A5060803109- Obstructive Sleep Apnea Research
- Mineral Processing and Grinding
- Non-Invasive Vital Sign Monitoring
- EEG and Brain-Computer Interfaces
- Sleep and Wakefulness Research
- Balance, Gait, and Falls Prevention
- Rock Mechanics and Modeling
- Non-Destructive Testing Techniques
- Drilling and Well Engineering
- Context-Aware Activity Recognition Systems
- Fault Detection and Control Systems
Taiyuan University of Technology
2024
Soochow University
2024
MediaTek (Taiwan)
2018-2020
Many questionnaires or prediction models tried to identify patients with obstructive sleep apnea (OSA) prioritize study. However, the performance was not unified which related prevalence and definition of OSA, characteristics participants, feature selected. Therefore, present study proposed a novel model predict OSA minimal features. We collected clinical features polysomnographic parameters from 5,301 (mean age 47.5 ± 14.4 y/o, men 76.5%) referred for suspect [apnea-hypopnea index (AHI) ≥...
Abstract Introduction Excessive daytime sleepiness (EDS) is a common symptom that patients with obstructive sleep apnea (OSA) seek medical attention for. Prevalence ranged from 20% to 60%. Previous studies reported factors associated EDS included age, body mass index (BMI), depression, and OSA severity. In most studies, the sample size was small, participants having specific co-morbidities, definitions of heterogeneous. Moreover, association between anxiety, habitual pattern, has not been...
Abstract Introduction Obstructive sleep apnea (OSA) is a condition characterized by repeated episodes of partial or complete obstruction the respiratory passages during sleep. Traditional polysomnography (PSG) for OSA estimation bulky and time-consuming daily use. Therefore, this study aims to develop novel photoplethysmography (PPG) accelerometer based smart watch detection, in which high-performance low-complexity automated detection was embedded long-term in-home measurement. Methods The...
Traditional PSG for sleep staging is bulky real-life use, and manual scoring time-consuming expensive. Previous automated algorithms were constrained by expert knowledge have limited accuracy. Therefore, a simplified equipment with high-performance algorithm the rising demand. Artificial intelligence (AI) has shown to strong computational capability, widely being used. We developed novel AI method that can automatically learn distinguish single-channel EEG features from different stages....