DOSED: a deep learning approach to detect multiple sleep micro-events in EEG signal

7 Dec 2018Stanislas ChambonValentin ThoreyPierrick J. ArnalEmmanuel MignotAlexandre Gramfort

Background: Electroencephalography (EEG) monitors brain activity during sleep and is used to identify sleep disorders. In sleep medicine, clinicians interpret raw EEG signals in so-called sleep stages, which are assigned by experts to every 30s window of signal... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Sleep apnea detection Dreem_NCT03657329 DOSED Accuracy 81% # 1
F1-score (@IoU = 0.3) 0.57 ± 0.23 # 1
Mean AHI Error 4.69 ± 4.25 # 1
K-complex detection MASS SS2 DOSED F1-score (@IoU = 0.3) 0.6 # 3
Spindle Detection MASS SS2 DOSED F1-score (@IoU = 0.3) 0.75 # 3
Sleep Arousal Detection MESA DOSED (3 EEG + 2 EOG) F1-score (@IoU = 0.3) 0.71 # 1
Sleep Arousal Detection MESA DOSED (1 EEG) F1-score (@IoU = 0.3) 0.61 # 2
Spindle Detection Stanford Sleep Cohort (SSC) DOSED F1-score (@IoU = 0.3) 0.48 # 1
Spindle Detection Wisconsin Sleep Cohort (WSC) DOSED F1-score (@IoU = 0.3) 0.46 # 1

Methods used in the Paper