Home-Use and Real-Time Sleep-Staging System Based on Eye Masks and Mobile Devices with a Deep Learning Model.

PURPOSE: Sleep is an important human activity. Comfortable sensing and accurate analysis in sleep monitoring is beneficial to many healthcare and medical applications. From 2020, owing to the COVID­19 pandemic that spreads between people when they come into close physical contact with one another, the willingness to go to hospital for receiving care has reduced; care-at-home is the trend in modern healthcare. Therefore, a home-use and real-time sleep-staging system is developed in this paper. METHODS: We developed and implemented a real-time sleep staging system that integrates a wearable eye mask for high-quality electroencephalogram/electrooculogram measurement and a mobile device with MobileNETV2 deep learning model for sleep-stage identification. In the experiments, 25 all-night recordings were acquired, 17 of which were used for training, and the remaining eight were used for testing. RESULTS: The averaged scoring agreements for the wake, light sleep, deep sleep, and rapid eye movement stages were 85.20%, 87.17%, 82.87%, and 89.30%, respectively, for our system compared with the manual scoring of PSG recordings. In addition, the mean absolute errors of four objective sleep measurements, including sleep efficiency, total sleep time, sleep onset time, and wake after sleep onset time were 1.68%, 7.56 min, 5.50 min, and 3.94 min, respectively. No significant differences were observed between the proposed system and manual PSG scoring in terms of the percentage of each stage and the objective sleep measurements. CONCLUSION: These experimental results demonstrate that our system provides high scoring agreements in sleep staging and unbiased sleep measurements owing to the use of EEG and EOG signals and powerful mobile computing based on deep learning networks. These results also suggest that our system is applicable for home-use real-time sleep monitoring.

Empirical Mode Decomposition and Monogenic Signal-Based Approach for Quantification of Myocardial Infarction From MR Images.

Quantification of myocardial infarction on late Gadolinium enhancement cardiovascular magnetic resonance (LGE-CMR) images into heterogeneous infarct periphery (or gray zone) and infarct core plays an important role in cardiac diagnosis, especially in identifying patients at high risk of cardiovascular mortality. However, quantification task is challenging due to noise corrupted in cardiac MR images, the contrast variation, and limited resolution of images. In this study, we propose a novel approach for automatic myocardial infarction quantification, termed DEMPOT, which consists of three key parts: Decomposition of image into intrinsic modes, monogenic phase performing on combined dominant modes, and multilevel Otsu thresholding on the phase. In particular, inspired by the Hilbert-Huang transform, we perform the multidimensional ensemble empirical mode decomposition and 2-D generalization of the Hilbert transform known as the Riesz transform on the MR image to obtain the monogenic phase that is robust to noise and contrast variation. Then, a two-stage algorithm using multilevel Otsu thresholding is accomplished on the monogenic phase to automatically quantify the myocardium into healthy, gray zone, and infarct core regions. Experiments on LGE-CMR images with myocardial infarction from 82 patients show the superior performance of the proposed approach in terms of reproducibility, robustness, and effectiveness.

Uniform Phase Empirical Mode Decomposition: An Optimal Hybridization of Masking Signal and Ensemble Approaches.

The empirical mode decomposition (EMD) is an established method for the time-frequency analysis of nonlinear and nonstationary signals. However, one major drawback of the EMD is the mode mixing effect. Many modifications have been made to resolve the mode mixing effect. In particular, disturbance-assisted EMDs, such as the noise-assisted EMD and the masking EMD, have been proposed to resolve this problem. These disturbance-assisted approaches have led to a better performance of the EMD in the analysis of real-world data sets, but they may also have two side effects: the mode splitting and residual noise effects. To minimize or eliminate the mode mixing effect while avoiding the two side effects of traditional disturbance-assisted EMDs, we propose an EMD-based algorithm assisted by sinusoidal functions with a designed uniform phase distribution with a comprehensive theoretical explanation for the substantial reduction of the mode splitting and the residual noise effects simultaneously. We examine the performance of the new method and compare it to those of other disturbance-assisted EMDs using synthetic signals. Finally numerical experiments with real-world examples are conducted to verify the performance of the proposed method.

On Holo-Hilbert spectral analysis: a full informational spectral representation for nonlinear and non-stationary data.

