•Proposing a methodology for the classification of heart sounds based on convolutional neural network and bi-directional long short-term memory (CNN-BiLSTM) model that is able of extracting combined ...spatial and temporal features from the sound recordings.•Classifying with high performance the 5 major types of valvular heart diseases (VHD) such as the aortic stenosis (AS), mitral stenosis (MS), mitral regurgitation (MR), and mitral valve pro-lapse (MVP), using a raw heart phonocardiography (PCG) recordings.•Achieving improved levels of performance compared to other studies found in literature with an overall Cohens kappa, accuracy, sensitivity, and specificity of 97.87%, 99.32%, 98.30%, and 99.50%.•The study paves the way towards implementing simple, yet effective, deep learning models in VHD identification under clinical settings to assist clinicians in critical decision making.
Valvular heart diseases (VHD) are one of the major causes of cardiovascular diseases that are having high mortality rates worldwide. The early diagnosis of VHD prevents the development of cardiac diseases and allows for optimum medication. Despite of the ability of current gold standards in identifying VHD, they still lack the required accuracy and thus, several cases go misdiagnosed. In this vein, a study is conducted herein to investigate the efficiency of deep learning models in identifying VHD through phonocardiography (PCG) recordings. PCG heart sounds were obtained from an open-access data-set representing normal heart sounds along with four major VHD; namely aortic stenosis (AS), mitral stenosis (MS), mitral regurgitation (MR), and mitral valve prolapse (MVP). A total of 1,000 patients were involved in the study with 200 recordings for each class. All recordings were initially trimmed to have 9,600 samples ensuring their coverage of at least 1 cardiac cycle. In addition, they were pre-processed by applying maximal overlap discrete wavelet transform (MODWT) smoothing algorithm and z-score normalization. The neural network architecture was designed to reduce the complexity often found in literature and consisted of a combination of convolutional neural networks (CNN) and recurrent neural networks (RNN) based on Bi-directional long short-term memory (BiLSTM). The model was trained and tested following a k-fold cross-validation scheme of 10-folds utilizing the CNN-BiLSTM network as well as the CNN and BiLSTM, individually. The highest performance was achieved using the CNN-BiLSTM network with an overall Cohen’s kappa, accuracy, sensitivity, and specificity of 97.87%, 99.32%, 98.30%, and 99.58%, respectively. In addition, the model had an average area under the curve (AUC) of 0.998. Furthermore, the performance of the model was assessed on the PhysioNet/Computing in Cardiology 2016 challenge data-set and reached an overall accuracy of 87.31% with an AUC of 0.900. This study paves the way towards implementing deep learning models in VHD identification under clinical settings to assist clinicians in decision making and prevent many cases from cardiac abnormalities development.
This study was sought to investigate the feasibility of using smartphone-based breathing sounds within a deep learning framework to discriminate between COVID-19, including asymptomatic, and healthy ...subjects. A total of 480 breathing sounds (240 shallow and 240 deep) were obtained from a publicly available database named Coswara. These sounds were recorded by 120 COVID-19 and 120 healthy subjects via a smartphone microphone through a website application. A deep learning framework was proposed herein that relies on hand-crafted features extracted from the original recordings and from the mel-frequency cepstral coefficients (MFCC) as well as deep-activated features learned by a combination of convolutional neural network and bi-directional long short-term memory units (CNN-BiLSTM). The statistical analysis of patient profiles has shown a significant difference (p-value: 0.041) for ischemic heart disease between COVID-19 and healthy subjects. The Analysis of the normal distribution of the combined MFCC values showed that COVID-19 subjects tended to have a distribution that is skewed more towards the right side of the zero mean (shallow: 0.59±1.74, deep: 0.65±4.35, p-value: <0.001). In addition, the proposed deep learning approach had an overall discrimination accuracy of 94.58% and 92.08% using shallow and deep recordings, respectively. Furthermore, it detected COVID-19 subjects successfully with a maximum sensitivity of 94.21%, specificity of 94.96%, and area under the receiver operating characteristic (AUROC) curves of 0.90. Among the 120 COVID-19 participants, asymptomatic subjects (18 subjects) were successfully detected with 100.00% accuracy using shallow recordings and 88.89% using deep recordings. This study paves the way towards utilizing smartphone-based breathing sounds for the purpose of COVID-19 detection. The observations found in this study were promising to suggest deep learning and smartphone-based breathing sounds as an effective pre-screening tool for COVID-19 alongside the current reverse-transcription polymerase chain reaction (RT-PCR) assay. It can be considered as an early, rapid, easily distributed, time-efficient, and almost no-cost diagnosis technique complying with social distancing restrictions during COVID-19 pandemic.
