,从而使其能够胜任复杂的动态时序预测任务。LSTM模型的数学公式如下:
以上公式中,ft、it和ot分别表示t时刻的遗忘门、输入门和输出门;ct表示t时刻的神经元单元的状态;xt表示t时刻神经元的输入,ht-1代表上一时刻的隐藏输出。σ为Sigmoid函数。
Informer模型在Transformer架构基础上进行了改进,模型采用了概率稀疏自注意力机制、自注意力蒸馏和生成式解码器等内容进一步提升预测的效率与精度[12]。在预测效率方面,Informer可以通过概率稀疏化策略筛选出原始序列中具有显著贡献的Query向量,以此降低自注意力机制的计算复杂度;自注意力蒸馏操作则是对序列进行逐层压缩,在保留主导注意力特征的基础上忽略数据中无关紧要的细节,降低冗余信息的干扰,提高计算效率。在精度上,模型在解码阶段以动态生成权重矩阵的方式,一次性输出整个预测序列,可以避免逐步递归预测带来的误差累积问题[18]。
模型中稀疏自注意力机制的原理是将输入序列矩阵首先分解为查询矩阵Q、键矩阵K和值矩阵V,即Q=XWQ,K=XWK,V=XWV。之后通过KL散度公式度量每个查询向量与键向量集合的关联性。稀疏性度量的公式为:
式中为评价向量qi是否重要的指标,值越大,向量qi越重要;是对键矩阵K采样后得到的矩阵。Kj是K的第j行,为缩放因子;d为K的列数,LK为K的行数。该式子的前半部分是代表第i个查询向量在所有键向量上的LS(Log-Sum-Exp),后半部分是对其求算术平均值。最后通过KL散度计算,确定相关性前u个查询向量作为稀疏性查询向量。由此得出了稀疏自注意力计算公式:
这种选择性的计算方式使计算复杂度从O (L2)降为O (LlnL),提高了计算效率。
输入的数据通过稀疏自注意力机制处理后,会被选出具有主导地位的特征元素,之后自注意力蒸馏机制在编码器中逐层压缩数据特征维度,进一步蒸馏掉其余冗杂元素来减少内存消耗,其数学表达为:
式中MaxPool是最大池化操作,Convld是一维卷积操作,ELU是激活函数;是多头自注意力机制模块和基本操作。Informer模型的解码器采用了生成式预测模式,可以直接输出多步预测结果,其输入的序列是由历史序列与目标占位符拼接构成的混合序列,公式为:
其中为预测开始时的已知序列,为0值填充的待预测序列。
Informer模型的原理框架图如图1所示。编码器由独立堆栈的双模块协同机制组成,输入的序列会依次经过概率稀疏自注意力模块和自注意力蒸馏操作模块,以进行数据特征的筛选和关键时序节点的识别并形成注意力特征图,之后注意力特征图会被输入到解码器的多头注意力板块。解码器接收的是由历史已知数据与0值填充的待预测数据构成的混合序列,该序列会被输入到解码器的多头概率稀疏自注意力层,之后通过跨模态注意力层与注意力特征图进行动态特征交互,最终通过全连接网络实现隐式特征空间映射,直接输出时间序列的多步预测结果[19-20]。
Informer基于概率稀疏自注意力机制和数据蒸馏的方法,能较好的捕捉时间序列中的长期全局依赖关系。但该机制通过稀疏化减少计算量的同时,影响了模型对数据局部细微信息的处理,一方面,其注意力权重分布偏重于跨周期的全局模式,导致模型难以提取相邻短周期内局部时序间的关联;另一方面,注意力头的稀疏筛选过程会无意中忽略一些关键的细节特征,使得模型在需兼顾长期趋势和短期波动的场景中表现受限[8]。而基于三门控制机制的LSTM模型,可以很好的捕捉序列局部时序特征与短期波动关系,使得模型具备察觉数据局部细微变化的敏感性。LSTM与Informer结合的方式,可以充分利用数据中的有效信息,在保留对长序列处理优势的同时,兼顾模型对瞬态特征的敏感性。
LSTM-Informer 模型的整体运行逻辑是通过LSTM网络捕获时间序列的中短期波动、周期性片段等局部细节特征,再将提取的隐层状态输入Informer模块,借助Informer中概率稀疏自注意力机制解析跨时间步的全局依赖关系,最终形成局部-全局联合的建模方案。
分别将整体数据的最后12个月、18个月、24个月作为测试集用于模型预测效果的评价,剩余数据作为训练集进行模型的拟合训练。为了对模型性能进行全面评价,本研究采用均方误差(mean squared error, MSE)、均方根误差(root mean squared error, RMSE)、平均绝对误差(mean absolute error, MAE)、平均绝对百分比误差(mean absolute percentage error, MAPE)和决定系数(R2)这五个指标从不同角度对模型进行评估。计算这些指标的公式如下:
所有数据均采用Excel 2016软件进行整理,并在Python 3.9环境下使用TensorFlow与PyTorch 框架完成LSTM模型、Informer模型和LSTM-Informer模型的构建。
2010—2022年,济宁市肺结核发病率呈逐渐下降趋势,累积发病39 984例,年平均发病率为35.64/10万。其中2010年发病率最高,为52.33/10万,2022年发病率最低,为18.29/10万。结合整体时序图与具体数据可以看出,每年1月份左右为疾病高发时段,且具有明显的季节性和周期性,结果见图2。