The Holo-Hilbert spectral analysis (HHSA) method is introduced to cure the deficiencies of traditional spectral analysis and to give a full informational representation of nonlinear and non-stationary data. It uses a nested empirical mode decomposition and Hilbert-Huang transform (HHT) approach to identify intrinsic amplitude and frequency modulations often present in nonlinear systems. Comparisons are first made with traditional spectrum analysis, which usually achieved its results through convolutional integral transforms based on additive expansions of an a priori determined basis, mostly under linear and stationary assumptions. Thus, for non-stationary processes, the best one could do historically was to use the time-frequency representations, in which the amplitude (or energy density) variation is still represented in terms of time. For nonlinear processes, the data can have both amplitude and frequency modulations (intra-mode and inter-mode) generated by two different mechanisms: linear additive or nonlinear multiplicative processes. As all existing spectral analysis methods are based on additive expansions, either a priori or adaptive, none of them could possibly represent the multiplicative processes. While the earlier adaptive HHT spectral analysis approach could accommodate the intra-wave nonlinearity quite remarkably, it remained that any inter-wave nonlinear multiplicative mechanisms that include cross-scale coupling and phase-lock modulations were left untreated. To resolve the multiplicative processes issue, additional dimensions in the spectrum result are needed to account for the variations in both the amplitude and frequency modulations simultaneously. HHSA accommodates all the processes: additive and multiplicative, intra-mode and inter-mode, stationary and non-stationary, linear and nonlinear interactions. The Holo prefix in HHSA denotes a multiple dimensional representation with both additive and multiplicative capabilities.

Quantifying Spasticity With Limited Swinging Cycles Using Pendulum Test Based on Phase Amplitude Coupling.

Parameters derived from the goniometer measures in the Pendulum test are insufficient in describing the function of abnormal muscle activity in the spasticity. To explore a quantitative evaluation of muscle activation-movement interaction, we propose a novel index based on phase amplitude coupling (PAC) analysis with the consideration of the relations between movement and surface electromyography (SEMG) activity among 22 hemiplegic stroke patients. To take off trend and noise, we use the empirical mode decomposition (EMD) to obtain intrinsic mode functions (IMFs) of the angular velocity due to its superior decomposing ability in nonlinear oscillations. Shannon entropy based on angular velocity (phase)-envelope of EMG (amplitude) distribution was calculated to demonstrate characteristics of the coupling between SEMG activity and joint movement. We also compare our results with those from traditional methods such as the normalized relaxation index derived from the Pendulum test and the mean root mean square (RMS) of the SEMG signals in the study. Our results show effective discrimination ability between spastic and nonaffected limbs using our method . This study indicates the feasibility of using the novel indices based on the PAC in evaluation the spasticity among the hemiplegic stroke patients with less than three swinging cycles.

Endocardial Remodeling in Heart Failure Patients with Impaired and Preserved Left Ventricular Systolic Function--A Magnetic Resonance Image Study.

Left ventricular (LV) trabeculation has been studied in certain forms of cardiomyopathy. However, the changes of LV endocardial trabeculation during the remodeling process leading to heart failure (HF) are unclear. Seventy-four patients with systolic heart failure (SHF), 65 with heart failure with preserved ejection fraction (HFpEF) and 61 without HF were prospectively enrolled. All subjects received magnetic resonance imaging (MRI) study including cine, T1 and late gadolinium enhancement (LGE) images. Trabecular-papillary muscle (TPM) mass, fractal dimension (FD) and extracellular volume (ECV) were derived. The results showed that TPM mass index was higher in patients with SHF than that in patients with HFpEF and non-HF. The TPM mass-LV mass ratio (TPMm/LVM) was higher in SHF group than that in HFpEF and non-HF. FD was not different among groups. The presence of LGE was inversely associated with TPM mass index and TPMm/LVM while the ECV were positively associated with TPMm/LVM. The FD was positively associated with LV chamber size. In conclusion, TPM increases in patients with SHF and are probably related to myocardial cell hypertrophy and fibrotic repair during remodeling. The FD increases with the dilatation of LV chamber but remain unchanged with the deterioration of LV function.

Novel application of a Wii remote to measure spasticity with the pendulum test: Proof of concept.

BACKGROUND: The pendulum test is a standard clinical test for quantifying the severity of spasticity. In the test, an electrogoniometer is typically used to measure the knee angular motion. The device is costly and difficult to set up such that the pendulum test is normally time consuming. OBJECTIVE: The goal of this study is to determine whether a Nintendo Wii remote can replace the electrogroniometer for reliable assessment of the angular motion of the knee in the pendulum test. METHODS: The pendulum test was performed in three control participants and 13 hemiplegic stroke patients using both a Wii remote and an electrogoniometer. The correlation coefficient and the Bland-Altman difference plot were used to compare the results obtained from the two devices. The Wilcoxon signed-rank test was used to compare the difference between hemiplegia-affected and nonaffected sides in the hemiplegic stroke patients. RESULTS: There was a fair to strong correlation between measurements from the Wii remote and the electrogoniometer (0.513

A Novel Application of Multiscale Entropy in Electroencephalography to Predict the Efficacy of Acetylcholinesterase Inhibitor in Alzheimer's Disease.

