• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.89-103
• /
• 2023

Obstructive sleep apnea (OSA) is one of the most prevalent sleep disorders that can lead to serious consequences, including hypertension and/or cardiovascular diseases, if not treated promptly. Continuous positive airway pressure (CPAP) is widely recognized as the most effective treatment for OSA, which needs the proper titration of airway pressure to achieve the most effective treatment results. However, the process of CPAP titration can be time-consuming and cumbersome. There is a growing importance in predicting personalized CPAP pressure before CPAP treatment. The primary objective of this study was to optimize the CPAP titration process for obstructive sleep apnea patients through EEG feature engineering with machine learning techniques. We aimed to identify and utilize the most critical EEG features to forecast key OSA predictive indicators, ultimately facilitating more precise and personalized CPAP treatment strategies. Here, we analyzed 126 OSA patients' PSG datasets before and after the CPAP treatment. We extracted 29 EEG features to predict the features that have high importance on the OSA prediction index which are AHI and SpO2 by applying the Shapley Additive exPlanation (SHAP) method. Through extracted EEG features, we confirmed the six EEG features that had high importance in predicting AHI and SpO2 using XGBoost, Support Vector Machine regression, and Random Forest Regression. By utilizing the predictive capabilities of EEG-derived features for AHI and SpO2, we can better understand and evaluate the condition of patients undergoing CPAP treatment. The ability to predict these key indicators accurately provides more immediate insight into the patient's sleep quality and potential disturbances. This not only ensures the efficiency of the diagnostic process but also provides more tailored and effective treatment approach. Consequently, the integration of EEG analysis into the sleep study protocol has the potential to revolutionize sleep diagnostics, offering a time-saving, and ultimately more effective evaluation for patients with sleep-related disorders.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.1
• /
• pp.41-51
• /
• 2017

This Paper Describes a Method for the Evaluation of Sleep Apnea, Namely, the Peak Signal-to-noise ratio (PSNR) of Wavelet Transformed Electroencephalography (EEG) Data. The Purpose of this Study was to Investigate EEG Properties with Regard to Differences between Sleep Spindles and K-complexes and to Characterize Obstructive Sleep Apnea According to Sleep Stage. We Examined Non-REM and REM Sleep in 20 Patients with OSA and Established a New Approach for Detecting Sleep Apnea Base on EEG Frequency Changes According to Sleep Stage During Sleep Apnea Events. For Frequency Bands Corresponding to A3 Decomposition with a Sampling Applied to the KC and the Sleep Spindle Signal. In this Paper, the KC and Sleep Spindle are Ccalculated using MSE and PSNR for 4 Types of Mother Wavelets. Wavelet Transform Coefficients Were Obtained Around Sleep Spindles in Order to Identify the Frequency Information that Changed During Obstructive Sleep Apnea. We also Investigated Whether Quantification Analysis of EEG During Sleep Apnea is Valuable for Analyzing Sleep Spindles and The K-complexes in Patients. First, Decomposition of the EEG Signal from Feature Data was Carried out using 4 Different Types of Wavelets, Namely, Daubechies 3, Symlet 4, Biorthogonal 2.8, and Coiflet 3. We Compared the PSNR Accuracy for Each Wavelet Function and Found that Mother Wavelets Daubechies 3 and Biorthogonal 2.8 Surpassed the other Wavelet Functions in Performance. We have Attempted to Improve the Computing Efficiency as it Selects the most Suitable Wavelet Function that can be used for Sleep Spindle, K-complex Signal Processing Efficiently and Accurate Decision with Lesser Computational Time.

• Korean Journal of Clinical Laboratory Science
• /
• v.46 no.3
• /
• pp.106-110
• /
• 2014

