001048425 001__ 1048425
001048425 005__ 20251204202144.0
001048425 0247_ $$2doi$$a10.1515/cdbme-2025-0192
001048425 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-04636
001048425 037__ $$aFZJ-2025-04636
001048425 082__ $$a570
001048425 1001_ $$0P:(DE-HGF)0$$aGoldermann, Lavinia$$b0$$eCorresponding author
001048425 245__ $$aThe Influence of Human Annotation on CNN Performance for Anomaly Detection in ICU Data
001048425 260__ $$aBerlin$$bDe Gruyter$$c2025
001048425 3367_ $$2DRIVER$$aarticle
001048425 3367_ $$2DataCite$$aOutput Types/Journal article
001048425 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1764851276_6975
001048425 3367_ $$2BibTeX$$aARTICLE
001048425 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001048425 3367_ $$00$$2EndNote$$aJournal Article
001048425 520__ $$aDeep learning methods are increasingly used in clinical artificial intelligence (AI) research, including for detecting anomalies in intensive care data. However, their evaluation often depends on human annotations, which can vary in quality and consistency. In this study, we analyse the effect of annotation variability on the performance of DeepAnT, an unsupervised convolutional neural network for anomaly detection (AD). Using intensive care time-series data from 38 patients for training and six patients separately annotated for evaluation, we compare F1 scores based on two independent physician annotations. Our results show differences in model performance across different vital parameters, between patients, and especially between annotators evaluating the same data. These findings indicate that human labelling has a measurable impact on the perceived performance of the AD algorithm. Structured labelling protocols may be beneficial for achieving more consistent and reliable evaluations.
001048425 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001048425 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001048425 7001_ $$0P:(DE-HGF)0$$aFonck, Simon$$b1
001048425 7001_ $$0P:(DE-HGF)0$$aOlivier, Lena$$b2
001048425 7001_ $$0P:(DE-Juel1)185651$$aFritsch, Sebastian$$b3$$ufzj
001048425 7001_ $$0P:(DE-HGF)0$$aStollenwerk, André$$b4
001048425 773__ $$0PERI:(DE-600)2835398-5$$a10.1515/cdbme-2025-0192$$gVol. 11, no. 1, p. 362 - 365$$n1$$p362 - 365$$tCurrent directions in biomedical engineering$$v11$$x2364-5504$$y2025
001048425 8564_ $$uhttps://juser.fz-juelich.de/record/1048425/files/The%20Influence%20of%20Human%20Annotation%20on%20CNN%20Performance%20for%20Anomaly%20Detection%20in%20ICU%20Data.pdf$$yOpenAccess
001048425 909CO $$ooai:juser.fz-juelich.de:1048425$$pdnbdelivery$$popenaire$$pdriver$$popen_access$$pVDB
001048425 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)185651$$aForschungszentrum Jülich$$b3$$kFZJ
001048425 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001048425 9141_ $$y2025
001048425 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-30
001048425 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001048425 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-04-03T10:39:59Z
001048425 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-04-03T10:39:59Z
001048425 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001048425 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2024-04-03T10:39:59Z
001048425 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2024-12-30
001048425 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-30
001048425 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2024-12-30
001048425 920__ $$lno
001048425 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001048425 9201_ $$0I:(DE-Juel1)CASA-20230315$$kCASA$$lCenter for Advanced Simulation and Analytics$$x1
001048425 980__ $$ajournal
001048425 980__ $$aVDB
001048425 980__ $$aUNRESTRICTED
001048425 980__ $$aI:(DE-Juel1)JSC-20090406
001048425 980__ $$aI:(DE-Juel1)CASA-20230315
001048425 9801_ $$aFullTexts