Article(id=1241522920799925130, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1241522919977841545, articleNumber=null, orderNo=null, doi=10.20043/j.cnki.MPM.202309307, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1694880000000, receivedDateStr=2023-09-17, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1773931730699, onlineDateStr=2026-03-19, pubDate=1710000000000, pubDateStr=2024-03-10, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1773931730699, onlineIssueDateStr=2026-03-19, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1773931730699, creator=13701087609, updateTime=1773931730699, updator=13701087609, issue=Issue{id=1241522919977841545, tenantId=1146029695717560320, journalId=1227665162245664772, year='2024', volume='51', issue='5', pageStart='769', pageEnd='960', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1773931730503, creator=13701087609, updateTime=1773931880386, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1241523548695622547, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1241522919977841545, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1241523548695622548, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1241522919977841545, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=781, endPage=787, ext={EN=ArticleExt(id=1241522922284708747, articleId=1241522920799925130, tenantId=1146029695717560320, journalId=1227665162245664772, language=EN, title=Identification of patients with senile depression by interpretable machine learning model-based on the US National Health and Nutrition Examination Survey, columnId=1240413921954295836, journalTitle=Modern Preventive Medicine, columnName=Epidemiology and Statistical Methods, runingTitle=null, highlight=null, articleAbstract=
Objective

Based on the US National Health and Nutrition Survey from 2005 to 2021, an interpretable machine learning method was used to identify patients with depression in people over 65 years old.

Methods

The data of 2005 Mel 2018 and 2019-2020 were used as training set and test set, respectively, and three machine learning models of Lasso Logistic, random forest, and XG Boost were fitted. The best model of area under the curve (AUC) on the test set was selected and explained by interpretable machine learning model SHAP.

Results

The AUC value of XG Boost model was the highest, which was 0.933 (0.912-0.954). Sleep problems, health problems, and eosinophil count were the top three important variables affecting senile depression. The absolute values of SHAP were 1.16, 0.83, and 0.55, respectively, which showed the main influencing factors of each individual.

Conclusion

Machine learning is superior to logistic regression model in predicting depression in the elderly. Interpretable machine learning can explain the model from the global and individual levels to make predictions, open the black box of machine learning models, and can be used as a supplement to machine learning models in practical application.

, correspAuthors=null, 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, authorCompany=null, fund=null, authors=null, authorsList=Peng-cheng MIAO, Bei-er LU, Rong-ji MA, Yong-kang QIAN, Chen-hua HU, Hua-ling CHEN, Ru FAN, Bi-yun XU, Bing-wei CHEN), CN=ArticleExt(id=1241522923719160753, articleId=1241522920799925130, tenantId=1146029695717560320, journalId=1227665162245664772, language=CN, title=解释性机器学习模型对老年抑郁症患者的识别——基于美国国家健康和营养检测调查数据库, 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

基于2005—2021年美国国家健康和营养检测调查数据库,使用可解释性机器学习方法识别65岁以上老年人中的抑郁症患者。

方法

以2005—2018年及2019—2020年的数据分别作为训练集及测试集,拟合lasso logistic、随机森林、XGBoost三种机器学习模型,以测试集上的AUC最大选择较优的模型,使用解释性机器学习模型SHAP进行解释。

结果

XGBoost模型AUC值最大,为0.933(0.912~0.954),是否存在睡眠问题、是否存在健康问题和嗜酸性粒细胞计数为影响老年人抑郁症的前三重要的变量,变量SHAP值的绝对值分别为1.16、0.83、0.55;SHAP力图呈现了每个个体的主要的影响因素,根据SHAP值对每个个体进行解释。

结论

机器学习在预测老年人抑郁症方面性能优于logistic回归模型,解释性机器学习可以从全局和个体层面解释模型做出预测,打开机器学习模型的黑箱,在实际应用中可以作为机器学习模型的补充。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
陈炳为,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=3vF6bqHCX9Y1XWUvRkYAVA==, magXml=XD0KZZsxyIsKair22uA73g==, pdfUrl=null, pdf=zViZQnoXsy3YTdQFFBvowQ==, pdfFileSize=1723160, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=8Et+YPhuQUvw90WGB5i8uQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=kVeZASJnWhEeHPI/rokTuA==, mapNumber=null, authorCompany=null, fund=null, authors=

缪鹏程(1998—),男,硕士在读,研究方向:流行病与卫生统计专业

, authorsList=缪鹏程, 陆贝尔, 马溶基, 钱永康, 胡陈华, 陈华玲, 凡如, 许碧云, 陈炳为)}, authors=[Author(id=1241678292953124982, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, 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=1241678293796180110, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678292953124982, language=EN, stringName=Peng-cheng MIAO, firstName=Peng-cheng, middleName=null, lastName=MIAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241678294626652319, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678292953124982, language=CN, stringName=缪鹏程, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东南大学公共卫生学院,江苏 南京 210009, bio={"content":"

