Sleep deprivation detected by voice analysis

Thoret, Etienne; Andrillon, Thomas; Gauriau, Caroline; Léger, Damien; Pressnitzer, Daniel

doi:10.1101/2022.11.17.516913

Cited by 1 publication

(1 citation statement)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Metrics like those presented in Samek et al (2017a) , Petsiuk et al (2018) could help rate the quality of each explainability method, and future studies might enhance LRP explanation quality by applying different relevance rules to different parts of a network ( Samek et al, 2017b ). Additionally, while our analysis of relationships between local explanations and clinical and demographic variables was insightful, future studies might perform a variety of other analyses on local explanations ( Thoret et al, 2022 ). For example, they might cluster local explanations to identify subtypes of individuals or compute measures that quantify aspects of the temporal distribution of importance.…”

Section: Discussionmentioning

confidence: 99%

Novel methods for elucidating modality importance in multimodal electrophysiology classifiers

Ellis

Sendi

Zhang

et al. 2023

Front. Neuroinform.

View full text Add to dashboard Cite

IntroductionMultimodal classification is increasingly common in electrophysiology studies. Many studies use deep learning classifiers with raw time-series data, which makes explainability difficult, and has resulted in relatively few studies applying explainability methods. This is concerning because explainability is vital to the development and implementation of clinical classifiers. As such, new multimodal explainability methods are needed.MethodsIn this study, we train a convolutional neural network for automated sleep stage classification with electroencephalogram (EEG), electrooculogram, and electromyogram data. We then present a global explainability approach that is uniquely adapted for electrophysiology analysis and compare it to an existing approach. We present the first two local multimodal explainability approaches. We look for subject-level differences in the local explanations that are obscured by global methods and look for relationships between the explanations and clinical and demographic variables in a novel analysis.ResultsWe find a high level of agreement between methods. We find that EEG is globally the most important modality for most sleep stages and that subject-level differences in importance arise in local explanations that are not captured in global explanations. We further show that sex, followed by medication and age, had significant effects upon the patterns learned by the classifier.DiscussionOur novel methods enhance explainability for the growing field of multimodal electrophysiology classification, provide avenues for the advancement of personalized medicine, yield unique insights into the effects of demographic and clinical variables upon classifiers, and help pave the way for the implementation of multimodal electrophysiology clinical classifiers.

show abstract

Section: Discussionmentioning

confidence: 99%