Neonatal sleep analysis at the neonatal intensive care units (NICU) is critical for the diagnosis of any brain growth risks during the early stages of life. In this paper, an investigation is carried ...out on the use of a long short-term memory (LSTM) learning system in automatic sleep stage scoring in neonates. The developed algorithm automatically classifies sleep stages based on inputs from a single channel EEG recording. Up to this date, only a single study have developed an approach for automatic sleep stage scoring in neonatal sleep signals using deep neural network (DNN). A total of 5095 sleep stages signals acquired from EEG recordings of the University of Pittsburgh are used in this study. The sleep stages are annotated by a medical doctor from the Pediatric Neurology Department of Case Western Reserve University for three neonatal sleep stages including the awake (W), active sleep (AS), and quiet sleep (QS) stages on every 60-s epoch. The signals are pre-processed through normalization and filtering. The resulted signals are divided following 4-, 6-, and 10-fold cross-validation schemes. The training and classification process is done using a bi-directional LSTM network classifier built with pre-defined training parameters. At the end, the developed algorithm is evaluated along with a complete summary table that reports the results of this study and other state-of-the-art studies. The current study achieved high levels of Cohen’s kappa (
κ
), accuracy, and F1 score with 91.37%, 96.81%, and 94.43%, respectively. Based on the confusion matrix, the overall true positives percentage reached 95.21%. The developed algorithm gave promising results in automatic sleep stage scoring in neonatal sleep signals. Future work include LSTM architecture and training parameters improvements to enhance the overall accuracy of the classifier.
The process of inspecting electroencephalography (EEG) signals of patients with epilepsy to distinguish between focal and non-focal seizure source is a crucial step prior to surgical interference. In ...this paper, a deep learning approach using a long short-term memory (LSTM) algorithm is investigated for the purpose of automatic discrimination between focal and non-focal epileptic EEG signals. The study is carried out by acquiring 7500 pairs of x and y EEG channels signals from the publicly available Bern-Barcelona EEG database. The manual classification of each signal type was visually done by two board-certified electroencephalographers and neurologists. Initially, every channel signals are pre-processed using <inline-formula> <tex-math notation="LaTeX">z </tex-math></inline-formula>-score normalization and Savitzky-Golay filtering. The signals are used as inputs to a pre-defined Bi-directional LSTM algorithm for the training process. The classification is performed using a k-fold cross-validation following 4-, 6-, and 10-fold schemes. At the end, the performance of the algorithm is evaluated using several metrics with a complete summary table of the recent state-of-art studies in the field. The developed algorithm achieved an overall Cohen's kappa <inline-formula> <tex-math notation="LaTeX">\kappa </tex-math></inline-formula>, accuracy, sensitivity, and specificity values of 99.20%, 99.60%, 99.55%. and 99.65%, respectively, using x channels and 10-fold cross-validation scheme. The study pave the ways toward implementing deep learning algorithms for the purpose of EEG signals identification in a clinical environment to overcome human errors resulting from visually inspection.