缪鹏程(1998—),男,硕士在读,研究方向:流行病与卫生统计专业

"}, bioImg=null, bioContent=

缪鹏程(1998—),男,硕士在读,研究方向:流行病与卫生统计专业

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241678290331684948, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, xref=1., ext=[AuthorCompanyExt(id=1241678290340073559, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China), AuthorCompanyExt(id=1241678290348462170, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东南大学公共卫生学院,江苏 南京 210009)])]), Author(id=1241678295117385897, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, 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=1241678297264869558, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678295117385897, language=EN, stringName=Bei-er LU, firstName=Bei-er, middleName=null, lastName=LU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241678297877237955, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678295117385897, language=CN, stringName=陆贝尔, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东南大学公共卫生学院,江苏 南京 210009, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241678290331684948, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, xref=1., ext=[AuthorCompanyExt(id=1241678290340073559, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China), AuthorCompanyExt(id=1241678290348462170, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东南大学公共卫生学院,江苏 南京 210009)])]), Author(id=1241678298183422158, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, 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=1241678298774819038, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678298183422158, language=EN, stringName=Rong-ji MA, firstName=Rong-ji, middleName=null, lastName=MA, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241678299303301352, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678298183422158, language=CN, stringName=马溶基, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东南大学公共卫生学院,江苏 南京 210009, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241678290331684948, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, xref=1., ext=[AuthorCompanyExt(id=1241678290340073559, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China), AuthorCompanyExt(id=1241678290348462170, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东南大学公共卫生学院,江苏 南京 210009)])]), Author(id=1241678302914597106, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, 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=1241678303380164863, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678302914597106, language=EN, stringName=Yong-kang QIAN, firstName=Yong-kang, middleName=null, lastName=QIAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241678303703126277, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678302914597106, language=CN, stringName=钱永康, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东南大学公共卫生学院,江苏 南京 210009, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241678290331684948, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, xref=1., ext=[AuthorCompanyExt(id=1241678290340073559, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China), AuthorCompanyExt(id=1241678290348462170, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东南大学公共卫生学院,江苏 南京 210009)])]), Author(id=1241678306005799184, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, 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=1241678306651722012, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678306005799184, language=EN, stringName=Chen-hua HU, firstName=Chen-hua, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241678306777551145, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678306005799184, language=CN, stringName=胡陈华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东南大学公共卫生学院,江苏 南京 210009, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241678290331684948, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, xref=1., ext=[AuthorCompanyExt(id=1241678290340073559, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China), AuthorCompanyExt(id=1241678290348462170, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东南大学公共卫生学院,江苏 南京 210009)])]), Author(id=1241678306903380271, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, 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=1241678307243118906, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678306903380271, language=EN, stringName=Hua-ling CHEN, firstName=Hua-ling, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241678307788378439, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678306903380271, language=CN, stringName=陈华玲, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东南大学公共卫生学院,江苏 南京 210009, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241678290331684948, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, xref=1., ext=[AuthorCompanyExt(id=1241678290340073559, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China), AuthorCompanyExt(id=1241678290348462170, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东南大学公共卫生学院,江苏 南京 210009)])]), Author(id=1241678308581101909, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, 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=1241678310959272283, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678308581101909, language=EN, stringName=Ru FAN, firstName=Ru, middleName=null, lastName=FAN, 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=1241678311479365990, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678308581101909, language=CN, stringName=凡如, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2南京大学医学院附属鼓楼医院统计中心, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241678292357533793, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, xref=2, ext=[AuthorCompanyExt(id=1241678292365922401, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678292357533793, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2南京大学医学院附属鼓楼医院统计中心)])]), Author(id=1241678311785550192, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, orderNo=7, 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=1241678315480732033, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678311785550192, language=EN, stringName=Bi-yun XU, firstName=Bi-yun, middleName=null, lastName=XU, 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=1241678316579639691, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678311785550192, language=CN, stringName=许碧云, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2南京大学医学院附属鼓楼医院统计中心, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241678292357533793, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, xref=2, ext=[AuthorCompanyExt(id=1241678292365922401, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678292357533793, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2南京大学医学院附属鼓楼医院统计中心)])]), Author(id=1241678319448543641, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, orderNo=8, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=drchenbw@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241678319914111399, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678319448543641, language=EN, stringName=Bing-wei CHEN, firstName=Bing-wei, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241678320320958894, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, authorId=1241678319448543641, language=CN, stringName=陈炳为, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东南大学公共卫生学院,江苏 南京 210009, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241678290331684948, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, xref=1., ext=[AuthorCompanyExt(id=1241678290340073559, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China), AuthorCompanyExt(id=1241678290348462170, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东南大学公共卫生学院,江苏 南京 210009)])])], keywords=[Keyword(id=1241678321549889985, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=EN, orderNo=1, keyword=Elderly), Keyword(id=1241678321973514691, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=EN, orderNo=2, keyword=Depression), Keyword(id=1241678322397139403, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=EN, orderNo=3, keyword=Interpretable machine learning), Keyword(id=1241678323038867928, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=EN, orderNo=4, keyword=XG Boost), Keyword(id=1241678323324080605, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=EN, orderNo=5, keyword=SHAP), Keyword(id=1241678323831591397, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=CN, orderNo=1, keyword=老年人), Keyword(id=1241678324422988271, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=CN, orderNo=2, keyword=抑郁症), Keyword(id=1241678324741755384, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=CN, orderNo=3, keyword=解释性机器学习), Keyword(id=1241678324859195904, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=CN, orderNo=4, keyword=XGBoost), Keyword(id=1241678325328957961, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=CN, orderNo=5, keyword=SHAP)], refs=[Reference(id=1241678335286235794, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2017, volume=317, issue=20, pageStart=2114, pageEnd=2122, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Kok RM, Reynolds CF3, journalName=JAMA: the Journal of the American Medical Association, refType=null, unstructuredReference=Kok RM, Reynolds CF3. Management of depression in older adults:a review[J]. JAMA: the Journal of the American Medical Association, 2017, 317(20): 2114-2122., articleTitle=Management of depression in older adults:a review, refAbstract=null), Reference(id=1241678335479173788, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2023, volume=50, issue=11, pageStart=2062, pageEnd=2066, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=程小伟, 黄俭, 朱向阳, journalName=现代预防医学, refType=null, unstructuredReference=程小伟,黄俭,朱向阳,等.