001014812 001__ 1014812
001014812 005__ 20231027114415.0
001014812 0247_ $$2doi$$a10.1186/s12916-023-02941-4
001014812 0247_ $$2datacite_doi$$a10.34734/FZJ-2023-03482
001014812 0247_ $$2pmid$$a37400814
001014812 0247_ $$2WOS$$aWOS:001022895400003
001014812 037__ $$aFZJ-2023-03482
001014812 082__ $$a610
001014812 1001_ $$0P:(DE-HGF)0$$aChen, Zhiyi$$b0$$eCorresponding author
001014812 245__ $$aSampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry
001014812 260__ $$aHeidelberg [u.a.]$$bSpringer$$c2023
001014812 3367_ $$2DRIVER$$aarticle
001014812 3367_ $$2DataCite$$aOutput Types/Journal article
001014812 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1694681451_31006
001014812 3367_ $$2BibTeX$$aARTICLE
001014812 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001014812 3367_ $$00$$2EndNote$$aJournal Article
001014812 500__ $$aThis work was supported by the PLA Key Research Foundation (CWS20J007), PLA Talent Program Foundation (2022160258), the STI2030-Major Projects (No. 2022ZD0214000), the National Key R&D Program of China (No. 2021YFC2502200) and the National Natural Science Foundation of China (No. 82201658).
001014812 520__ $$aAbstractBackground The development of machine learning models for aiding in the diagnosis of mental disorder is rec‑ognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains achallenge, with poor generalizability being a major limitation.Methods Here, we conducted a pre‑registered meta‑research assessment on neuroimaging‑based models in thepsychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a viewthat has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment.Based on these findings, we built a comprehensive 5‑star rating system to quantitatively evaluate the quality of exist‑ing machine learning models for psychiatric diagnoses.Results A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient(G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany,G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by nationaleconomic levels (β = − 2.75, p < .001, R2adj = 0.40; r = − .84, 95% CI: − .41 to − .97), and was plausibly predictable formodel performance, with higher sampling inequality for reporting higher classification accuracy. Further analysesshowed that lack of independent testing (84.24% of models, 95% CI: 81.0–87.5%), improper cross‑validation (51.68%of models, 95% CI: 47.2–56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9–90.8%)/availability(80.88% of models, 95% CI: 77.3–84.4%) are prevailing in current diagnostic classifiers despite improvements overtime. Relating to these observations, model performances were found decreased in studies with independent cross‑country sampling validations (all p < .001, BF10 > 15). In light of this, we proposed a purpose‑built quantitative assess‑ment checklist, which demonstrated that the overall ratings of these models increased by publication year but werenegatively associated with model performance.Conclusions Together, improving sampling economic equality and hence the quality of machine learning modelsmay be a crucial facet to plausibly translating neuroimaging‑based diagnostic classifiers into clinical practice.Keywords Psychiatric machine learning, Diagnostic classification, Meta‑analysis, Neuroimaging, Sampling inequalities
001014812 536__ $$0G:(DE-HGF)POF4-5252$$a5252 - Brain Dysfunction and Plasticity (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001014812 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001014812 7001_ $$aHu, Bowen$$b1
001014812 7001_ $$aLiu, Xuerong$$b2
001014812 7001_ $$aBecker, Benjamin$$b3
001014812 7001_ $$0P:(DE-Juel1)131678$$aEickhoff, Simon B.$$b4$$ufzj
001014812 7001_ $$aMiao, Kuan$$b5
001014812 7001_ $$aGu, Xingmei$$b6
001014812 7001_ $$aTang, Yancheng$$b7
001014812 7001_ $$aDai, Xin$$b8
001014812 7001_ $$aLi, Chao$$b9
001014812 7001_ $$aLeonov, Artemiy$$b10
001014812 7001_ $$aXiao, Zhibing$$b11
001014812 7001_ $$aFeng, Zhengzhi$$b12
001014812 7001_ $$0P:(DE-HGF)0$$aChen, Ji$$b13$$eCorresponding author
001014812 7001_ $$aChuan-Peng, Hu$$b14
001014812 773__ $$0PERI:(DE-600)2131669-7$$a10.1186/s12916-023-02941-4$$gVol. 21, no. 1, p. 241$$n1$$p241$$tBMC medicine$$v21$$x1741-7015$$y2023
001014812 8564_ $$uhttps://juser.fz-juelich.de/record/1014812/files/Chen23.pdf$$yOpenAccess
001014812 909CO $$ooai:juser.fz-juelich.de:1014812$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001014812 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131678$$aForschungszentrum Jülich$$b4$$kFZJ
001014812 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5252$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
001014812 9141_ $$y2023
001014812 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2022-11-25
001014812 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2022-11-25
001014812 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2022-11-25
001014812 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2022-11-25
001014812 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001014812 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001014812 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2022-11-25
001014812 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2023-05-02T09:07:15Z
001014812 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2023-05-02T09:07:15Z
001014812 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Open peer review$$d2023-05-02T09:07:15Z
001014812 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bBMC MED : 2022$$d2023-10-25
001014812 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-10-25
001014812 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-10-25
001014812 915__ $$0StatID:(DE-HGF)0320$$2StatID$$aDBCoverage$$bPubMed Central$$d2023-10-25
001014812 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2023-10-25
001014812 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2023-10-25
001014812 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-10-25
001014812 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2023-10-25
001014812 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-10-25
001014812 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2023-10-25
001014812 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bBMC MED : 2022$$d2023-10-25
001014812 920__ $$lyes
001014812 9201_ $$0I:(DE-Juel1)INM-7-20090406$$kINM-7$$lGehirn & Verhalten$$x0
001014812 980__ $$ajournal
001014812 980__ $$aVDB
001014812 980__ $$aUNRESTRICTED
001014812 980__ $$aI:(DE-Juel1)INM-7-20090406
001014812 9801_ $$aFullTexts