Obstructive sleep apnea-hypopnea (OSAH) is known to be related to nocturnal blood pressure (BP) and hypertension. The aim of this study was to evaluate the prevalence of hypertension according to the apnea-hypopnea grading. A total of 2,210 adults with snoring and obstructive sleep apnea were referred to our sleep center from July 2009 to May 2013. Clinical blood pressure (BP) was measured before sleeping (bedtime BP) and immediately after waking up in the next morning (morning BP). Subjects were classified into four groups based on the apnea-hypopnea index (AHI) from PSG as follows: control group (n=470) simple snoring and with AHI<5; mild group (n=577) with $AHI{\geq}5$ and <15; moderate group (n=508) $AHI{\geq}15$ and <30; and severe group (n=655) with $AHI{\geq}30$. The differences and correlations between BP and PSG parameters according to the AHI groups were analyzed. Patient's were classified as nomentensive (blood pressure <120/90 mmHg, n=700), prehypertensive (blood pressure < $140-120{\leq}mmHg$, n=1297) hypertensive (blood pressure ${\geq}140/90mmHg$, n=214) according to the office blood pressure measurements. The comparison of sleep parameters showed that OSA groups had a significantly higher stage N1 (control group vs. moderate OSA, severe OSA; $66.4{\pm}30.7$ vs. $85.5{\pm}36.6$, $128.4{\pm}57.3$, p<0.001) and total arousal number (control vs. moderate OSA, severe OSA; $110.7{\pm}47.7$ vs. $150.8{\pm}56.6$, $236.6{\pm}95.8$, p<0.001) compared to control group. The comparison of sleep parameters showed that OSA groups had a significantly lower stage N2 (control group vs. moderate OSA, severe OSA; $172.6{\pm}47.2$ vs. $150.7{\pm}50.5$, $120.3{\pm}57.4$, p<0.001), stage N3 (control group vs. moderate OSA, severe OSA; $38.4{\pm}33.4$ vs. $27.4{\pm}26.0$, $56.1{\pm}27.5$, p<0.001), REM (control group vs. moderate OSA, severe OSA; $64.3{\pm}25.5$ vs. $56.1{\pm}27.5$, $47.3{\pm}25.9$, p<0.001) and mean SaO2% (control group vs. moderate OSA, severe OSA; $90.0{\pm}3.5$ vs. $82.5{\pm}5.5$, $70.0{\pm}8.8$, p<0.001) compared to control group. The Apnea-hypopnea index was significantly higher in OSA groups, increased systolic and diastolic blood pressure than in the nomentensive group (bed time systolic pressure vs. AHI; <120 vs. 120-139, 140-159, >159; $17.5{\pm}18.6$ vs. $24.9{\pm}21.0$, $31.0{\pm}25.7$, $42.3{\pm}31.7$, p<0.001), (bed time diastolic pressure vs. AHI; 60-79 vs. 80-89, 90-99, >99; $19.3{\pm}19.7$ vs. $22.4{\pm}20.3$, $29.8{\pm}23.3$, $38.8{\pm}28.5$, p<0.001). AHI was positively correlated with morning systolic pressure, diastolic pressure, bed time systolic pressure and diastolic pressure (r=0.314, 0.279, 0.233 and 0.200, respectively, p<0.001). We conclude that BMI, Age, neck circumference and AHI increase with the blood pressure.

• The Journal of the Korean dental association
• /
• v.53 no.4
• /
• pp.249-258
• /
• 2015

Snoring and obstructive sleep apnea are the representative sleep disordered breathings, caused by the temporary and repetitive constriction or obstruction of upper airway during sleep. They present with excessively vibratory noise and repetitive cease of respiration. These disorders commonly result in sleep disturbance and the subsequent daytime sleepiness, chronic fatigue. Furthermore, they can cause the serious and extensive complications including increased risk of hypertension, cardiac arrhythmia, cardiovascular disease, cerebrovascular accident, neurocognitive disturbance, traffic and occupational accidents, type II diabetes, childhood growth interruption, awakening headache and finally, relatively increased mortality rate. Because appropriate therapeutic intervention is best way for patients to relieve their symptoms and prevent their possible complications, it is very important for dentists to recognize their own role and responsibility in diagnosis and treatment of these disorders. For this, the present article provides the understanding of the clinical features, possible complications, various treatment modalities, and suitable treatment strategies for snoring and obstructive sleep apnea.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.7
• /
• pp.113-123
• /
• 2020

Obstructive sleep apnea (OSA) among sleep disorders is one of relatively common diseases. Patients can be checked for the disease through sleep polysomnography. However, as far as he diagnosis of OSA using polysomnography (PSG) is concerned, many practical problems such as an increasing number of patients, expensive testing cost, discomfort during examination, and the limited number of people for testing have been pointed out. Accordingly, for the purpose of substituting PSG researchers have been actively conducting studies on OSA diagnosis based on machine learning using bio signals. In this regard, we review a rich body of existing OSA diagnosis studies applying machine learning techniques based on bio-signal data. As a result, this paper presents a novel taxonomy of the reviewed studies and provides their comprehensive comparative analysis results. Also, we reveal various limitations of the studies using the bio signals and suggest several improvements about utilization of the used machine learning methods. Finally, this paper presents future research topics related to the application of machine learning techniques using bio signals.