抑郁症患者心理韧性在述情障碍与情绪自我效能感间的中介效应[J].现代预防医学202350(11):2062-2066., articleTitle=抑郁症患者心理韧性在述情障碍与情绪自我效能感间的中介效应, refAbstract=null), Reference(id=1241678335646945952, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2023, volume=50, issue=11, pageStart=2062, pageEnd=2066, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Cheng XW, Huang J, Zhu XY, journalName=Modern Preventive Medicine, refType=null, unstructuredReference=Cheng XW, Huang J, Zhu XY, et al. Mediating effect of psychological resilience between alexithymia and emotional self-efficacy in patients with depression[J]. Modern Preventive Medicine, 2023, 50(11): 2062-2066., articleTitle=Mediating effect of psychological resilience between alexithymia and emotional self-efficacy in patients with depression, refAbstract=null), Reference(id=1241678336041210538, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=1, pageStart=73, pageEnd=83, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=谢静静, 李丽霞, 柳学华, journalName=中国心理卫生杂志, refType=null, unstructuredReference=谢静静,李丽霞,柳学华,等.正念减压疗法和正念认知疗法安全性的meta分析[J].中国心理卫生杂志2024,(1):73-83., articleTitle=正念减压疗法和正念认知疗法安全性的meta分析, refAbstract=null), Reference(id=1241678336322228910, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=1, pageStart=73, pageEnd=83, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Xie JJ, Li LX, Liu XH, journalName=Chinese Mental Health Journal, refType=null, unstructuredReference=Xie JJ, Li LX, Liu XH, et al. A meta-analysis of safety of mindfulness-based stress reduction therapy and mindfulness-based cognitive therapy[J].Chinese Mental Health Journal, 2024, (1): 73-83., articleTitle=A meta-analysis of safety of mindfulness-based stress reduction therapy and mindfulness-based cognitive therapy, refAbstract=null), Reference(id=1241678336703910583, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2001, volume=9, issue=2, pageStart=102, pageEnd=112, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Bruce ML, journalName=The American Journal of Geriatric Psychiatry:Official Journal of the American Association for Geriatric Psychiatry, refType=null, unstructuredReference=Bruce ML. Depression and disability in late Life: directions for future research[J]. The American Journal of Geriatric Psychiatry:Official Journal of the American Association for Geriatric Psychiatry,2001, 9(2): 102-112., articleTitle=Depression and disability in late Life: directions for future research, refAbstract=null), Reference(id=1241678337316278977, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2021, volume=127, issue=null, pageStart=193, pageEnd=211, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Beghi M, Butera E, Cerri CG, journalName=Neuroscience and Biobehavioral Reviews, refType=null, unstructuredReference=Beghi M, Butera E, Cerri CG, et al. Suicidal behaviour in older age:A systematic review of risk factors associated to suicide attempts and completed suicides[J]. Neuroscience and Biobehavioral Reviews,2021, 127: 193-211., articleTitle=Suicidal behaviour in older age:A systematic review of risk factors associated to suicide attempts and completed suicides, refAbstract=null), Reference(id=1241678337597297349, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2020, volume=49, issue=4, pageStart=462, pageEnd=467, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=蔡利强, 游亚凤, 魏丽丽, journalName=浙江大学学报:医学版, refType=null, unstructuredReference=蔡利强,游亚凤,魏丽丽,等.老年抑郁症患者自杀观念与多导睡眠图参数的相关性分析[J].浙江大学学报:医学版202049(4):462-467., articleTitle=老年抑郁症患者自杀观念与多导睡眠图参数的相关性分析, refAbstract=null), Reference(id=1241678339434402512, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2020, volume=49, issue=4, pageStart=462, pageEnd=467, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=Cai LQ, You YF, Wei LL, journalName=Journal of Zhejiang University. Medical Sciences, refType=null, unstructuredReference=Cai LQ, You YF, Wei LL, et al. Correlation between suicidal ideation and polysomnography parameters in late-life depression patients[J]. Journal of Zhejiang University. Medical Sciences, 2020, 49(4): 462-467., articleTitle=Correlation between suicidal ideation and polysomnography parameters in late-life depression patients, refAbstract=null), Reference(id=1241678340185182933, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2022, volume=63, issue=11, pageStart=1064, pageEnd=1072, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=王威, 第五永长, 杨谦, journalName=中医杂志, refType=null, unstructuredReference=王威,第五永长,杨谦,等.轻度认知障碍与老年期痴呆患者中医证候要素及影响因素的横断面调查[J].中医杂志202263(11):1064-1072., articleTitle=轻度认知障碍与老年期痴呆患者中医证候要素及影响因素的横断面调查, refAbstract=null), Reference(id=1241678340428452572, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2022, volume=63, issue=11, pageStart=1064, pageEnd=1072, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=Wang W, Di Wu YC, Yang Q, journalName=Journal of Traditional Chinese Medicine, refType=null, unstructuredReference=Wang W, Di Wu YC, Yang Q, et al. Traditional Chinese medicine syndrome elements and influencing factors of patients with mild cognitive impairment and senile dementia: a cross-sectional study[J]. Journal of Traditional Chinese Medicine, 2022, 63(11): 1064-1072., articleTitle=Traditional Chinese medicine syndrome elements and influencing factors of patients with mild cognitive impairment and senile dementia: a cross-sectional study, refAbstract=null), Reference(id=1241678340772385501, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2023, volume=50, issue=8, pageStart=1461, pageEnd=1467, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=石萌, 邹宇量, journalName=现代预防医学, refType=null, unstructuredReference=石萌, 邹宇量.中国中老年人午睡时长与抑郁症状的关联——基于CHARLS数据分析[J].现代预防医学202350(8):1461-1467., articleTitle=中国中老年人午睡时长与抑郁症状的关联——基于CHARLS数据分析, refAbstract=null), Reference(id=1241678341242147555, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2023, volume=50, issue=8, pageStart=1461, pageEnd=1467, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=Shi M, Zou YL, journalName=Modern Preventive Medicine, refType=null, unstructuredReference=Shi M, Zou YL. Relationship between nap duration and depressive symptoms among middle-aged and elderly Chinese——based on CHARLS data analysis[J]. Modern Preventive Medicine, 2023, 50(8): 1461-1467., articleTitle=Relationship between nap duration and depressive symptoms among middle-aged and elderly Chinese——based on CHARLS data analysis, refAbstract=null), Reference(id=1241678341623829223, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2022, volume=312, issue=null, pageStart=275, pageEnd=291, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=Sun YH, Liu QJ, Lee NY, journalName=Journal of Affective Disorders, refType=null, unstructuredReference=Sun YH, Liu QJ, Lee NY, et al. A novel machine learning approach to shorten depression risk assessment for convenient uses[J]. Journal of Affective Disorders, 2022, 312: 275-291., articleTitle=A novel machine learning approach to shorten depression risk assessment for convenient uses, refAbstract=null), Reference(id=1241678342064231155, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2022, volume=11, issue=7, pageStart=1111, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=Aleem S, Huda NU, Amin R, journalName=Electronics, refType=null, unstructuredReference=Aleem S, Huda NU, Amin R, et al. Machine learning algorithms for depression: diagnosis, insights, and research directions[J].Electronics, 2022, 11(7): 1111., articleTitle=Machine learning algorithms for depression: diagnosis, insights, and research directions, refAbstract=null), Reference(id=1241678344119440121, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2017, volume=4, issue=null, pageStart=4768, pageEnd=4777, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=Lundberg S, Lee SI, journalName=A unified approach to interpreting model predictions, refType=null, unstructuredReference=Lundberg S, Lee SI. A unified approach to interpreting model predictions[M]. Neural Information Processing Systems, 2017, 4:4768-4777., articleTitle=null, refAbstract=null), Reference(id=1241678344870220542, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=刘悦, journalName=null, refType=null, unstructuredReference=刘悦.