Convolutional neural network based on photoplethysmography signals for sleep apnea syndrome detection.

Introduction: The current method of monitoring sleep disorders is complex, time-consuming, and uncomfortable, although it can provide scientifc guidance to ensure worldwide sleep quality. This study aims to seek a comfortable and convenient method for identifying sleep apnea syndrome. Methods: In this work, a one-dimensional convolutional neural network model was established. To classify this condition, the model was trained with the photoplethysmographic (PPG) signals of 20 healthy people and 39 sleep apnea syndrome (SAS) patients, and the influence of noise on the model was tested by anti-interference experiments. Results and Discussion: The results showed that the accuracy of the model for SAS classifcation exceeds 90%, and it has some antiinterference ability. This paper provides a SAS detection method based on PPG signals, which is helpful for portable wearable detection.

Variation of peripheral pulse transit time with internal vascular pressure changes induced by arm movement.

Pulse transit time (PTT) and blood pressure (BP) are widely used to quantify arterial characteristics. Arm position influences arterial BP and peripheral PTT. This study aims to quantify the relationship between PTT changes with internal vascular pressure variations induced by the arm moving. With left arm at horizontal position as reference and the right arm moving from 90 to 45, 0, -45, and -90° respectively, PTT difference was calculated by the difference of the pulse foot between right arm and left arm within the same heartbeat. The change in the BP was calculated from the gravitational effect with the measured arm length. Our results showed that the change in PTT with arm elevating is more obvious than that with arm lowering, indicating the different relationship between PTT changes due to the internal BP changes. This can help in understanding the inherent physiological/pathological mechanism of cardiovascular system.

Classification of heart sounds based on quality assessment and wavelet scattering transform.

Automatic classification of heart sound plays an important role in the diagnosis of cardiovascular diseases. In this study, a heart sound sample classification method based on quality assessment and wavelet scattering transform was proposed. First, the ratio of zero crossings (RZC) and the root mean square of successive differences (RMSSD) were used for assessing the quality of heart sound signal. The first signal segment conforming to the threshold standard was selected as the current sample for the continuous heart sound signal. Using the wavelet scattering transform, the wavelet scattering coefficients were expanded according to the wavelet scale dimension, to obtain the features. Support vector machine (SVM) was used for classification, and the classification results for the samples were obtained using the wavelet scale dimension voting approach. The effects of RZC and RMSSD on the results are discussed in detail. On the database of PhysioNet Computing in Cardiology Challenge 2016 (CinC 2016), the proposed method yields 92.23% accuracy (Acc), 96.62% sensitivity (Se), 90.65% specificity (Sp), and 93.64% measure of accuracy (Macc). The results show that the proposed method can effectively classify normal and abnormal heart sound samples with high accuracy.

Performance Analysis of Ten Common QRS Detectors on Different ECG Application Cases.

A systematical evaluation work was performed on ten widely used and high-efficient QRS detection algorithms in this study, aiming at verifying their performances and usefulness in different application situations. Four experiments were carried on six internationally recognized databases. Firstly, in the test of high-quality ECG database versus low-quality ECG database, for high signal quality database, all ten QRS detection algorithms had very high detection accuracy (F1 >99%), whereas the F1 results decrease significantly for the poor signal-quality ECG signals (all <80%). Secondly, in the test of normal ECG database versus arrhythmic ECG database, all ten QRS detection algorithms had good F1 results for these two databases (all >95% except RS slope algorithm with 94.24% on normal ECG database and 94.44% on arrhythmia database). Thirdly, for the paced rhythm ECG database, all ten algorithms were immune to the paced beats (>94%) except the RS slope method, which only output a low F1 result of 78.99%. At last, the detection accuracies had obvious decreases when dealing with the dynamic telehealth ECG signals (all <80%) except OKB algorithm with 80.43%. Furthermore, the time costs from analyzing a 10 s ECG segment were given as the quantitative index of the computational complexity. All ten algorithms had high numerical efficiency (all <4 ms) except RS slope (94.07 ms) and sixth power algorithms (8.25 ms). And OKB algorithm had the highest numerical efficiency (1.54 ms).

Changes in the bilateral pulse transit time difference with a moving arm.