A major cause of bone mass loss worldwide is osteoporosis. X-ray is considered to be the gold-standard technique to diagnose this disease. However, there is currently a need for an alternative ...modality due to the ionizing radiations used in X-rays. In this vein, we conducted a numerical study herein to investigate the feasibility of using microwave tomography (MWT) to detect bone density variations that are correlated to variations in the complex relative permittivity within the reconstructed images. This study was performed using an in-house finite-element method contrast source inversion algorithm (FEM-CSI). Three anatomically-realistic human leg models based on magnetic resonance imaging reconstructions were created. Each model represents a leg with a distinct fat layer thickness; thus, the three models are for legs with thin, medium, and thick fat layers. In addition to using conventional matching media in the numerical study, the use of commercially available and cheap ultrasound gel was evaluated prior to bone image analysis. The inversion algorithm successfully localized bones in the thin and medium fat scenarios. In addition, bone volume variations were found to be inversely proportional to their relative permittivity in the reconstructed images with the root mean square error as low as 2.54. The observations found in this study suggest MWT as a promising bone imaging modality owing to its safe and non-ionizing radiations used in imaging objects with high quality.
Osteoporosis is the major cause of bone weakness and fragility in more than 10 million people in the United States. This disease causes bone fractures in the hip or spine, which result in increasing ...the risk of disabilities or even death. The current gold standard in osteoporosis diagnostics, X-ray, although reliable, it uses ionizing radiations that makes it unfeasible for early and continuous monitoring applications. Recently, microwave tomography (MWT) has been emerging as a biomedical imaging modality that utilizes non-ionizing electromagnetic signals to screen bones' electrical properties. These properties are highly correlated to bones' density, which makes MWT to be an effective and safe alternative for frequent testing in osteoporosis diagnostics.
Both the conventional and wearable simulated systems were successful in localizing the tibia and fibula bones in the enhanced MWT images. Furthermore, structure extraction of the leg's model from the blind MWT images had a minimal error compared to the original one (L2-norm: 15.60%). Under five sequentially incremental bone volume fraction (BVF) scenarios simulating bones' treatment procedure, bones were detected successfully and their densities were found to be inversely proportional to the real part of the relative permittivity values.
This study paves the way towards implementing a safe and user-friendly MWT system that can be wearable to monitor bone degradation or treatment for osteoporosis cases.
An anatomically realistic finite-element (FE) model representing the human leg was initially generated and filled with corresponding tissues' (skin, fat, muscles, and bones) dielectric properties. Then, numerically, the forward and inverse MWT problems were solved within the framework of the finite-element method-contrast source inversion algorithm (FEM-CSI). Furthermore, image reconstruction enhancements were investigated by utilizing prior information about different tissues as an inhomogeneous background as well as by adjusting the imaging domain and antennas locations based on the prior structural information. In addition, the utilization of a medically approved matching medium that can be used in wearable applications, namely an ultrasound gel, was suggested. Additionally, an approach based on k-means clustering was developed to extract the prior structural information from blind reconstructions. Finally, the enhanced images were used to monitor variations in BVF.
Nowadays, the whole world is being concerned with a major health problem, which is diabetes. A very common symptom of diabetes is the diabetic foot ulcer (DFU). The early detection of such foot ...complications can protect diabetic patients from any dangerous stages that develop later and may require foot amputation. This work aims at building a mobile thermal imaging system that can be used as an indicator for possible developing ulcers.
The proposed system consists of a thermal camera connected to a Samsung smart phone, which is used to acquire thermal images. This thermal imaging system has a simulated temperature gradient of more than 2.2 °C, which represents the temperature difference (in the literature) than can indicate a possible development of ulcers. The acquired images are processed and segmented using basic image processing techniques. The analysis and interpretation is conducted using two techniques: Otsu thresholding technique and Point-to-Point mean difference technique.
The proposed system was implemented under MATLAB Mobile platform and thermal images were analyzed and interpreted. Four testing images (feet images) were used to test this procedure; one image with any temperature variation to the feet, and three images with skin temperature increased to more than 2.2 °C introduced at different locations. With the two techniques applied during the analysis and interpretation stage, the system was successful in identifying the location of the temperature increase.
