Computer-assisted interpretation of clinical EEGs

The aim of this study is to explore the capability of an Emfit (electromechanical film transducer) mattress to detect snoring (SN) by analyzing the spectral differences between normal breathing (NB) and SN. Episodes of representative NB and SN of a maximum of 10 min were visually selected for analysis from 33 subjects. To define the bands of interest, we studied the statistical differences in the power spectral density (PSD) between both breathing types. Three bands were selected for further analysis: 6-16 Hz (BW1), 16-30 Hz (BW2) and 60-100 Hz (BW3). We characterized the differences between NB and SN periods in these bands using a set of spectral features estimated from the PSD. We found that 15 out of the 29 features reached statistical significance with the Mann-Whitney U-test. Diagnostic properties for each feature were assessed using receiver operating characteristic analysis. According to our results, the highest diagnostic performance was achieved using the power ratio between BW2 and BW3 (0.85 area under the receiver operating curve, 80% sensitivity, 80% specificity and 80% accuracy). We found that there are significant differences in the defined bands between the NB and SN periods. A peak was found in BW3 for SN epochs, which was best detected using power ratios. Our work suggests that it is possible to detect snoring with an Emfit mattress. The mattress-type movement sensors are inexpensive and unobtrusive, and thus provide an interesting tool for sleep research.

show abstract

“…Finally, the form factor (F) or complexity (Hjorth 1970, Binnie et al 1978 was computed in all three bands:…”

Section: Estimation Of Spectral Parametersmentioning

confidence: 99%

Spectral analysis of snoring events from an Emfit mattress

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The design details of the RBFN used in our experiments are as follows: The input layer contains M = 5 nodes to accept the set of features {FF1, FF2, S, K, H} extracted from each VAG signal. The spread parameter r was varied over the range [1,6], and the number of hidden nodes I was varied over the range [1,30]. The resulting output values were used to derive ROC curves and the associated A z values using ROCKIT.…”

Section: Pattern Classificationmentioning

confidence: 99%

Screening of knee-joint vibroarthrographic signals using statistical parameters and radial basis functions

Rangayyan

2007

Med Biol Eng Comput

View full text Add to dashboard Cite

Externally detected vibroarthrographic (VAG) signals bear diagnostic information related to the roughness, softening, breakdown, or the state of lubrication of the articular cartilage surfaces of the knee joint. Analysis of VAG signals could provide quantitative indices for noninvasive diagnosis of articular cartilage breakdown and staging of osteoarthritis. We propose the use of statistical parameters of VAG signals, including the form factor involving the variance of the signal and its derivatives, skewness, kurtosis, and entropy, to classify VAG signals as normal or abnormal. With a database of 89 VAG signals, screening efficiency of up to 0.82 was achieved, in terms of the area under the receiver operating characteristics curve, using a neural network classifier based on radial basis functions.

show abstract

“…Recently, power spectral analysis is often employed in experimental as well as clinical studies in order to qualitatively and quanti tatively clarify the EEG changes caused by CNS acting drugs (1-5) or psychological stress (6) and to diagnose cerebral disorders (7)(8)(9)(10). It might be possible to characterize the alterations of the CNS caused by drugs or other agents as alterations of spectra by this analysis, if better techniques were developed.…”

Section: Various Computer Techniquesmentioning

confidence: 99%

Characteristics of the Cortical and Hippocampal EEG Power Spectra of Rabbits during Normal Behavioral States and after Administration of CNS Acting Drugs

Yamamoto

1985

Japanese Journal of Pharmacology

View full text Add to dashboard Cite

Abstract-TheEEG power spectra of the motor cortex (MC) and hippocampus (HPC) in rabbits were characterized, and the effects of CNS acting drugs on the spectra were investigated. The EEGs of rabbits with chronically implanted elec trodes were recorded with bipolar leads and simultaneously analyzed for 15 min with a computer to obtain their power spectra. MC spectra had one peak of delta wave, and HPC spectra had two peaks of delta and theta waves, whose peak powers and frequencies were changed in correspondence to the level of consciousness. Pentobarbital (20 mg/kg, i.v.) produced the peaks at 11 and 4 Hz in MC and HPC spectra, respectively. Morphine (5 mg/kg, i.v.) produced the peak at 7 Hz in MC spectra and shifted the theta wave peak of HPC to lower frequencies. Diazepam (4 mg/kg, i.v.) produced the peak at 14 Hz in MC spectra and decreased the two peak powers in HPC spectra. Chlorpromazine (4 mg/kg, i.v.) shifted the theta wave peak of HPC to lower frequencies. Amitriptyline (5 mg/kg, i.v.) increased the peak powers of the delta waves in MC and HPC spectra. These results suggest that each of the five CNS acting drugs produces the characteristic spectra, and they are different from the spectra obtained during normal behavioral states.

show abstract

Computer-assisted interpretation of clinical EEGs

Cited by 36 publications

References 6 publications

Spectral analysis of snoring events from an Emfit mattress

Spectral analysis of snoring events from an Emfit mattress

Screening of knee-joint vibroarthrographic signals using statistical parameters and radial basis functions

Characteristics of the Cortical and Hippocampal EEG Power Spectra of Rabbits during Normal Behavioral States and after Administration of CNS Acting Drugs

Contact Info

Product

Resources

About