BACKGROUND: Changes of pulse transit time (PTT) induced by arm position were studied for unilateral arm. However, consistency of the PTT changes was not validated for both arm sides. OBJECTIVE: We aimed to quantify the PTT changes between horizontal and non-horizontal positions from right arm and left arm in order to explore the consistency of both arms. METHODS: Twenty-four normal subjects aged between 21 and 50 (14 male and 10 female) years were enrolled. Left and right radial artery pulses were synchronously recorded from 24 healthy subjects with one arm (left or right) at five angles (90∘, 45∘, 0∘, -45∘ and -90∘) and the other arm at the horizontal level (0∘) for reference. RESULTS: The overall mean PTT changes at the five angles (from 90∘ to -90∘) in the left arm (right as reference) were 16.1, 12.3, -0.5, -2.5 and -2.6 ms, respectively, and in the right arm (left as reference) were 18.0, 12.6, 1.6, -1.6 and -2.0 ms, respectively. CONCLUSIONS: Obvious differences were not found in the PTT changes between the two arms (left arm moving or right arm moving) under each of the five different positions (all P> 0.05).

Possible role of toll-like receptor 4 in acute pancreatitis.

Because the mechanism underlying the development of acute pancreatitis (AP) has not yet been fully clarified, it has been a hot but difficult topic in basic and clinical research for a long time. Currently, the dominant hypothesis for the pathogenesis of AP is that it is a disease of self-digestive acute chemical inflammation induced by trypsin activation. As proteins to trigger the inflammatory response cascade, Toll-like receptors (TLRs), especially TLR4, provide a new clue for studying the pathogenesis of AP from the source. Some studies have found that when TLR4 is activated by certain factors, it can amplify an inflammatory effect and aggravate the body's inflammatory response through a series of signal transduction. Toll-like receptor 4 may play an important role in the synthesis and release of proinflammatory cytokines, and the up-regulation of the TLR4 gene may be related with the development and progression of multiple organ injury during AP. As the "gate" of inflammatory response, TLR4 may be closely associated with the development and progression of multiple organ injury during AP. Understanding the roles of TLR4 in AP will help to further clarify the pathogenesis of AP and to search a new target for the treatment of AP.

Pathological changes at early stage of multiple organ injury in a rat model of severe acute pancreatitis.

BACKGROUND: Severe acute pancreatitis (SAP) is a commonly seen acute abdominal syndrome characterized by sudden onset, rapid progression and high mortality rate. The damage in peripheral organs may be more severe than that in the pancreas, and can even lead to multiple organ dysfunction. It is critical to recognize early pathological changes in multiple organs. This study aimed to assess the early pathological features of damaged organs in a rat model of SAP. METHODS: Thirty clean grade healthy male Sprague-Dawley rats weighing 250-300 g were randomly divided into a model control group (n=15) and a sham-operated group (n=15). The SAP rat model was induced by sodium taurocholate. Samples of blood and from multiple organs were collected 3 hours after operation. We assessed the levels of IL-6, TNF-alpha, PLA2, NO, ET-1, MDA, amylases and endotoxin in blood and observed the early pathological changes in multiple damaged organs. RESULTS: Levels of IL-6, TNF-alpha, PLA2, NO, ET-1 and MDA in serum and of amylase and endotoxin in plasma of the model control group rats were significantly higher than those of the sham-operated group (P<0.01). Different degrees of pathological change were observed in multiple damaged organs. CONCLUSION: Multiple organ injury may occur at the early stage of SAP in rats.

Effect of baicalin on inflammatory mediator levels and microcirculation disturbance in rats with severe acute pancreatitis.