基于机器学习的老年人抑郁症状的预测[D].济南:山东大学,2023., articleTitle=基于机器学习的老年人抑郁症状的预测, refAbstract=null), Reference(id=1241678345256096514, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=Liu Y, journalName=null, refType=null, unstructuredReference=Liu Y. Prediction of depression in the elderly based on machine learning[D]. Jinan: Shandong University, 2023., articleTitle=Prediction of depression in the elderly based on machine learning, refAbstract=null), Reference(id=1241678345658749703, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=周雯惠, journalName=null, refType=null, unstructuredReference=周雯惠.中国老年人抑郁症状影响因素研究[D].南京:南京邮电大学,2022., articleTitle=中国老年人抑郁症状影响因素研究, refAbstract=null), Reference(id=1241678345897825034, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=Zhou WH, journalName=null, refType=null, unstructuredReference=Zhou WH. Study on influencing factors of depressive symptoms in Chinese Elderly-Based on 2018 CLHLS data[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2022., articleTitle=Study on influencing factors of depressive symptoms in Chinese Elderly-Based on 2018 CLHLS data, refAbstract=null), Reference(id=1241678346438890254, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2024, volume=348, issue=null, pageStart=191, pageEnd=199, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=Zeng Z, Li Q, Caine ED, journalName=Journal of Affective Disorders, refType=null, unstructuredReference=Zeng Z, Li Q, Caine ED, et al. Prevalence of and optimal screening tool for postpartum depression in a community-based population in China[J]. Journal of Affective Disorders, 2024, 348: 191-199., articleTitle=Prevalence of and optimal screening tool for postpartum depression in a community-based population in China, refAbstract=null), Reference(id=1241678348464739092, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2023, volume=34, issue=9, pageStart=6390, pageEnd=6404, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=Dablain D, Krawczyk B, Chawla NV, journalName=IEEE Transactions on Neural Networks and Learning Systems, refType=null, unstructuredReference=Dablain D, Krawczyk B, Chawla NV. DeepSMOTE: fusing deep learning and SMOTE for imbalanced data[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(9): 6390-6404., articleTitle=DeepSMOTE: fusing deep learning and SMOTE for imbalanced data, refAbstract=null), Reference(id=1241678348779311896, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2011, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=Bergstra J, Bardenet R, Bengio Y, journalName=null, refType=null, unstructuredReference=Bergstra J, Bardenet R, Bengio Y, et al. Algorithms for hyper-parameter optimization[C]//Proceedings of the 24th International Conference on Neural Information Processing Systems. Granada,Spain, Red Hook, NY, USA: Curran Associates Inc., 2011., articleTitle=Algorithms for hyper-parameter optimization, refAbstract=null), Reference(id=1241678349194547995, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2022, volume=18, issue=null, pageStart=329, pageEnd=357, url=null, language=null, rfNumber=[17], rfOrder=23, authorNames=Monroe SM, Harkness KL, journalName=Annual Review of Clinical Psychology, refType=null, unstructuredReference=Monroe SM, Harkness KL. Major depression and its recurrences:Life course matters[J]. Annual Review of Clinical Psychology, 2022,18: 329-357., articleTitle=Major depression and its recurrences:Life course matters, refAbstract=null), Reference(id=1241678349865636638, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2022, volume=32, issue=null, pageStart=8019, pageEnd=8026, url=null, language=null, rfNumber=[18], rfOrder=24, authorNames=Jiang YW, Xu XJ, Wang R, journalName=European Radiology, refType=null, unstructuredReference=Jiang YW, Xu XJ, Wang R, et al. Radiomics analysis based on lumbar spine CT to detect osteoporosis[J]. European Radiology, 2022,32: 8019-8026., articleTitle=Radiomics analysis based on lumbar spine CT to detect osteoporosis, refAbstract=null), Reference(id=1241678350335398689, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2016, volume=21, issue=10, pageStart=1366, pageEnd=1371, url=null, language=null, rfNumber=[19], rfOrder=25, authorNames=Kessler RC, Van Loo HM, Wardenaar KJ, journalName=Molecular Psychiatry, refType=null, unstructuredReference=Kessler RC, Van Loo HM, Wardenaar KJ, et al. Testing a machine- learning algorithm to predict the persistence and severity of major depressive disorder from baseline self-reports[J]. Molecular Psychiatry, 2016, 21(10): 1366-1371., articleTitle=Testing a machine- learning algorithm to predict the persistence and severity of major depressive disorder from baseline self-reports, refAbstract=null), Reference(id=1241678350750634788, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2021, volume=306, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=26, authorNames=Zhang CY, Chen XF, Wang S, journalName=Psychiatry Research, refType=null, unstructuredReference=Zhang CY, Chen XF, Wang S, et al. Using CatBoost algorithm to identify middle-aged and elderly depression, National health and nutrition examination survey 2011-2018[J]. Psychiatry Research,2021, 306: 114261., articleTitle=Using CatBoost algorithm to identify middle-aged and elderly depression, National health and nutrition examination survey 2011-2018, refAbstract=null), Reference(id=1241678351086179110, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2023, volume=12, issue=9, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=27, authorNames=Du TC, Tran TQB, Deo N, journalName=Journal of the American Heart Association, refType=null, unstructuredReference=Du TC, Tran TQB, Deo N, et al. Survey and evaluation of hypertension machine learning research[J]. Journal of the American Heart Association, 2023, 12(9): e027896., articleTitle=Survey and evaluation of hypertension machine learning research, refAbstract=null), Reference(id=1241678352965227306, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, doi=null, pmid=null, pmcid=null, year=2021, volume=140, issue=null, pageStart=364, pageEnd=372, url=null, language=null, rfNumber=[22], rfOrder=28, authorNames=Lin ZQ, Lawrence WR, Huang YH, journalName=Journal of Psychiatric Research, refType=null, unstructuredReference=Lin ZQ, Lawrence WR, Huang YH, et al. Classifying depression using blood biomarkers: A large population study[J].Journal of Psychiatric Research, 2021, 140: 364-372., articleTitle=Classifying depression using blood biomarkers: A large population study, refAbstract=null)], funds=[Fund(id=1241678332975174279, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, awardId=ZKX22019, language=CN, fundingSource=南京市医学重点科技发展项目(ZKX22019), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1241678290331684948, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, xref=1., ext=[AuthorCompanyExt(id=1241678290340073559, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China), AuthorCompanyExt(id=1241678290348462170, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678290331684948, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东南大学公共卫生学院,江苏 南京 210009)]), AuthorCompany(id=1241678292357533793, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, xref=2, ext=[AuthorCompanyExt(id=1241678292365922401, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, companyId=1241678292357533793, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2南京大学医学院附属鼓楼医院统计中心)])], figs=[ArticleFig(id=1241678327006679577, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=EN, label=Figure 1, caption=ROC curve of three machine learning models, figureFileSmall=c/NtTx32k37wFA5Lo9qtkQ==, figureFileBig=b62mRiEz+qnXy/Oscvn04w==, tableContent=null), ArticleFig(id=1241678327652602399, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=CN, label=图1, caption=三种机器学习模型的ROC曲线, figureFileSmall=c/NtTx32k37wFA5Lo9qtkQ==, figureFileBig=b62mRiEz+qnXy/Oscvn04w==, tableContent=null), ArticleFig(id=1241678328306913839, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=EN, label=Figure 2, caption=

