Deep Learning-Based Stroke Disease Prediction System Using Real-Time Bio Signals.

The emergence of an aging society is inevitable due to the continued increases in life expectancy and decreases in birth rate. These social changes require new smart healthcare services for use in daily life, and COVID-19 has also led to a contactless trend necessitating more non-face-to-face health services. Due to the improvements that have been achieved in healthcare technologies, an increasing number of studies have attempted to predict and analyze certain diseases in advance. Research on stroke diseases is actively underway, particularly with the aging population. Stroke, which is fatal to the elderly, is a disease that requires continuous medical observation and monitoring, as its recurrence rate and mortality rate are very high. Most studies examining stroke disease to date have used MRI or CT images for simple classification. This clinical approach (imaging) is expensive and time-consuming while requiring bulky equipment. Recently, there has been increasing interest in using non-invasive measurable EEGs to compensate for these shortcomings. However, the prediction algorithms and processing procedures are both time-consuming because the raw data needs to be separated before the specific attributes can be obtained. Therefore, in this paper, we propose a new methodology that allows for the immediate application of deep learning models on raw EEG data without using the frequency properties of EEG. This proposed deep learning-based stroke disease prediction model was developed and trained with data collected from real-time EEG sensors. We implemented and compared different deep-learning models (LSTM, Bidirectional LSTM, CNN-LSTM, and CNN-Bidirectional LSTM) that are specialized in time series data classification and prediction. The experimental results confirmed that the raw EEG data, when wielded by the CNN-bidirectional LSTM model, can predict stroke with 94.0% accuracy with low FPR (6.0%) and FNR (5.7%), thus showing high confidence in our system. These experimental results demonstrate the feasibility of non-invasive methods that can easily measure brain waves alone to predict and monitor stroke diseases in real time during daily life. These findings are expected to lead to significant improvements for early stroke detection with reduced cost and discomfort compared to other measuring techniques.

The Severity of Sleep Disordered Breathing Induces Different Decrease in the Oxygen Saturation During Rapid Eye Movement and Non-Rapid Eye Movement Sleep.

OBJECTIVE: To investigate how differences in oxygen saturation between non-REM (NREM) and REM sleep in patients according to the severity of sleep apnea. METHODS: We studied 396 male patients diagnosed with simple snoring or obstructive sleep apnea syndrome (OSAS) on nocturnal polysomnography. Patients were divided into groups by the OSAS severity. We compared the average oxygen saturation between REM and NREM sleep in each group. RESULTS: In the simple snoring group, average oxygen saturation was significantly greater during REM than during NREM sleep. In the severe OSA group alone, average oxygen saturation was greater in NREM than in REM sleep. The difference of NREM-REM average oxygen saturation correlated significantly with AHI in the severe OSA group. CONCLUSION: More severe hypoxemia was seen in REM than NREM sleep in the severe OSAS group. The differential oxygen decrease between REM and NREM sleep is likely due to the differentially occurring sleep breathing events in each sleep stage according to the SDB severity. The more AHI increases in the severe OSAS patients, the more prominent the hypoxemia of REM sleep compared with NREM sleep is likely to appear. This suggests that the pressure of continuous positive airway pressure should be increased to control the hypoxemia of REM sleep in extremely severe OSAS.

The relationship between visceral adiposity and cognitive performance in older adults.

BACKGROUND: a direct association between visceral adiposity on abdominal computed tomography (CT) and cognitive performance has not been reported. OBJECTIVES: to investigate the associations between total and regional adiposity measured with abdominal CT, and cognitive performance in elderly persons and to explore their modification by age. DESIGN: cross-sectional study. SETTING: a health promotion centre of a tertiary university hospital. SUBJECTS: two-hundred and fifty individuals aged 60 years and above who underwent anthropometric measurements, abdominal CT and cognitive testing. METHODS: adiposity measures included body mass index (BMI), waist circumference and visceral and subcutaneous adiposity by abdominal CT. Poor cognitive performance was defined as Mini-Mental State Examination score being at or below 1 SD of age, sex and education-normative values. RESULTS: in multivariate logistic regression analyses obesity [odds ratio (OR) 2.61, 95% confidence interval (CI)=1.21-6.01, P=0.015] and being in the top tertile of the visceral adiposity area (OR: 2.58, 95% CI=1.001-6.62, P=0.045) were associated with poor cognitive performance in subjects younger than 70 years, but not in those 70 years and older. CONCLUSION: high adiposity, particularly visceral adiposity, was associated with poor cognitive functioning in younger elderly persons.