模型超参数的设置对模型性能、泛化能力和最终预测效果至关重要,调整和优化模型参数是提高模型效果的关键之一。本研究模型的超参数根据数据情况并参考取值范围,在多次重复试验后,最终取值如下:批量大小为32,模型维度为32,多头注意力头数为4,解码器层数与编码器层数为1,模型学习率设置为0.001,训练次数为500次,激活函数选择gelu,时间步长为12。表1展示的是模型各超参数的解释、常用取值范围以及本研究的最终取值汇总。为了客观评估组合模型和单一模型的性能,Informer模型采用与LSTM-Informer相同的超参数设置,LSTM模型采用贝叶斯算法选取最佳参数,各模型均采用相同的数据集进行建模。
本研究通过MSE、RMSE、MAE、MAPE和R2五项指标系统评估了不同模型在12、18和24个月时间窗口下的预测性能,见表2、图3。LSTM模型在12个月时取得尚可的预测效果(R2=0.623),但与其他模型相比均有一定差距,且随窗口延长误差显著递增,至24个月时基本丧失了有效预测能力。相比之下,Informer模型则表现更加稳定,预测长度不断增大的过程中,其R2值均保持在0.7以上,其余指标均比LSTM有较明显的下降。LSTM-Informer模型则在所有预测长度上均表现最优,在12个月长度的预测中,该模型MSE为0.028,较LSTM降低了59.4%,MAE值0.155,较LSTM减少34.0%,R2值达到了0.850;预测时间延长至18个月时,其MAPE指标稳定在0.104,虽R2值0.808有所下降,但仍较次优模型提高5.4个百分点。组合模型性能随预测长度延长的衰减幅度显著优于单一架构,即便在24个月预测长度下,LSTM-Informer模型仍可以保持R2=0.782的优势。
至今为止,肺结核仍是威胁居民健康的主要公共卫生问题之一。作为一种由结核分枝杆菌引起、通过飞沫传播且易产生耐药性的慢性传染病,患者一旦发生就诊延迟,极易造成人群间传播和耐药结核的产生[21]。因此,及时掌握结核病的流行趋势对预警响应机制的构建具有重要现实意义。从2010—2022年,济宁市肺结核的发病率虽有逐年下降趋势,但仍然存在季节性波动和短期暴发的现象,整体防控形式不够乐观。本研究利用济宁市2010—2022年肺结核发病数据,创新性构建了LSTM-Informer模型,评估了该模型在不同预测时间长度下的性能表现,并与单一架构模型进行了比较。
研究结果显示,单一神经网络难以充分捕捉跨年度的全局时序依赖关系,预测时间越长模型性能衰减越显著。虽然LSTM模型可以通过门机制来解析局部波动情况,但由于其本身递归式计算结构的存在,使得模型难以对疾病中长期的发病情况进行有效预测。而依赖概率稀疏自注意力机制的Informer模型,在性能指标上均优于LSTM模型,这说明自注意力机制和直接多步预测的形式在长时间序列预测中能更好的控制误差波动。LSTM-Informer模型则在12~24个月的预测中均表现最优,尤其在R2指标上较单一模型有不小的提升。这种性能提升源于混合架构设计的协同效应:数据首先在LSTM层通过遗忘门滤除短期噪声并强化相邻时间步关联性,之后输入到Informer模块利用特有的注意力权重动态融合长周期特征,对数据进行分层次的特征提取。这种建模策略解决了单一模型在局部-全局特征提取不足的问题,有效提高了预测精度。山东省济宁市是著名的运河之城,位于京杭大运河南北分界的“黄金坐标”,其特殊的地理位置造就了该地区具有密集的人员流动和商业往来,这使当地肺结核传播呈现短期聚集与长期扩散交织的复杂特征。LSTM-Informer模型显然更能适应这种长短波动交错的复杂场景,从而提供更加准确的预测结果。
然而,本研究仍存在一些局限性:模型输入仅基于历史发病数据,未整合气候因素、人口流动强度等外部协变量。外部协变量的存在可能使模型面对极端事件与政策干预时预测失准,导致预测发病率与实际发病情况产生偏差,后续的研究可以考虑将外部因素纳入模型[22]。其次,在Informer模型与组合模型超参数的选择上,目前仍然依赖人工网格搜索来确定超参数,但这种方式选择的超参数不一定是模型的最优参数,从而没有达到模型的最佳状态,下一步可以考虑添加针对超参数选择的优化算法,以进一步提高模型的性能。综上,LSTM-Informer模型通过局部特征提取与全局依赖的思路进行建模,显著提高了模型的预测精度,为当地肺结核预测提供了新的方法论工具,这种思路和技术框架可以扩展至其他具有季节性和长期趋势特征的传染病,从而推动传染病防控体系的建设,减轻传染病对公众健康的负担。
  • 健康山东建设揭榜攻关面上项目(2024-2-29)
参考文献 引证文献
排序方式:
[1]
Dornelas moreira J, Rodrigues Silva H, de Paulo Coelho Peixoto de Toledo V, et al. Microparticles in the pathogenesis of TB: Novel perspectives for diagnostic and therapy management of Mycobacterium tuberculosis infection [J]. Microbial Pathogenesis, 2020, 144: 104176.