2A SHAP variable importance plots; 2B SHAP variable importance plots by age; 2C SHAP summary plot

, figureFileSmall=rEBuAEqyB49wa3i7ztNW5w==, figureFileBig=8ekD6LY5nC33G7qGa0Ktkg==, tableContent=null), ArticleFig(id=1241678328629875254, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=CN, label=图2, caption=SHAP变量重要性图

注:SLQ050表示是否存在睡眠问题;HSD010表示是否存在健康问题;LBDEONO表示嗜酸性粒细胞数;SLQ120表示近一个月内过度疲劳的次数;HSQ500表示近一个月内是否有过感冒;LBDBANO表示嗜碱性粒细胞数;LBXCOT表示血清可替宁浓度;LBDMONO表示单核细胞数;DMDEDUC2表示受教育程度;DR1TP184表示PFA 18:4(十八碳四烯酸);图A为SHAP变量重要性图;图B为按照年龄分组的SHAP重要性;图C为SHAP概要图。

, figureFileSmall=rEBuAEqyB49wa3i7ztNW5w==, figureFileBig=8ekD6LY5nC33G7qGa0Ktkg==, tableContent=null), ArticleFig(id=1241678329468736062, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=EN, label=Figure 3, caption=

3A SHAP dependence plot of count of basophils; 3B SHAP dependence plot of vitamin B6 taken

, figureFileSmall=M5jIeapZ/la2tHmGGbrZkg==, figureFileBig=rQrgQE67t1jAVzHBuprRqg==, tableContent=null), ArticleFig(id=1241678329921720906, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=CN, label=图3, caption=SHAP决定图

注:图A为嗜碱性粒细胞数变量的SHAP决定图;图B为摄入维生素B6的SHAP决定图。

, figureFileSmall=M5jIeapZ/la2tHmGGbrZkg==, figureFileBig=rQrgQE67t1jAVzHBuprRqg==, tableContent=null), ArticleFig(id=1241678330324374098, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=EN, label=Figure 4, caption=

4A: SHAP force plot of 128th individual; 4B: SHAP force plot of 777th individual

, figureFileSmall=ThPcT3Z1676uv60W5RrjFA==, figureFileBig=HqSpdf4Sfw7C8wg9wcX/uw==, tableContent=null), ArticleFig(id=1241678330781553237, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=CN, label=图4, caption=测试集上的SHAP力图