OBJECTIVES: To investigate the effect of bacailin on inflammatory mediators and microcirculation disturbance in severe acute pancreatitis (SAP) rats and explore its therapeutic mechanism. METHODS: The rats were randomly divided into SAP group, baicalin-treated group and sham operated group. At 3, 6, and 12 hours after operation, we examined the mortality rate of rats, ascites volume, and pancreatic pathological changes in each group and determined the contents of inflammatory mediators in blood as well as the changes in blood viscosity. RESULTS: Compared with SAP group, treatment with baicalin is able to improve the pathological damage of the pancreas, reduce the contents of multiple inflammatory mediators in blood, decrease the amount of ascitic fluid, and reduce the mortality rates of SAP rats. The low-shear whole blood viscosity in baicalin-treated group (at 3 hours) as well as the high-shear and low-shear whole blood viscosity in baicalin-treated group (at 12 hours) were significantly lower than that in SAP group. CONCLUSIONS: Baicalin has good prospects in the treatment for SAP because it can exert therapeutic effects on this disease through inhibiting the production of inflammatory mediators, decreasing blood viscosity, improving microcirculation, and mitigating the pathological damage of the pancreas.

Icam-1 and acute pancreatitis complicated by acute lung injury.

One of the most common complications of acute pancreatitis is acute lung injury, during which intercellular adhesion molecule-1 (ICAM-1) plays an important role by participating in leukocyte adhesion and activation as well as by inducing the "cascade effect" of inflammatory mediators, pulmonary microcirculation dysfunction and even acute respiratory distress syndrome, multiple organ failure or death. Although it is generally believed that the modulatory mechanism of ICAM-1 during this process is associated with the activation of nuclear transcription factor kappa B which is mediated by IL-1, IL-6, IL-18 and oxygen free radical, etc., further studies are still required to clarify it. Since the upregulation of ICAM-1 expression in the lung during acute lung injury is one of main pathogeneses, the early detection of the ICAM-1 expression level may contribute to the prevention and treatment of acute lung injury. Moreover, reducing pulmonary ICAM-1 expression levels through treatment with anti-ICAM-1 monoclonal antibody (aICAM-1) and antagonists of the neurokinin 1 receptor, etc., should have a positive effect on protecting the lungs during acute pancreatitis. This review aims to further clarify the relationship between ICAM-1 and acute pancreatitis complicated by acute lung injury, and therefore provides a theoretical basis for the formulation of corresponding therapeutic measures in clinical practice for acute pancreatitis.

Preparation method of an ideal model of multiple organ injury of rat with severe acute pancreatitis.

AIM: To establish an ideal model of multiple organ injury of rats with severe acute pancreatitis (SAP). METHODS: SAP models were induced by retrograde injection of 0.1 mL/100 g 3.5% sodium taurocholate into the biliopancreatic duct of Sprague-Dawley rats. The plasma and samples of multiple organ tissues of rats were collected at 3, 6 and 12 h after modeling. The ascites volume, ascites/body weight ratio, and contents of amylase, endotoxin, endothelin-1 (ET-1), nitrogen monoxidum (NO), phospholipase A(2) (PLA(2)), tumor necrosis factor-alpha (TNF-alpha), interleukin-6 (IL-6) in plasma were determined. The histological changes of multiple organs were observed under light microscope. RESULTS: The ascites volume, ascites/body weight ratio, and contents of various inflammatory mediators in blood were higher in the model group than in the sham operation group at all time points [2.38 (1.10), 2.58 (0.70), 2.54 (0.71) vs 0.20 (0.04), 0.30 (0.30), 0.22 (0.10) at 3, 6 and 12 h in ascites/body weight ratio; 1582 (284), 1769 (362), 1618 (302) (U/L) vs 5303 (1373), 6276 (1029), 7538 (2934) (U/L) at 3, 6 and 12 h in Amylase; 0.016 (0.005), 0.016 (0.010), 0.014 (0.015) (EU/mL) vs 0.053 (0.029), 0.059 (0.037), 0.060 (0.022) (EU/mL) at 3, 6 and 12 h in Endotoxin; 3.900 (3.200), 4.000 (1.700), 5.300 (3.000) (ng/L) vs 41.438 (37.721), 92.151 (23.119), 65.016 (26.806) (ng/L) at 3, 6 and 12 h in TNF-alpha, all P < 0.01]. Visible congestion, edema and lamellar necrosis and massive leukocytic infiltration were found in the pancreas of rats of model group. There were also pathological changes of lung, liver, kidney, spleen, ileum, lymphonode, thymus, myocardium and brain. CONCLUSION: This rat model features reliability, convenience and a high achievement ratio. Complicated with multiple organ injury, it is an ideal animal model of SAP.