FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384627103> ?p ?o ?g. }

• W4384627103 endingPage "4858" @default.
• W4384627103 startingPage "4848" @default.
• W4384627103 abstract "Abstract Deep learning is increasingly being proposed for detecting neurological and psychiatric diseases from electroencephalogram (EEG) data but the method is prone to inadvertently incorporate biases from training data and exploit illegitimate patterns. The recent demonstration that deep learning can detect the sex from EEG implies potential sex‐related biases in deep learning‐based disease detectors for the many diseases with unequal prevalence between males and females. In this work, we present the male‐ and female‐typical patterns used by a convolutional neural network that detects the sex from clinical EEG (81% accuracy in a separate test set with 142 patients). We considered neural sources, anatomical differences, and non‐neural artifacts as sources of differences in the EEG curves. Using EEGs from 1140 patients, we found electrocardiac artifacts to be leaking into the supposedly brain activity‐based classifiers. Nevertheless, the sex remained detectable after rejecting heart‐related and other artifacts. In the cleaned data, EEG topographies were critical to detect the sex, but waveforms and frequencies were not. None of the traditional frequency bands was particularly important for sex detection. We were able to determine the sex even from EEGs with shuffled time points and therewith completely destroyed waveforms. Researchers should consider neural and non‐neural sources as potential origins of sex differences in their data, they should maintain best practices of artifact rejection, even when datasets are large, and they should test their classifiers for sex biases." @default.
• W4384627103 created "2023-07-19" @default.
• W4384627103 creator A5044501245 @default.
• W4384627103 creator A5044825834 @default.
• W4384627103 creator A5047904405 @default.
• W4384627103 creator A5066399859 @default.
• W4384627103 creator A5083826027 @default.
• W4384627103 creator A5092490774 @default.
• W4384627103 date "2023-07-17" @default.
• W4384627103 modified "2023-10-09" @default.
• W4384627103 title "Sex‐related patterns in the electroencephalogram and their relevance in machine learning classifiers" @default.
• W4384627103 cites W1974418863 @default.
• W4384627103 cites W1983051793 @default.
• W4384627103 cites W2000261872 @default.
• W4384627103 cites W2000297198 @default.
• W4384627103 cites W2003212556 @default.
• W4384627103 cites W2011402106 @default.
• W4384627103 cites W2026478689 @default.
• W4384627103 cites W2028520297 @default.
• W4384627103 cites W2042345559 @default.
• W4384627103 cites W2058827825 @default.
• W4384627103 cites W2062450948 @default.
• W4384627103 cites W2063161386 @default.
• W4384627103 cites W2069800866 @default.
• W4384627103 cites W2079115142 @default.
• W4384627103 cites W2082945637 @default.
• W4384627103 cites W2087496688 @default.
• W4384627103 cites W2101807845 @default.
• W4384627103 cites W2133665775 @default.
• W4384627103 cites W2169918686 @default.
• W4384627103 cites W2345279893 @default.
• W4384627103 cites W2399025472 @default.
• W4384627103 cites W2464981751 @default.
• W4384627103 cites W2568766977 @default.
• W4384627103 cites W2599251041 @default.
• W4384627103 cites W2741907166 @default.
• W4384627103 cites W2788175131 @default.
• W4384627103 cites W2883338911 @default.
• W4384627103 cites W2903746889 @default.
• W4384627103 cites W2915893085 @default.
• W4384627103 cites W2954019805 @default.
• W4384627103 cites W2963355311 @default.
• W4384627103 cites W2963915399 @default.
• W4384627103 cites W2964121744 @default.
• W4384627103 cites W2970154784 @default.
• W4384627103 cites W2993404698 @default.
• W4384627103 cites W3118650553 @default.
• W4384627103 cites W3130235815 @default.
• W4384627103 cites W3158695122 @default.
• W4384627103 cites W3217634872 @default.
• W4384627103 cites W4238992175 @default.
• W4384627103 cites W4285596585 @default.
• W4384627103 cites W4384627103 @default.
• W4384627103 doi "https://doi.org/10.1002/hbm.26417" @default.
• W4384627103 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37461294" @default.
• W4384627103 hasPublicationYear "2023" @default.
• W4384627103 type Work @default.
• W4384627103 citedByCount "1" @default.
• W4384627103 countsByYear W43846271032023 @default.
• W4384627103 crossrefType "journal-article" @default.
• W4384627103 hasAuthorship W4384627103A5044501245 @default.
• W4384627103 hasAuthorship W4384627103A5044825834 @default.
• W4384627103 hasAuthorship W4384627103A5047904405 @default.
• W4384627103 hasAuthorship W4384627103A5066399859 @default.
• W4384627103 hasAuthorship W4384627103A5083826027 @default.
• W4384627103 hasAuthorship W4384627103A5092490774 @default.
• W4384627103 hasBestOaLocation W43846271031 @default.
• W4384627103 hasConcept C108583219 @default.
• W4384627103 hasConcept C119857082 @default.
• W4384627103 hasConcept C153180895 @default.
• W4384627103 hasConcept C154945302 @default.
• W4384627103 hasConcept C15744967 @default.
• W4384627103 hasConcept C158154518 @default.
• W4384627103 hasConcept C169760540 @default.
• W4384627103 hasConcept C17744445 @default.
• W4384627103 hasConcept C199539241 @default.
• W4384627103 hasConcept C2779010991 @default.
• W4384627103 hasConcept C41008148 @default.
• W4384627103 hasConcept C50644808 @default.
• W4384627103 hasConcept C522805319 @default.
• W4384627103 hasConcept C81363708 @default.
• W4384627103 hasConceptScore W4384627103C108583219 @default.
• W4384627103 hasConceptScore W4384627103C119857082 @default.
• W4384627103 hasConceptScore W4384627103C153180895 @default.
• W4384627103 hasConceptScore W4384627103C154945302 @default.
• W4384627103 hasConceptScore W4384627103C15744967 @default.
• W4384627103 hasConceptScore W4384627103C158154518 @default.
• W4384627103 hasConceptScore W4384627103C169760540 @default.
• W4384627103 hasConceptScore W4384627103C17744445 @default.
• W4384627103 hasConceptScore W4384627103C199539241 @default.
• W4384627103 hasConceptScore W4384627103C2779010991 @default.
• W4384627103 hasConceptScore W4384627103C41008148 @default.
• W4384627103 hasConceptScore W4384627103C50644808 @default.
• W4384627103 hasConceptScore W4384627103C522805319 @default.
• W4384627103 hasConceptScore W4384627103C81363708 @default.
• W4384627103 hasFunder F4320316264 @default.
• W4384627103 hasFunder F4320320875 @default.
• W4384627103 hasFunder F4320320879 @default.

• next