注:HSQ590表示除了献血外,是否进行过艾滋病毒检测;HSD010表示是否存在健康问题;HSQ500表示近一个月内是否有过感冒;SLQ050表示是否存在睡眠问题;DR2TP226表示PFA 22:6(二十二碳六烯酸,DHA)(标化值);HSQ510表示30天内是否患有胃病或肠道疾病,伴有呕吐或腹泻;DR2TCAFF表示膳食中摄入的咖啡因浓度(mg)(标化值);图A为第128个个体的力图;图B为第777个个体的SHAP力图。

, figureFileSmall=ThPcT3Z1676uv60W5RrjFA==, figureFileBig=HqSpdf4Sfw7C8wg9wcX/uw==, tableContent=null), ArticleFig(id=1241678331075154528, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=EN, label=Table 1, caption=

Basic characteristics in the train and test datasets [(),n(%)]

, figureFileSmall=null, figureFileBig=null, tableContent=
变量合计(n=8 598)测试集(n=1 790)训练集(n=6 808)
年龄(岁)73.26±5.4372.85±5.2973.37±5.47
受教育程度
初中以下1 215(14.13)162(9.05)1 053(15.47)
初中1 172(13.63)197(11.01)975(14.32)
高中2 141(24.90)456(25.47)1 685(24.75)
大学2 246(26.12)542(30.28)1 704(25.03)
大学毕业或以上1 811(21.06)430(24.02)1 381(20.28)
性别
男性4 352(50.62)924(51.62)3 428(50.35)
女性4 246(49.38)866(48.38)3 380(49.65)
种族
墨裔美国人850(9.89)117(6.54)733(10.77)
拉丁裔670(7.79)146(8.16)524(7.70)
非拉丁裔白人4 896(56.94)941(52.57)3 955(58.09)
非拉丁裔黑人1 625(18.90)417(23.30)1 208(17.74)
其他种族和混血557(6.48)169(9.44)388(5.70)
), ArticleFig(id=1241678331536527977, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=CN, label=表1, caption=

训练集和测试集中人口统计学特征[(),n(%)]

, figureFileSmall=null, figureFileBig=null, tableContent=
变量合计(n=8 598)测试集(n=1 790)训练集(n=6 808)
年龄(岁)73.26±5.4372.85±5.2973.37±5.47
受教育程度
初中以下1 215(14.13)162(9.05)1 053(15.47)
初中1 172(13.63)197(11.01)975(14.32)
高中2 141(24.90)456(25.47)1 685(24.75)
大学2 246(26.12)542(30.28)1 704(25.03)
大学毕业或以上1 811(21.06)430(24.02)1 381(20.28)
性别
男性4 352(50.62)924(51.62)3 428(50.35)
女性4 246(49.38)866(48.38)3 380(49.65)
种族
墨裔美国人850(9.89)117(6.54)733(10.77)
拉丁裔670(7.79)146(8.16)524(7.70)
非拉丁裔白人4 896(56.94)941(52.57)3 955(58.09)
非拉丁裔黑人1 625(18.90)417(23.30)1 208(17.74)
其他种族和混血557(6.48)169(9.44)388(5.70)
), ArticleFig(id=1241678331909821043, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=EN, label=Table 2, caption=

Performance of three machine learning models in test dataset

, figureFileSmall=null, figureFileBig=null, tableContent=
模型AUC(95%CI准确率(%)灵敏度(%)特异度(%)
Lasso logistic0.772(0.731~0.813)68.4474.0567.99
随机森林0.910(0.886~0.935)78.7292.3777.64
XGBoost0.933(0.912~0.954)84.9285.5084.87
), ArticleFig(id=1241678332203422326, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241522920799925130, language=CN, label=表2, caption=

三种机器学习模型在测试集上的表现

, figureFileSmall=null, figureFileBig=null, tableContent=
模型AUC(95%CI准确率(%)灵敏度(%)特异度(%)
Lasso logistic0.772(0.731~0.813)68.4474.0567.99
随机森林0.910(0.886~0.935)78.7292.3777.64
XGBoost0.933(0.912~0.954)84.9285.5084.87
)], 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=1770628902248, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=M, firstLetterEn=M, subjectCode=Life Sciences, subjectName=null, subjectCodeEn=Life Sciences, subjectNameEn=null, picCn=IeiuPXEZi6AA+k0VfvoiOQ==, picEn=/9iTl8/ndms4tBz1fL28Pg==, jcr=null, cjcr=null, exts=[JournalExt(id=1227669854342280188, 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=1770628902278, updatedTime=1770628902278, createdBy=13701087609, updatedBy=13701087609, 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=1227669854396806141, 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=1770628902291, updatedTime=1770628902291, createdBy=13701087609, updatedBy=13701087609, 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=M, 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), detailUrlCn=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/10.20043/j.cnki.MPM.202309307, detailUrlEn=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/10.20043/j.cnki.MPM.202309307, pdfUrlCn=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/PDF/10.20043/j.cnki.MPM.202309307, pdfUrlEn=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/PDF/10.20043/j.cnki.MPM.202309307, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
解释性机器学习模型对老年抑郁症患者的识别——基于美国国家健康和营养检测调查数据库
收藏切换
PDF下载
缪鹏程 1 , 陆贝尔 1 , 马溶基 1 , 钱永康 1 , 胡陈华 1 , 陈华玲 1 , 凡如 2 , 许碧云 2 , 陈炳为 1
现代预防医学 | 流行病与统计方法 2024,51(5): 781-787
收起
收藏切换
现代预防医学 | 流行病与统计方法 2024, 51(5): 781-787
解释性机器学习模型对老年抑郁症患者的识别——基于美国国家健康和营养检测调查数据库
全屏
缪鹏程1, 陆贝尔1, 马溶基1, 钱永康1, 胡陈华1, 陈华玲1, 凡如2, 许碧云2, 陈炳为1
作者信息
  • 1.东南大学公共卫生学院,江苏 南京 210009
  • 2南京大学医学院附属鼓楼医院统计中心
  • 缪鹏程(1998—),男,硕士在读,研究方向:流行病与卫生统计专业

通讯作者:

陈炳为,E-mail:
Identification of patients with senile depression by interpretable machine learning model-based on the US National Health and Nutrition Examination Survey
Peng-cheng MIAO1, Bei-er LU1, Rong-ji MA1, Yong-kang QIAN1, Chen-hua HU1, Hua-ling CHEN1, Ru FAN2, Bi-yun XU2, Bing-wei CHEN1
Affiliations
  • School of Public Health, Southeast University, Nanjing, Jiangsu 210009, China
出版时间: 2024-03-10 doi: 10.20043/j.cnki.MPM.202309307
文章导航
收藏切换
目的

基于2005—2021年美国国家健康和营养检测调查数据库,使用可解释性机器学习方法识别65岁以上老年人中的抑郁症患者。

方法

以2005—2018年及2019—2020年的数据分别作为训练集及测试集,拟合lasso logistic、随机森林、XGBoost三种机器学习模型,以测试集上的AUC最大选择较优的模型,使用解释性机器学习模型SHAP进行解释。

结果

XGBoost模型AUC值最大,为0.933(0.912~0.954),是否存在睡眠问题、是否存在健康问题和嗜酸性粒细胞计数为影响老年人抑郁症的前三重要的变量,变量SHAP值的绝对值分别为1.16、0.83、0.55;SHAP力图呈现了每个个体的主要的影响因素,根据SHAP值对每个个体进行解释。

结论

机器学习在预测老年人抑郁症方面性能优于logistic回归模型,解释性机器学习可以从全局和个体层面解释模型做出预测,打开机器学习模型的黑箱,在实际应用中可以作为机器学习模型的补充。

老年人  /  抑郁症  /  解释性机器学习  /  XGBoost  /  SHAP
Objective

Based on the US National Health and Nutrition Survey from 2005 to 2021, an interpretable machine learning method was used to identify patients with depression in people over 65 years old.