This work successfully implemented a mobile thermal imaging system that includes an automated method to identify possible ulcers in diabetic patients. This may give diabetic patients the ability for a frequent self-check of possible ulcers. Although this work was implemented in simulated conditions, it provides the necessary feasibility to be further developed and tested in a clinical environment.
Previous literature has highlighted the importance of maternal behavior during the prenatal period for the upbringing of healthy adults. During pregnancy, fetal health assessments are mainly carried ...out non-invasively by monitoring fetal growth and heart rate (HR) or RR interval (RRI). Despite this, research entailing prediction of fHRs from mHRs is scarce mainly due to the difficulty in non-invasive measurements of fetal electrocardiogram (fECG). Also, so far, it is unknown how mHRs are associated with fHR over the short term. In this study, we used two machine learning models, support vector regression (SVR) and random forest (RF), for predicting average fetal RRI (fRRI). The predicted fRRI values were compared with actual fRRI values calculated from non-invasive fECG. fRRI was predicted from 13 maternal features that consisted of age, weight, and non-invasive ECG-derived parameters that included HR variability (HRV) and R wave amplitude variability. 156 records were used for training the models and the results showed that the SVR model outperformed the RF model with a root mean square error (RMSE) of 29 ms and an average error percentage (< 5%). Correlation analysis between predicted and actual fRRI values showed that the Spearman coefficient for the SVR and RF models were 0.31 (P < 0.001) and 0.19 (P < 0.05), respectively. The SVR model was further used to predict fRRI of 14 subjects who were not included in the training. The latter prediction results showed that individual error percentages were (≤ 5%) except in 3 subjects. The results of this study show that maternal factors can be potentially used for the assessment of fetal well-being based on fetal HR or RRI.
Heart failure is characterized by sympathetic activation and parasympathetic withdrawal leading to an abnormal autonomic modulation. Beta-blockers (BB) inhibit overstimulation of the sympathetic ...system and are indicated in heart failure patients with reduced ejection fraction. However, the effect of beta-blocker therapy on heart failure with preserved ejection fraction (HFpEF) is unclear. ECGs of 73 patients with HFpEF > 55% were recruited. There were 56 patients in the BB group and 17 patients in the without BB (NBB) group. The HRV analysis was performed for the 24-h period using a window size of 1,4 and 8-h. HRV measures between day and night for both the groups were also compared. Percentage change in the BB group relative to the NBB group was used as a measure of difference. RMSSD (13.27%), pNN50 (2.44%), HF power (44.25%) and LF power (13.53%) showed an increase in the BB group relative to the NBB group during the day and were statistically significant between the two groups for periods associated with high cardiac risk during the morning hours. LF:HF ratio showed a decrease of 3.59% during the day. The relative increase in vagal modulated RMSSD, pNN50 and HF power with a decrease in LF:HF ratio show an improvement in the parasympathetic tone and an overall decreased risk of a cardiac event especially during the morning hours that is characterized by a sympathetic surge.
Artifacts in the Electrocardiogram (ECG) degrade the quality of the recorded signal and are not conducive to heart rate variability (HRV) analysis. The two types of noise most often found in ECG ...recordings are technical and physiological artifacts. Current preprocessing methods primarily attend to ectopic beats but do not consider technical issues that affect the ECG. A secondary aim of this study was to investigate the effect of increasing increments of artifacts on 24 of the most used HRV measures. A two-step preprocessing approach for denoising HRV is introduced which targets each type of noise separately. First, the technical artifacts in the ECG are eliminated by applying complete ensemble empirical mode decomposition with adaptive noise. The second step removes physiological artifacts from the HRV signal using a combination filter of single dependent rank order mean and an adaptive filtering algorithm. The performance of the two-step pre-processing tool showed a high correlation coefficient of 0.846 and RMSE value of 7.69 × 10
for 6% of added ectopic beats and 6 dB Gaussian noise. All HRV measures studied except HF peak and LF peak are significantly affected by both types of noise. Frequency measures of Total power, HF power, and LF power and fragmentation measures; PAS, PIP, and PSS are the most sensitive to both types of noise.