• Journal of Oral Medicine and Pain
• /
• v.41 no.2
• /
• pp.54-60
• /
• 2016

Purpose: Mandibular advancement devices (MAD) are used effectively and widely for the treatment of obstructive sleep apnea (OSA) and rapid-eye-movement (REM) dependency of the patients can affect the treatment outcome of OSA. The aim of this study was to compare treatment outcomes of MAD between REM-related and not-REM-related OSA patients. Methods: Fifty-six consecutive patients with OSA who received MAD therapy were evaluated using full night polysomnography before and after insertion of the MADs. The patients were divided into REM-related (REM apnea-hypopnea index [AHI] at least two times higher than their non-REM AHI) and not-REM-related (REM AHI less than two times higher than their non-REM AHI) OSA groups. Results: MAD is used for the treatment of OSA effectively. In respect of AHI, MAD therapy were effective both in REM-related OSA and not-REM-related OSA, but MAD therapy was more effective in not-REM-related OSA than REM-related OSA in overall sleep and non-REM sleep. $SpO_2$ saturations were improved after MAD therapy, but were not different between two groups. Epworth sleepiness scale scores were not improved after MAD therapy. Percentage of REM sleep was increased after MAD therapy but was not different between two groups. Conclusions: MAD therapy was more effective in not-REM-related OSA than REM-related OSA and REM dependency can be a predictive factor of treatment outcome of oral appliance for OSA patients.

• Journal of Oral Medicine and Pain
• /
• v.42 no.1
• /
• pp.1-7
• /
• 2017

Purpose: The aims of this study were to evaluate the clinical characteristics and polysomnographic results of patients visited the Seoul National University Dental Hospital (SNUDH) and to suggest guidelines for the management of sleep disordered-breathing patients in a dental clinic. Methods: Five hundred sixty-two patients who visited the Snoring and Sleep Apnea Clinic of SNUDH were evaluated for clinical characteristics including associated comorbidities, age, gender, body mass index (BMI), neck circumference, and daytime sleepiness and among them 217 patients were performed nocturnal polysomnography for evaluating respiratory disturbance index, apnea-hypopnea index (AHI), oxygen saturation levels, and sleep stages. The associations among clinical characteristics, sleep parameters, and positional and rapid eye movement (REM) dependencies of the patients were analyzed. Results: The most common co-morbidities of the patients were cardiovascular (30.2%), endocrine (10.8%), and respiratory diseases (7.9%). Age (${\beta}=0.394$), total AHI (${\beta}=0.223$), and lowest $O_2$ saturation levels (${\beta}=0.205$) were significantly associated with the number of co-morbidities in patients with obstructive sleep apnea (OSA). Mean $O_2$ saturation was not significantly associated with number of co-morbidities. Non-positional OSA patients had higher BMI, longer neck circumferences, more severe AHI values, and lower mean and lowest $O_2$ saturation levels compared to positional OSA patients. Not-REM-related patients were older and had more severe AHI values compared to REM-related patients. Not-REM-related patients have longer duration of stage I sleep and shorter stage II, III, and REM sleep than REM-related patients. There were no significant differences in each sleep stage between positional and non-positional patients. Neck circumference, positional dependency, REM dependency, and percentage of supine position were significantly associated with severity of OSA. Conclusions: Age, total AHI, and lowest $O_2$ saturation level were significantly associated with the number of co-morbidities in patients with OSA. Neck circumference, positional dependency, REM dependency, and percentage of supine position were significantly associated with severity of OSA.