[2]
康万里,李恬静,王赛赛, 等. 全国活动性肺结核报告发病率变动趋势及预测研究 [J]. 中国防痨杂志, 2022, 44 (7): 681-684.
Kang WL, Li TJ, Wang SS, et al. Study on the trend and prediction of reported incidence of National active pulmonary tuberculosis in China [J]. Chinese Journal of Antituberculosis, 2022, 44 (7): 681-684. (In Chinese)
[3]
Koeken VACM, Verrall AJ, Ardiansyah E, et al. IL-32 and its splice variants are associated with protection against Mycobacterium tuberculosis infection and skewing of Th1/Th17 cytokines [J]. Journal of Leukocyte Biology, 2020, 107 (1): 113-118.
[4]
Fan L, Li DF, Zhang SJ, et al. Parallel tests using culture, xpert MTB/RIF, and SAT-TB in sputum plus bronchial alveolar lavage fluid significantly increase diagnostic performance of Smear-Negative pulmonary tuberculosis [J]. Frontiers in Microbiology, 2018, 9: 1107.
[5]
崔灵绸,石海萍. 某高校5起肺结核聚集性疫情特征分析 [J]. 中国防痨杂志, 2024, 46 (11): 1388-1394.
Cui LC, Shi HP. Analysis of characteristics of 5 pulmonary tuberculosis cluster epidemics in a university [J]. Chinese Journal of Antituberculosis, 2024, 46 (11): 1388-1394. (In Chinese)
[6]
Vernikou S, Lyras A, Kanavos A. Multiclass sentiment analysis on COVID-19-related tweets using deep learning models [J]. Neural Computing & Applications, 2022, 34 (22): 19615-19627.
[7]
高建树,郝世宇,党一诺, 等. 基于长短期记忆网络- Transformer模型参数优化的锂离子电池剩余使用寿命预测 [J/OL]. 中国药师:1-7 [2025-09-15]. http://kns.cnki.net/kcms/detail/42.1626.R.20200508.0915.002.html.
Gao JS, Hao SY, Dang YN, et al. Prediction of remaining service life of lithium-ion batteries based on Optimization of long-term and short-term memory network-Transformer model parameters [J/OL]. Automot Eng: 1-7 [2025-09-15]. http://kns.cnki.net/kcms/detail/42.1626.R.20200508.0915.002.html.
[8]
余琼芳,杨鹏飞,唐高峰. 基于LSTM-Informer模型的液压支架压力时空多步长预测 [J]. 工矿自动化, 2024, 50 (6): 30-35.
Yu QF, Yang PF, Tang GF. Spatiotemporal multi-step prediction of hydraulic support pressure based on LSTM-Informer model [J]. Industry and Mine Automation, 2024, 50 (6): 30-35. (In Chinese)
[9]
杨玥,左卫兵. 基于GAT-Informer模型的河南省空气污染物浓度预测 [J]. 电脑知识与技术, 2025, 21 (7): 6-10.