Methods

The data of 2005 Mel 2018 and 2019-2020 were used as training set and test set, respectively, and three machine learning models of Lasso Logistic, random forest, and XG Boost were fitted. The best model of area under the curve (AUC) on the test set was selected and explained by interpretable machine learning model SHAP.

Results

The AUC value of XG Boost model was the highest, which was 0.933 (0.912-0.954). Sleep problems, health problems, and eosinophil count were the top three important variables affecting senile depression. The absolute values of SHAP were 1.16, 0.83, and 0.55, respectively, which showed the main influencing factors of each individual.

Conclusion

Machine learning is superior to logistic regression model in predicting depression in the elderly. Interpretable machine learning can explain the model from the global and individual levels to make predictions, open the black box of machine learning models, and can be used as a supplement to machine learning models in practical application.

Elderly  /  Depression  /  Interpretable machine learning  /  XG Boost  /  SHAP
缪鹏程, 陆贝尔, 马溶基, 钱永康, 胡陈华, 陈华玲, 凡如, 许碧云, 陈炳为. 解释性机器学习模型对老年抑郁症患者的识别——基于美国国家健康和营养检测调查数据库. 现代预防医学, 2024 , 51 (5) : 781 -787 . DOI: 10.20043/j.cnki.MPM.202309307
Peng-cheng MIAO, Bei-er LU, Rong-ji MA, Yong-kang QIAN, Chen-hua HU, Hua-ling CHEN, Ru FAN, Bi-yun XU, Bing-wei CHEN. Identification of patients with senile depression by interpretable machine learning model-based on the US National Health and Nutrition Examination Survey[J]. Modern Preventive Medicine, 2024 , 51 (5) : 781 -787 . DOI: 10.20043/j.cnki.MPM.202309307
老年人抑郁症是一种常见的精神疾病,会影响老年人健康相关的生活质量。2017年的一项研究显示,10%~15%的老年人有临床意义的抑郁症状,55岁及以上人群中重度抑郁症发生率在2%左右,且患病率随着年龄的增长而上[1]。抑郁症是晚年体重减轻的主要原因[2]。抑郁症通常与心血管疾病等慢性疾病有关,并且可能使这些疾病的过程复杂化[3]。抑郁症也与功能障碍有关,并随着时间的推移影响残疾状态[4-5]。71%的自杀尝试者报告以前至少有一次重度抑郁症发作[5]。在65岁以上老年自杀人群中,约83%因抑郁症引起[6]。药物治疗和心理治疗的联合治疗对于老年抑郁症的治疗是有效的,早期发现抑郁症并对老年抑郁患者的治疗非常重要[7]。因此,了解老年人抑郁的危险因素可能有助于识别高危人群,以延缓疾病进程并建立个性化干预措施[8]
机器学习能够较好地解决变量间的非线性复杂关系,其预测性能及泛化性能往往高于传统的统计方法,被广泛应用于医学各个领域。在精神方面,Yuan等人[9]使用多种机器学习算法识别抑郁症患者,在这项31 715例的研究中,集成学习算法的受试者工作特征曲线下面积(area under curve, AUC)为0.903 6。在一篇抑郁症中的机器学习的综述中表明,随机森林(random forest, RF)、及极限梯度提升(extreme gradient boosting, XGBoost)是应用较多的两种方法[10]。尽管这些机器学习模型提供了良好的预测性能,由于机器学习模型属于黑盒模型,在实际临床中应用中还是受到一定的限制。Lundberg和Lee[11]提出了SHAP (SHapley Additive exPlanations)用以解释机器学习模型做出的决策。
本研究基于2005—2021年美国国家健康与营养调查数据库(National Health And Nutrition Examination Survey, NHANES),采用了XGBoost算法、随机森林和lasso logistic回归三种机器学习方法,构建识别老年人抑郁症相关的模型,并使用可解释性机器学习SHAP评估影响老年人抑郁症和老年人个体的主要影响因素。本研究旨在为抑郁症高危人群的早期发现和早期治疗提供科学依据。
NHANES旨在收集美国家庭人口健康和营养的信息,评估美国个人的健康和营养状况和了解公共卫生问题,每两年调查一次,所有数据在https://www.cdc.gov/nchs/NHANES/网站可以下载。在刘悦[12]、周雯惠[13]等文章中将≥65岁定义为老年人,因此本研究将年龄≥65的个体作为本次研究对象。为了评价预测模型的外部一致性,研究将2005—2018年的数据作为训练集,将2019—2020年的数据作为测试集评价模型的预测性能。数据集中删除了PHQ—9量表中有任意一项缺失的个体,同时缺失比例超过30%的变量和缺失变量比例大于50%的个体也被删去。
在NHANES数据库中,采用患者健康问卷9(patient health questionnaire-9, PHQ-9)[14]量表筛选抑郁症患者,该量表既是抑郁症严重程度的衡量标准,也是抑郁症的诊断指标。量表共有9个条目(在NHANES数据库中变量条目为DPQ010—DPQ090),每个条目0~3分,PHQ-9的总分范围为0~27分,以得分≥10分作为划分临床相关抑郁症的界值可以得到最高的特异度和灵敏度[14]
本研究的变量分别来自NHANES数据库中的人口学、膳食、测量、实验室指标和问卷或量表数据集。人口学数据中包括年龄、种族、学历、收入情况、收入与贫困比例和家庭人数等变量。膳食数据集包括总营养素摄入量和补充剂中的营养素摄入量,这些数据先通过面对面访谈获取第一次数据,再通过电话跟进获得第二次数据;膳食数据集包括饮食结构,膳食营养素包括金属元素、不饱和脂肪酸、维生素和水的摄入量。测量数据集包括身体测量指标如身高、体重、腰围、血压等。实验室测量指标包括血液和(或尿液)中的生化和金属指标,如脂蛋白、胆固醇、尼古丁、可替宁、免疫细胞、维生素、汞、铁、碘、铅、镉、硒和锰等。问卷或量表数据包括吸烟、饮酒、心血管健康、消费行为、当前健康状况、残疾、吸毒、身体活动、心理健康和睡眠等数据集。
由于实验室指标中的血生化指标、血液和尿液中金属元素和膳食营养素等指标进行对数变换,当这些变量的值为0时,给其加上0.01以使其能够进行对数变换。原始数据库中舒张压和收缩压分别测量了三次,取均值收缩压和舒张压变量纳入分析。
在描述人口统计学特征时,使用(均数±标准差)的形式描述定量变量,使用频数(百分比)描述定性变量。
在训练集和测试集中采用多重填补的方式填补自变量的缺失,使用递归特征消除(recursive feature elimination, RFE)筛选变量。因为该数据集属于不平衡数据,因此对于训练集使用少数类过采样法(synthetic minority over-sampling technique, SMOTE)[15],以使得抑郁症患者与正常人人数一致,从而提高模型训练效果。最后对数据进行标准化、归一化处理。
选择lasso logistic回归、随机森林和XGBoost算法构建模型,机器学习模型的超参数较多,因此采用贝叶斯优化的TPE (tree parzen estimator)[16]算法选择超参数,经过十折交叉验证保证结果的稳定性。
在测试集上评估模型性能,主要的评价指标为AUC、准确度、灵敏度和特异度。AUC置信区间的计算和比较使用De Long检验[15]P值小于0.05被认为有统计学差异。最后使用SHAP解释结果。SHAP值起源于博弈论,Shapley在1950年旨在根据玩家对游戏最终结果的贡献,在玩家之间分配收益而提出。它已发展为机器学习的一种重要解释方法,通过计算每个特征的重要性值(SHAP值)解释变量与个体的预测,以提高模型可解释性。本研究的数据处理与统计学检验使用R 4.2.1执行,模型构建、评价与解释均使用Python 3.0执行。检验水准α=0.05。
在训练集中共有6 808名老年人参与者接受了抑郁症评估,441名参与者被诊断患有抑郁症,患病率及95%CI为6.48%(5.90%~7.09%),在测试集中共有1 790名参与者接受了抑郁症评估,131名参与者被诊断患有抑郁症,患病率及95%CI为7.32%(6.45%~9.03%)。研究人群的人口统计学特征。见表1
经过SMOTE算法,训练集中共有12 734个观测,抑郁症和非抑郁症的个体各占50%。训练集经过RFE后得到特征变量62个。在这些变量的基础上建立lasso logistic回归、随机森林和XGBoost模型。表2图1总结了三种机器学习分类器在识别老年抑郁症方面的表现。
在训练集上,XGBoost模型的AUC、准确率和灵敏度最高,分别达到0.933、84.92%和84.87%。随机森林模型的灵敏度最高,为92.37%。Lasso logistic模型的表现最差,AUC为0.772。经过De Long检验,XGBoost模型的AUC高于lasso logistic模型(P<0.001)和RF模型(P<0.001),RF模型的AUC高于lasso logistic模型(P<0.001)。因此,采用XGBoost模型进行解释。
图2A为训练集上SHAP变量重要性图,前十重要的变量为是否存在睡眠问题、是否存在健康问题、嗜酸性粒细胞数、一个月内过度疲倦的次数、近一个月内是否有过感冒、嗜碱性粒细胞数、血清可替宁浓度、单核细胞数、受教育程度、PFA 18:4(十八碳四烯酸)。图2B显示不同性别之间,各个变量重要性差距接近。图2C为训练集上SHAP概要图,在重要性前十的变量中,未报告过存在睡眠问题、一个月内有过感冒以及教育程度较高患抑郁症的风险会降低。与之相反,健康状况越差、一个月内感到疲倦次数越多、血清可替宁浓度越高患抑郁症的风险会升高。
图3为SHAP决定图,其中图3A为嗜碱性粒细胞数变量的SHAP决定图,图3B为膳食中摄入的维生素B6的SHAP决定图(数值均经过对数转换)。图3A显示大多数患抑郁症风险较高的个体嗜碱性粒细胞数量较低;而图3B显示在膳食中摄入的维生素B6浓度较低和较高时,SHAP值大于0,提示患抑郁症风险较高的个体维生素B6摄入的浓度较高或较低,呈现“U”形的关系。
根据模型可以获得每个个体的SHAP力图,它可以显示影响个体的抑郁症的主要变量,整个模型的SHAP基础值为-0.022。如在图4A中测试集里第128个个体,模型认为其SHAP值为0.66大于-0.022,即预测其患抑郁症,主要原因为该个体近一个月有过感冒、差的健康状况、献血之外进行过艾滋病毒检测。图4B中展示的是第777个个体的力图,该个体的SHAP值为-2.33低于-0.022认为不存在抑郁症,主要原因为该个体无睡眠问题、膳食中较低的咖啡因摄入等。
抑郁症发病机制复杂,在人群中特别是老年人中会造成严重后果。及时发现并尽早采取干预措施有助于提高生活质量。一方面造成抑郁症的机制复杂,另一方面抑郁症的影响因素来自多个方面,如人口学特征、生活方式和遗传学等[17]。因此识别抑郁症的影响因素很关键。
近年来数据挖掘技术在探寻疾病的影响因素方面应用广泛,Su等人[18]基于中国健康调查数据库,使用长短期记忆模型(LSTM)和其他6个机器学习模型预测老年人抑郁情况和寻找抑郁的影响因素,最终在机器学习模型认为,日常生活活动(ADL)/工具性ADL(IADL)、自我评估的健康状况、婚姻状况、关节炎和同居次数是抑郁症老年人最重要的预测因素。Kessler等人[19]使用机器学习模型应用于1 056名参与者,预测重度抑郁症,最终发现机器学习模型的性能优于传统logistic回归模型。Zhang等人[20]使用Catboost模型识别2011—2018年NHANES数据库中中老年人抑郁症,结果显示,在中老年人抑郁症识别方面,Catboost模型性能最优;在中年人中抑郁症的最重要的影响因素为家庭收入与贫困的比率、一般健康状况和存在睡眠困难;在老年人中,抑郁症最主要的影响因素为一般健康状况、存在睡眠困难和经历困惑或记忆问题。
