Fusae Kawana

Automatic EEG arousal detection for sleep apnea syndrome

Abstract Electroencephalographic (EEG) arousals are seen in EEG recordings as an awakening response of the human brain. Sleep apnea is a serious sleep disorder. Severe sleep apnea brings about EEG arousals and sleep for patients with sleep apnea syndrome (SAS) is thus frequently interrupted. The number of respiratory-related arousals during the whole night on PSG recordings is directly related to the quality of sleep. Detecting EEG arousals in the PSG record is thus a significant task for clinical diagnosis in sleep medicine. In this paper, a method for automatic detection of EEG arousals in SAS patients was proposed. To effectively detect respiratory-related arousals, threshold values were determined according to pathological events as sleep apnea and electromyogram (EMG). If resumption of ventilation (end of the apnea interval) was detected, much lower thresholds were adopted for detecting EEG arousals, including relatively doubtful arousals. Conversely, threshold was maintained high when pathological events were undetected. The proposed method was applied to polysomnographic (PSG) records of eight patients with SAS and accuracy of EEG arousal detection was verified by comparative visual inspection. Effectiveness of the proposed method in clinical diagnosis was also investigated.

Multi-valued decision making of sleep stages determination based on expert knowledge

This paper introduced an expert knowledge-based automatic sleep stage determination system working on statistical signal processing. The main methods included two processes. One was expert knowledge base construction, which was developed in terms of probability density functions (pdfs) of parameters for each sleep stage. Here, the visual inspection by a clinician was utilized rather than stage scoring criteria for expert knowledge base construction. Another was multi-valued decision making of sleep stages, where stages were determined automatically according to the conditional probabilities. Totally, four subjects were participated, They are patients from Toranomon hospital, Japan. The automatic sleep stage determination results showed close agreements with the visual inspection in stage awake, light sleep stages and deep sleep stages. The constructed expert knowledge base reflected the distributions of characteristic parameters corresponding to each stage. The proposed method may have strong performance to be an assistant tool for clinicians enabling further inspection of sleep disorder cases.

Conditional probability of Cauchy distribution in automatic sleep stage determination for sleep data with artifacts

An automatic sleep stage determination system dealing with the sleep data contaminated by artifacts is developed, which is working on an expert knowledge-based multi-valued decision making method. The knowledge database is consisted of probability density functions of parameters for various sleep stages according to the visual inspection by a qualified clinician. The probability density functions are approximated by Cauchy distribution on histograms. Sleep stages are determined automatically according to the maximum value of conditional probability. Due to the infinite variance of Cauchy distribution, the effect of mis-determination caused by artifacts can be abated. The result of automatic sleep stage determination was satisfactory. The presented automatic sleep stage determination can be an assistant tool for clinical practice.

Automatic determination of sleep stage through bio-neurological signals contaminated with artifacts by a conditional probability of the knowledge base

In this study, an automatic sleep-stage determination system with the capacity for artifact detection was developed. The methodology was based on the conditional probability of the knowledge base of an expert visual inspection. Expert visual inspection was the manual scoring of sleep stages and artifacts by a qualified clinician. The knowledge base consisted of probability density functions of characteristic parameters for stages and artifacts. Automatic sleep-stage determination and artifact detection were carried out based on a value of conditional probability. The total overnight bioneurological signals under the usual recording conditions with the artifacts of four subjects were analyzed. The results of automatic sleep-stage determination showed a close agreement with the expert visual inspections. In addition, an artifact can be detected at the same time by using the same method. With the capacity for artifact detection, the proposed automatic sleep-stage determination system can be adapted for real clinical applications.

Automatic Sleep Stage Determination by Conditional Probability: Optimized Expert Knowledge-based Multi-Valued Decision Making

The aim of this study is to develop a knowledgebased automatic sleep stage determination system which can be optimized for different cases of sleep data at hospitals. The main methodology of multi-valued decision making includes two modules. One is a learning process of expert knowledge database construction. Visual inspection by a qualified clinician is utilized to obtain the probability density functions of parameters for sleep stages. Parameter selection is introduced to find out optimal parameters for variable sleep data. Another is automatic sleep stage determination process. The decision making of sleep stage is made based on conditional probability. The result showed close agreement comparing with the visual inspection. The developed system is flexible to learn from any clinician. It can meet the customized requirements in hospitals and institutions.

Automatic EEG Arousals Detection for Obstructive Sleep Apnea Syndrome

Abstract EEG arousals are seen in EEG records as awakening response of human brain. Obstructive sleep apnea (OSA) is one of serious sleep disorders. Sevier OSA brings about EEG arousals and sleep of patients with OSAS is frequently interrupted. Number of respiratory-related arousals during the whole night PSG recordings is directly concerned with the quality of patients’ sleep. Therefore, to detect EEG arousals in PSG record is significant task for clinical diagnosis. In this paper, the method for automatic detection of EEG arousals was proposed. In order to detected respiratory-related arousals effectively, threshold values were determined according to the pathological events as sleep apnea and EMG. If the resumption of ventilation (end of apnea) was detected, lower thresholds were adopted for detecting EEG arousals including relatively doubtful arousals. On the other hand, threshold maintains high when the pathological events were not detected. Proposed method was applied to the data of eight patients with OSAS, and accuracy of EEG arousals detection was verified by comparing the visual inspection. Effectiveness of the proposed method in clinical diagnosis was investigated.

Adaptive Threshold Determination for Automatic Detection of EEG Arousals in PSG Records Proceedings

Recent years, increase of patients with a sleep apnea syndrome (SAS) becomes a serious problem. The EEG arousals appeared in the sleep EEG of whole night recording gives specific information for clinical diagnosis on sleep disorders. In this paper, the automatic detection of EEG arousals in PSG record was proposed. EEG arousals originating from the external stimuli such as sleep apnea, periodic leg movement and so on are clinically important, so the respiratory information, increase of electromyographic (EMG) activities of subject were considered for determining the threshold values. In order to restrain the differences of characteristics of EEG between subjects, the normalization procedures were adopted for calculating parameters. The proposed method was applied to the data acquired from eight subjects and the accuracy was investigated by comparing the visual inspection. Proposed automatic detection method will be an powerful assistant tool for visual inspection of whole night PSG recordings.