Yang Y, Zuo WB. Prediction of air pollutant concentration in Henan Province Based on gat informer model [J]. Computer Knowledge and Technology, 2025, 21 (7): 6-10. (In Chinese)
[10]
Li L, Jiang YW, Huang BQ. Long-term prediction for temporal propagation of seasonal influenza using Transformer-based model [J]. Journal of Biomedical Informatics, 2021, 122: 103894.
[11]
Er S, Yang SH, Zhao T. County augmented transformer for COVID-19 state hospitalizations prediction [J]. Scientific Reports, 2023, 13 (1): 9955.
[12]
Zhou H, Zhang S, Peng J, et al. Informer: beyond efficient transformer for long sequence Time-Series forecasting [J]. arXiv, 2012, 35 (12): 1-8.
[13]
Anonym . User2Vec: A novel representation for the information of the social networks for stock market predict [2025-09-15]. https://www.citexs.com/allSearchDetail?wid=4382940705.
[14]
Khan DM, Ali M, Iqbal N, et al. Short-Term prediction of COVID-19 using novel hybrid ensemble empirical mode decomposition and error trend seasonal model [J]. Front Public Health, 2022, 10: 922795.
[15]
Guo JQ, Wan BX, Zheng SY, et al. A teenager physical fitness evaluation model based on 1D-CNN with LSTM and wearable running PPG recordings [J]. Biosensors-BASEL, 2022, 12 (4): 202.
[16]
王淑平,杜敏,罗建伟, 等. GM(1,1)模型与LSTM神经网络在肺结核发病数预测中的应用 [J]. 公共卫生与预防医学, 2019, 30 (5): 11-14.
Wang SP, Du M, Luo JW, et al. Application of GM(1,1)model and LSTM neural network in predicting the incidence of pulmonary tuberculosis [J]. Journal of Public Health and Preventive Medicine, 2019, 30 (5): 11-14. (In Chinese)
[17]
Wang L, Zhang XD, Tang JW, et al. Machine learning analysis of SERS fingerprinting for the rapid determination of Mycobacterium tuberculosis infection and drug resistance [J]. Computational and Structural Biotechnology Journal, 2022, 20: 5364-5377.
[18]
陈迁任,全航,胡鹏. 基于Informer算法的间开气井产气量预测方法 [J/OL]. 特种油气藏, 1-14 [2025-09-15]. https://link.cnki.net/urlid/21.1357.TE.20250114.1829.014.
Chen QR, Quan H, Hu P. Gas production prediction method of open gas wells based on informer algorithm [J/OL]. Spec Oil Gas Reserv, 1-14 [2025-09-15]. https://link.cnki.net/urlid/21.1357.TE.20250114.1829.014. (In Chinese)
[19]
曹建文,委兴宝,杨裔, 等. 基于时间序列的非周期预测模型 [J]. 大数据, 2025, 11 (1): 135-149.
Cao JW, Wei XB, Yang Y, et al. Model for non-periodic time series prediction [J]. Big Data Research, 2025, 11 (1): 135-149. (In Chinese)
[20]
Xie H, Chen ZJ, Deng JC, et al. Automatic segmentation of the gross target volume in radiotherapy for lung cancer using transresSEUnet 2.5D Network [J]. Journal of Translational Medicine, 2022, 20 (1): 524.
[21]
易海波,高兴红,罗果, 等. 结核分枝杆菌Rv3432c蛋白的原核表达与生物信息学分析 [J]. 四川大学学报(医学版), 2024, 55 (2): 330-336.
Yi HB, Gao XH, Luo G, et al. Prokaryotic expression and bioinformatics analysis of rv3432c protein of Mycobacterium tuberculosis [J]. J Sichuan Univ(Med Sci), 2024, 55 (2): 330-336. (In Chinese)
[22]
李忠奇. 气象因素及空气污染物与肺结核发病风险的关联研究 [D]. 南京:南京医科大学, 2023.
Li ZQ. Association study of meteorological factors and air pollutants with the risk of pulmonary tuberculosis [D]. Nanjing: Nanjing Medical University, 2023. (In Chinese)
2025年第52卷第21期
PDF下载
30
15
引用本文
BibTeX
文章信息
doi: 10.20043/j.cnki.MPM.202505216
  • 接收时间:2025-05-13
  • 首发时间:2026-10-29
  • 出版时间:2025-11-10
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-05-13
基金
健康山东建设揭榜攻关面上项目(2024-2-29)
作者信息
    1.华北理工大学公共卫生学院,河北 唐山 063210
    2.潍坊护理职业学院,山东 潍坊 261000
    3.济宁市疾病预防控制中心

通讯作者:

王文军,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/xdyfyx/CN/10.20043/j.cnki.MPM.202505216
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