虽然机器学习模型在医学领域的研究很多,但实际在临床上的应用受到了一定限制[21]。通常机器学习模型被视为黑盒模型,因此想要获得医患的信任,就必须要具有解释性。SHAP作为一种与模型无关的解释性机器学习方法,可以解释模型是如何做出决策的,给出各个变量的贡献大小和方向。同时,SHAP还可以解释影响个体的主要因素,为精准化预防和控制疾病提供帮助。
本研究数据集来源于2005—2021年的NHANES数据库,使用机器学习模型识别65岁以上老年抑郁症患者。因为数据属于不平衡数据,因此采用SMOTE对数据集进行重抽样,以增加模型预测的准确性,使用lasso logistic、随机森林和XGBoost三种机器学习模型,最终XGBoost模型的AUC、准确率和特异度达到最高,随机森林模型的灵敏度最高。利用可视化的方式展示SHAP是如何做出决策的,其表现在变量重要性与个体解释两方面。第一方面,通过计算SHAP绝对值来比较变量重要性并通过柱状图展示,SHAP认为最主要的影响因素是是否存在睡眠问题、是否存在健康问题、嗜酸性粒细胞数,这和Zhang等人[20]的研究结果基本一致。SHAP概要图在此基础上还可以说明变量作用的方向以及该变量中个体值的分布情况,SHAP概要图显示嗜酸性粒细胞浓度较高时,会增大患抑郁症的风险,在更高浓度时和较低浓度时会降低抑郁的风险,提示炎症水平可能和抑郁症相关这与Lin等人[22]的研究一致。同时模型还提示在生活方式和血生化指标以外,膳食影响因素如不饱和脂肪酸中的十八碳四烯酸、DHA等还有维生素B6等可能也与抑郁症相关。第二方面体现在个体的预测,SHAP力图展示了单个个体的影响因素及其贡献(因素的SHAP值大小),并求和得到个体的SHAP值,并通过比较与模型的SHAP基础值(本数据为-0.022)大小判断是否存在抑郁症,有助于为个体精准化防治提供依据。
同时本研究还存在一些不足,本研究的数据为横断面数据,获得因素仅能进行抑郁症患者的识别,而不能进行因果推断。
  • 南京市医学重点科技发展项目(ZKX22019)
参考文献 引证文献
排序方式:
[1]
Kok RM, Reynolds CF3. Management of depression in older adults:a review[J]. JAMA: the Journal of the American Medical Association, 2017, 317(20): 2114-2122.
[2]
程小伟,黄俭,朱向阳,等.抑郁症患者心理韧性在述情障碍与情绪自我效能感间的中介效应[J].现代预防医学202350(11):2062-2066.
Cheng XW, Huang J, Zhu XY, et al. Mediating effect of psychological resilience between alexithymia and emotional self-efficacy in patients with depression[J]. Modern Preventive Medicine, 2023, 50(11): 2062-2066.
[3]
谢静静,李丽霞,柳学华,等.正念减压疗法和正念认知疗法安全性的meta分析[J].中国心理卫生杂志2024,(1):73-83.
Xie JJ, Li LX, Liu XH, et al. A meta-analysis of safety of mindfulness-based stress reduction therapy and mindfulness-based cognitive therapy[J].Chinese Mental Health Journal, 2024, (1): 73-83.
[4]
Bruce ML. Depression and disability in late Life: directions for future research[J]. The American Journal of Geriatric Psychiatry:Official Journal of the American Association for Geriatric Psychiatry,2001, 9(2): 102-112.
[5]
Beghi M, Butera E, Cerri CG, et al. Suicidal behaviour in older age:A systematic review of risk factors associated to suicide attempts and completed suicides[J]. Neuroscience and Biobehavioral Reviews,2021, 127: 193-211.
[6]
蔡利强,游亚凤,魏丽丽,等.老年抑郁症患者自杀观念与多导睡眠图参数的相关性分析[J].浙江大学学报:医学版202049(4):462-467.
Cai LQ, You YF, Wei LL, et al. Correlation between suicidal ideation and polysomnography parameters in late-life depression patients[J]. Journal of Zhejiang University. Medical Sciences, 2020, 49(4): 462-467.
[7]
王威,第五永长,杨谦,等.轻度认知障碍与老年期痴呆患者中医证候要素及影响因素的横断面调查[J].中医杂志202263(11):1064-1072.
Wang W, Di Wu YC, Yang Q, et al. Traditional Chinese medicine syndrome elements and influencing factors of patients with mild cognitive impairment and senile dementia: a cross-sectional study[J]. Journal of Traditional Chinese Medicine, 2022, 63(11): 1064-1072.
[8]
石萌, 邹宇量.中国中老年人午睡时长与抑郁症状的关联——基于CHARLS数据分析[J].现代预防医学202350(8):1461-1467.
Shi M, Zou YL. Relationship between nap duration and depressive symptoms among middle-aged and elderly Chinese——based on CHARLS data analysis[J]. Modern Preventive Medicine, 2023, 50(8): 1461-1467.
[9]
Sun YH, Liu QJ, Lee NY, et al. A novel machine learning approach to shorten depression risk assessment for convenient uses[J]. Journal of Affective Disorders, 2022, 312: 275-291.
[10]
Aleem S, Huda NU, Amin R, et al. Machine learning algorithms for depression: diagnosis, insights, and research directions[J].Electronics, 2022, 11(7): 1111.
[11]
Lundberg S, Lee SI. A unified approach to interpreting model predictions[M]. Neural Information Processing Systems, 2017, 4:4768-4777.
[12]
刘悦.基于机器学习的老年人抑郁症状的预测[D].济南:山东大学,2023.
Liu Y. Prediction of depression in the elderly based on machine learning[D]. Jinan: Shandong University, 2023.
[13]
周雯惠.中国老年人抑郁症状影响因素研究[D].南京:南京邮电大学,2022.
Zhou WH. Study on influencing factors of depressive symptoms in Chinese Elderly-Based on 2018 CLHLS data[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2022.
[14]
Zeng Z, Li Q, Caine ED, et al. Prevalence of and optimal screening tool for postpartum depression in a community-based population in China[J]. Journal of Affective Disorders, 2024, 348: 191-199.
[15]
Dablain D, Krawczyk B, Chawla NV. DeepSMOTE: fusing deep learning and SMOTE for imbalanced data[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(9): 6390-6404.
[16]
Bergstra J, Bardenet R, Bengio Y, et al. Algorithms for hyper-parameter optimization[C]//Proceedings of the 24th International Conference on Neural Information Processing Systems. Granada,Spain, Red Hook, NY, USA: Curran Associates Inc., 2011.
[17]
Monroe SM, Harkness KL. Major depression and its recurrences:Life course matters[J]. Annual Review of Clinical Psychology, 2022,18: 329-357.
[18]
Jiang YW, Xu XJ, Wang R, et al. Radiomics analysis based on lumbar spine CT to detect osteoporosis[J]. European Radiology, 2022,32: 8019-8026.
[19]
Kessler RC, Van Loo HM, Wardenaar KJ, et al. Testing a machine- learning algorithm to predict the persistence and severity of major depressive disorder from baseline self-reports[J]. Molecular Psychiatry, 2016, 21(10): 1366-1371.
[20]
Zhang CY, Chen XF, Wang S, et al. Using CatBoost algorithm to identify middle-aged and elderly depression, National health and nutrition examination survey 2011-2018[J]. Psychiatry Research,2021, 306: 114261.
[21]
Du TC, Tran TQB, Deo N, et al. Survey and evaluation of hypertension machine learning research[J]. Journal of the American Heart Association, 2023, 12(9): e027896.
[22]
Lin ZQ, Lawrence WR, Huang YH, et al. Classifying depression using blood biomarkers: A large population study[J].Journal of Psychiatric Research, 2021, 140: 364-372.
2024年第51卷第5期
PDF下载
55
23
引用本文
BibTeX
文章信息
doi: 10.20043/j.cnki.MPM.202309307
  • 接收时间:2023-09-17
  • 首发时间:2026-03-19
  • 出版时间:2024-03-10
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-09-17
基金
南京市医学重点科技发展项目(ZKX22019)
作者信息
    1.东南大学公共卫生学院,江苏 南京 210009
    2南京大学医学院附属鼓楼医院统计中心

通讯作者:

陈炳为,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/xdyfyx/CN/10.20043/j.cnki.MPM.202309307
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

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

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