• Korean Journal of Clinical Laboratory Science
• /
• v.51 no.1
• /
• pp.119-123
• /
• 2019

Obstructive sleep apnea (OSA) is a sleep disorder with no breathing symptoms due to repetitive upper airway resistance. OSA is a disease that can have significant effects on the cerebral cardiovascular system. Active treatment is needed to prevent these complications. The use of continuous positive airway pressure (CPAP), the standard therapy of OSA, has comparative therapeutic effects. On the other hand, there is no comparison report of the polysomnography (PSG) results before and after CPAP therapy without using a mask. This paper reports a patient who was diagnosed as OSA and used CPAP every night for more than 2 years. The patient showed a decrease in the apnea-hypopnea index from 64.7/h to 12.9/h. In addition, other sleep-related indicators improved significantly. The daily use of CPAP as a treatment for OSA for more than 2 years may improve the PSG results. Constant follow up of PSG will be needed to adjust the appropriate CPAP pressure to patients because there might be a change in the Apnea-Hypopnea Index and other sleep-related indicators for constant CPAP users for at least 2 years.

• Korean Journal of Clinical Laboratory Science
• /
• v.53 no.4
• /
• pp.285-295
• /
• 2021

Sleep plays an important role in maintaining overall human health. There is increasing interest regarding the impact of sleep related disorders on metabolic diseases. Obstructive sleep apnea (OSA) is a common health problem, and in the last decade, the emergence of increasing obesity rates has further led to a remarkable increase in the prevalence of OSA, along with more prominent metabolic diseases. Obesity is the strongest risk factor for OSA. However, OSA is also known to cause obesity, suggesting an interaction between OSA and obesity. Although the underlying mechanisms leading to OSA-induced metabolic diseases are probably multi-factorial and are yet to be fully elucidated, the activation of inflammation and oxidative stress and the dysregulation of appetite-regulating hormones have emerged as important pathophysiological components of metabolic dysfunction and obesity observed in patients with OSA. Here, we will review the current state of research regarding the association of OSA with metabolic diseases and the possible pathophysiological mechanisms by which OSA could lead to such diseases. This will enhance our understanding of the potential interactions between OSA and obesity and between OSA and metabolic dysfunction.

• Sleep Medicine and Psychophysiology
• /
• v.8 no.1
• /
• pp.22-29
• /
• 2001

Objectives: Obstructive sleep apnea syndrome (OSA) is a moderately prevalent disorder. Even though much progress has been made in the diagnosis of this disorder, the cost-effectiveness of nocturnal polysomnography is undertermined and physicians and patients are still hesitant to undergo this procedure. The authors wanted to see the validity of chin press/tongue curl maneuver in estimating the severity of OSA which is easy to measure and was originally proposed by Simmons etc. by looking at the correlations between this score and the conventional respiratory disturbance indices. Methods: Forty-three sleep-related breathing disorder patients (28 OSA patients and 15 upper airway resistance syndrome (UARS) patients) who underwent investigation for posssible OSA were studied. Two conventional indices of OSA (apnea/hypopnea index (AHI) and oxygen saturation dip rate (SaO2 dips)), four other sleep variables (lowest SaO2, % of time with SaO2<90% (%SaO2 <90), % of sleep stage 1, mean length of SaO2 dips) and the score of Epworth sleepiness scale (ESS) were compared with the chin press score (CPS) which was newly revised by the author and ranges from 0 to 6. Results: The age of subjects was $45.95{\pm}12.47$ (range 14-76) and their average BMI was $25.98{\pm}3.61$ (range 19.65-37.64). There were no significant differences in age, sex and BMI except repiratory disturbance indices and ESS (p<0.05) between OSA and UARS group. Grouped median CPS of the all subjects was 4.14 (range 1-6). There was a remarkable relationship between CPS and diagnosis category (Likelihood Ratio $X^2$ test; $X^2$=17.41, df=5, p=0.004) and measures of association (Somers' $d=0.65{\pm}0.12$, t=4.83, p=0.000) indicated that CPS increased when the diagnosis changed from UARS to OSA. Spearman's rank correlations between CPS and SaO2 dips (R=0.83), between CPS and AHI (R=0.77) were good (p<0.001). Other variables except mean length of SaO2 dips showed good correlations with CPS as well (p<0.05). Regression analysis indicated that when CPS is 3 there is a provability of 0.35 to have AHI of less than 5. Conclusion: Chin press scores that can be measured easily is well correlation with the conventional sleep apnea indices. They may therefore provide a useful guide in diagnosing obstructive sleep apnea synrome.