USE OF PULSE TRANSIT TIME AS A MEASURE OF AUTONOMIC AROUSALS IN PATIENTS WITH OBSTRUCTIVE SLEEP APNEA

Objective To evaluate the feasibility of pulse transit time (PTT) arousals as an index of sleep fragmentation in patients with obstructive sleep apnea hypopnea syndrome (OSAHS). Methods Individuals referred for evaluation of possible OSAHS underwent overnight polysomnography (PSG). Three conventional indices of sleep fragmentation [electroencephalography (EEG) arousals, apnea/hypopnea index (AHI), oxygen desaturation index (ODI)], PTT arousals, and Epworth sleepiness scale (ESS) were compared. Results PTT arousals were positively correlated with EEG arousals (r= 0.746, P<0.001), AHI (r= 0.786, P<0.001), and ODI (r= 0.665, P<0.001), respectively. But, both PTT arousals and EEG arousals had no correlation with ESS (r= 0.432, P=0.201; r= 0.196, P=0.591, respectively). Conclusion PTT arousals are correlated well with other standard measures estimating severity of OSAHS and potentially a non-invasive marker with which to measure the sleep fragmentation in patients with OSAHS.

Mechanism of Magnetic Pulse Wave Signal for Blood Pressure Measurement

Continuous non-invasive blood pressure (BP) measurement can be realized by using pulse transit time (PTT) based on electrocardiogram (ECG) and pulse wave signal. Modulated magnetic signature of blood (MMSB) is a promising approach to obtain PTT. The origin of MMSB is critical to establish the relationship between MMSB and BP. In this paper, two possible origins of MMSB, blood disturbance mechanism and angular variation mechanism, are analyzed and verified through three control experi-ments under different conditions. The influence of blood velocity alteration and blood volume alteration on magnetic field is investigated though blood flow simulation sys-tem. It is found that MMSB comes mainly from the periodic blood flow while the per-turbation caused by angular variation between sensitive axis of the magnetic sensor and geomagnetic field can be neglected. As to blood disturbance mechanism, the change of blood volume plays a decisive role while the effect of blood velocity altera-tion is negligible.

Machine Learning for Detecting Blood Transfusion Needs Using Biosignals

Adequate oxygen in red blood cells carrying through the body to the heart and brain is important to maintain life.For those patients requiring blood,blood transfusion is a common procedure in which donated blood or blood components are given through an intravenous line.However,detecting the need for blood transfusion is time-consuming and sometimes not easily diagnosed,such as internal bleeding.This study considered physiological signals such as electrocardiogram(ECG),photoplethysmogram(PPG),blood pressure,oxygen saturation(SpO2),and respiration,and proposed the machine learning model to detect the need for blood transfusion accurately.For the model,this study extracted 14 features from the physiological signals and used an ensemble approach combining extreme gradient boosting and random forest.The model was evaluated by a stratified five-fold crossvalidation:the detection accuracy and area under the receiver operating characteristics were 92.7%and 0.977,respectively.