Automated Sleep-Spindle Detection in Healthy Children Polysomnograms

• Published in: IEEE transactions on biomedical engineering Vol. 57; no. 9; pp. 2135 - 2146
• Main Authors: Causa, Leonardo, Held, Claudio M., Causa, Javier, Estévez, Pablo A., Perez, Claudio A., Chamorro, Rodrigo, Garrido, Marcelo, Algarín, Cecilia, Peirano, Patricio
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.09.2010; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithm design and analysis; Algorithms; Biological and medical sciences; Child; Children & youth; Computerized, statistical medical data processing and models in biomedicine; EEG; Electrodiagnosis. Electric activity recording; Electroencephalography; Electroencephalography - methods; empirical-mode decomposition (EMD); Frequency; Fundamental and applied biological sciences. Psychology; Fuzzy Logic; Hilbert-Huang transform (HHT); Humans; Inspection; Investigative techniques, diagnostic techniques (general aspects); Medical management aid. Diagnosis aid; Medical sciences; Nervous system; Neurons; Nonlinear Dynamics; Pattern Recognition, Automated - methods; Pediatrics; Polysomnography - methods; Reproducibility of Results; ROC Curve; Signal Processing, Computer-Assisted; Sleep; sleep spindles (SSs); sleep-pattern recognition; Sleep. Vigilance; Testing; Training; Vertebrates: nervous system and sense organs; Visual databases; Human; Empirical mode decomposition; empirical-mode decomposition (EMD); Spindle; EEG; Decomposition method; Empirical method; Electrophysiology; Electroencephalography; Pattern recognition; Hilbert transformation; Hilbert-Huang transform (HHT); Electrodiagnosis; Sleep; sleep-pattern recognition; Automatic measurement; Signal processing; Sleep wake cycle; sleep spindles (SSs); Child; Biomedical engineering
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2010.2052924

We present a new methodology to detect and characterize sleep spindles (SSs), based on the nonlinear algorithms, empirical-mode decomposition, and Hilbert-Huang transform, which provide adequate temporal and frequency resolutions in the electroencephalographic analysis. In addition, the application of fuzzy logic allows to emulate expert's procedures. Additionally, we built a database of 56 all-night polysomnographic recordings from children for training and testing, which is among the largest annotated databases published on the subject. The database was split into training (27 recordings), validation (10 recordings), and testing (19 recordings) datasets. The SS events were marked by sleep experts using visual inspection, and these marks were used as golden standard. The overall SS detection performance on the testing dataset of continuous all-night sleep recordings was 88.2% sensitivity, 89.7% specificity, and 11.9% false-positive (FP) rate. Considering only non-REM sleep stage 2, the results showed 92.2% sensitivity, 90.1% specificity, and 8.9% FP rate. In general, our system presents enhanced results when compared with most systems found in the literature, thus improving SS detection precision significantly without the need of hypnogram information.