Alzheimer's disease (AD) is the most common form of dementia. According to one hypothesis, AD is caused by the reduced synthesis of the neurotransmitter acetylcholine. Therefore, acetylcholinesterase (AChE) inhibitors are considered to be an effective therapy. For clinicians, however, AChE inhibitors are not a predictable treatment for individual patients. We aimed to disclose the difference by biosignal processing. In this study, we used multiscale entropy (MSE) analysis, which can disclose the embedded information in different time scales, in electroencephalography (EEG), in an attempt to predict the efficacy of AChE inhibitors. Seventeen newly diagnosed AD patients were enrolled, with an initial minimental state examination (MMSE) score of 18.8 ± 4.5. After 12 months of AChE inhibitor therapy, 7 patients were responsive and 10 patients were nonresponsive. The major difference between these two groups is Slope 2 (MSE6 to 20). The area below the receiver operating characteristic (ROC) curve of Slope 2 is 0.871 (95% CI = 0.69-1). The sensitivity is 85.7% and the specificity is 60%, whereas the cut-off value of Slope 2 is -0.024. Therefore, MSE analysis of EEG signals, especially Slope 2, provides a potential tool for predicting the efficacy of AChE inhibitors prior to therapy.

A new method to derive fetal heart rate from maternal abdominal electrocardiogram: monitoring fetal heart rate during cesarean section.

BACKGROUND: Monitoring of fetal heart rate (FHR) is important during labor since it is a sensitive marker to obtain significant information about fetal condition. To take immediate response during cesarean section (CS), we noninvasively derive FHR from maternal abdominal ECG. METHODS: We recruited 17 pregnant women delivered by elective cesarean section, with abdominal ECG obtained before and during the entire CS. First, a QRS-template is created by averaging all the maternal ECG heart beats. Then, Hilbert transform was applied to QRS-template to generate the other basis which is orthogonal to the QRS-template. Second, maternal QRS, P and T waves were adaptively subtracted from the composited ECG. Third, Gabor transformation was applied to obtain time-frequency spectrogram of FHR. Heart rate variability (HRV) parameters including standard deviation of normal-to-normal intervals (SDNN), 0V, 1V, 2V derived from symbolic dynamics of HRV and SD1, SD2 derived from Poincareé plot. Three emphasized stages includes: (1) before anesthesia, (2) 5 minutes after anesthesia and (3) 5 minutes before CS delivery. RESULTS: FHRs were successfully derived from all maternal abdominal ECGs. FHR increased 5 minutes after anesthesia and 5 minutes before delivery. As for HRV parameters, SDNN increased both 5 minutes after anesthesia and 5 minutes before delivery (21.30±9.05 vs. 13.01±6.89, P < 0.001 and 22.88±12.01 vs. 13.01±6.89, P < 0.05). SD1 did not change during anesthesia, while SD2 increased significantly 5 minutes after anesthesia (27.92±12.28 vs. 16.18±10.01, P < 0.001) and both SD2 and 0V percentage increased significantly 5 minutes before delivery (30.54±15.88 vs. 16.18±10.01, P < 0.05; 0.39±0.14 vs. 0.30±0.13, P < 0.05). CONCLUSIONS: We developed a novel method to automatically derive FHR from maternal abdominal ECGs and proved that it is feasible during CS.

Synchronized imaging and acoustic analysis of the upper airway in patients with sleep-disordered breathing.

Progressive narrowing of the upper airway increases airflow resistance and can produce snoring sounds and apnea/hypopnea events associated with sleep-disordered breathing due to airway collapse. Recent studies have shown that acoustic properties during snoring can be altered with anatomic changes at the site of obstruction. To evaluate the instantaneous association between acoustic features of snoring and the anatomic sites of obstruction, a novel method was developed and applied in nine patients to extract the snoring sounds during sleep while performing dynamic magnetic resonance imaging (MRI). The degree of airway narrowing during the snoring events was then quantified by the collapse index (ratio of airway diameter preceding and during the events) and correlated with the synchronized acoustic features. A total of 201 snoring events (102 pure retropalatal and 99 combined retropalatal and retroglossal events) were recorded, and the collapse index as well as the soft tissue vibration time were significantly different between pure retropalatal (collapse index, 2 ± 11%; vibration time, 0.2 ± 0.3 s) and combined (retropalatal and retroglossal) snores (collapse index, 13 ± 7% [P ≤ 0.0001]; vibration time, 1.2 ± 0.7 s [P ≤ 0.0001]). The synchronized dynamic MRI and acoustic recordings successfully characterized the sites of obstruction and established the dynamic relationship between the anatomic site of obstruction and snoring acoustics.

Fast computation of sample entropy and approximate entropy in biomedicine.

Both sample entropy and approximate entropy are measurements of complexity. The two methods have received a great deal of attention in the last few years, and have been successfully verified and applied to biomedical applications and many others. However, the algorithms proposed in the literature require O(N(2)) execution time, which is not fast enough for online applications and for applications with long data sets. To accelerate computation, the authors of the present paper have developed a new algorithm that reduces the computational time to O(N(3/2))) using O(N) storage. As biomedical data are often measured with integer-type data, the computation time can be further reduced to O(N) using O(N) storage. The execution times of the experimental results with ECG, EEG, RR, and DNA signals show a significant improvement of more than 100 times when compared with the conventional O(N(2)) method for N=80,000 (N=length of the signal). Furthermore, an adaptive version of the new algorithm has been developed to speed up the computation for short data length. Experimental results show an improvement of more than 10 times when compared with the conventional method for N>4000.