Towards Investigating Global Warming Impact on Human Health Using Derivatives of Photoplethysmogram Signals

Evaluation of CMIP5 Climate Models Using Historical Surface Air Temperatures in Central Asia

Using historical data compiled by the Climate Research Unit, spatial and temporal analysis, trend analysis, empirical orthogonal function (EOF) analysis, and Taylor diagram analysis were applied to test the ability of 24 Coupled Model Intercomparison Project Phase 5 (CMIP5) climate models to accurately simulate the annual mean surface air temperature in central Asia from the perspective of the average climate state and climate variability. Results show that each model can reasonably capture the spatial distribution characteristics of the surface air temperature in central Asia but cannot accurately describe the regional details of climate change impacts. Some of the studied models, including CNRM-CM5, GFDL-CM3, and GISS-E2-H, could better simulate the high- and low-value centers and the contour distribution of the surface air temperature. Taylor diagram analysis showed that the root mean square errors of all models were less than 3, the standard deviations were between 8.36 and 13.45, and the spatial correlation coefficients were greater than 0.96. EOF analysis showed that the multi-model ensemble can accurately reproduce the surface air temperature characteristics in central Asia from 1901 to 2005, including the rising periods and the fluctuations of the north and south inversion phases. Overall, this study provides a valuable reference for future climate prediction studies in central Asia.

Photoplethysmography and Deep Learning: Enhancing Hypertension Risk Stratification

Blood pressure is a basic physiological parameter in the cardiovascular circulatory system. Long-term abnormal blood pressure will lead to various cardiovascular diseases, making the early detection and assessment of hypertension profoundly significant for the prevention and treatment of cardiovascular diseases. In this paper, we investigate whether or not deep learning can provide better results for hypertension risk stratification when compared to the classical signal processing and feature extraction methods. We tested a deep learning method for the classification and evaluation of hypertension using photoplethysmography (PPG) signals based on the continuous wavelet transform (using Morse) and pretrained convolutional neural network (using GoogLeNet). We collected 121 data recordings from the Multiparameter Intelligent Monitoring in Intensive Care (MIMIC) Database, each containing arterial blood pressure (ABP) and photoplethysmography (PPG) signals. The ABP signals were utilized to extract blood pressure category labels, and the PPG signals were used to train and test the model. According to the seventh report of the Joint National Committee, blood pressure levels are categorized as normotension (NT), prehypertension (PHT), and hypertension (HT). For the early diagnosis and assessment of HT, the timely detection of PHT and the accurate diagnosis of HT are significant. Therefore, three HT classification trials were set: NT vs. PHT, NT vs. HT, and (NT + PHT) vs. HT. The F-scores of these three classification trials were 80.52%, 92.55%, and 82.95%, respectively. The tested deep method achieved higher accuracy for hypertension risk stratification when compared to the classical signal processing and feature extraction method. Additionally, the method achieved comparable results to another approach that requires electrocardiogram and PPG signals.

An optimal filter for short photoplethysmogram signals

A photoplethysmogram (PPG) contains a wealth of cardiovascular system information, and with the development of wearable technology, it has become the basic technique for evaluating cardiovascular health and detecting diseases. However, due to the varying environments in which wearable devices are used and, consequently, their varying susceptibility to noise interference, effective processing of PPG signals is challenging. Thus, the aim of this study was to determine the optimal filter and filter order to be used for PPG signal processing to make the systolic and diastolic waves more salient in the filtered PPG signal using the skewness quality index. Nine types of filters with 10 different orders were used to filter 219 (2.1s) short PPG signals. The signals were divided into three categories by PPG experts according to their noise levels: excellent, acceptable, or unfit. Results show that the Chebyshev II filter can improve the PPG signal quality more effectively than other types of filters and that the optimal order for the Chebyshev II filter is the 4^th order.

Optimal Signal Quality Index for Photoplethysmogram Signals

A photoplethysmogram (PPG) is a noninvasive circulatory signal related to the pulsatile volume of blood in tissue and is typically collected by pulse oximeters. PPG signals collected via mobile devices are prone to artifacts that negatively impact measurement accuracy, which can lead to a significant number of misleading diagnoses. Given the rapidly increased use of mobile devices to collect PPG signals, developing an optimal signal quality index (SQI) is essential to classify the signal quality from these devices. Eight SQIs were developed and tested based on: perfusion, kurtosis, skewness, relative power, non-stationarity, zero crossing, entropy, and the matching of systolic wave detectors. Two independent annotators annotated all PPG data (106 recordings, 60 s each) and a third expert conducted the adjudication of differences. The independent annotators labeled each PPG signal with one of the following labels: excellent, acceptable or unfit for diagnosis. All indices were compared using Mahalanobis distance, linear discriminant analysis, quadratic discriminant analysis, and support vector machine with leave-one-out cross-validation. The skewness index outperformed the other seven indices in differentiating between excellent PPG and acceptable, acceptable combined with unfit, and unfit recordings, with overall F1 scores of 86.0%, 87.2%, and 79.1%, respectively.