Scale based entropy measures and deep learning methods for analyzing the dynamical characteristics of cardiorespiratory control system in COVID-19 subjects during and after recovery.

COVID-19, known as Coronavirus Disease 2019 primarily targets the respiratory system and can impact the cardiovascular system, leading to a range of cardiorespiratory complications. The current forefront in analyzing the dynamical characteristics of physiological systems and aiding clinical decision-making involves the integration of entropy-based complexity techniques with artificial intelligence. Entropy-based measures offer promising prospects for identifying disturbances in cardiorespiratory control system (CRCS) among COVID-19 patients by assessing the oxygen saturation variability (OSV) signals. In this investigation, we employ scale-based entropy (SBE) methods, including multiscale entropy (MSE), multiscale permutation entropy (MPE), and multiscale fuzzy entropy (MFE), to characterize the dynamical characteristics of OSV signals. These measurements serve as features for the application of traditional machine learning (ML) and deep learning (DL) approaches in the context of classifying OSV signals from COVID-19 patients during their illness and subsequent recovery. We use the Beurer PO-80 pulse oximeter which non-invasively acquired OSV and pulse rate data from COVID-19 infected patients during the active infection phase and after a two-month recovery period. The dataset comprises of 88 recordings collected from 44 subjects(26 men and 18 women), both during their COVID-19 illness and two months post-recovery. Prior to analysis, data preprocessing is performed to remove artifacts and outliers. The application of SBE measures to OSV signals unveils a reduction in signal complexity during the course of COVID-19. Leveraging these SBE measures as feature sets, we employ two DL techniques, namely the radial basis function network (RBFN) and RBFN with dynamic delay algorithm (RBFNDDA), for the classification of OSV data collected during and after COVID-19 recovery. To evaluate the classification performance, we employ standard metrics such as sensitivity, specificity, false positive rate (FPR), and the area under the receiver operator characteristic curve (AUC). Among the three scale-based entropy measures, MFE outperformed MSE and MPE by achieving the highest classification performance using RBFN with 13 best features having sensitivity (0.84), FPR (0.30), specificity (0.70) and AUC (0.77). The outcomes of our study demonstrate that SBE measures combined with DL methods offer a valuable approach for categorizing OSV signals obtained during and after COVID-19, ultimately aiding in the detection of CRCS dysfunction.

Complexity reduction of oxygen saturation variability signals in COVID-19 patients: Implications for cardiorespiratory control.

BACKGROUND: Coronavirus disease 2019 (COVID-19) is a respiratory illness that leads to severe acute respiratory syndrome and various cardiorespiratory complications, contributing to morbidity and mortality. Entropy analysis has demonstrated its ability to monitor physiological states and system dynamics during health and disease. The main objective of the study is to extract information about cardiorespiratory control by conducting a complexity analysis of OSV signals using scale-based entropy measures following a two-month timeframe after recovery. METHODS: This prospective study collected data from subjects meeting specific criteria, using a Beurer PO-80 pulse oximeter to measure oxygen saturation (SpO2) and pulse rate. Excluding individuals with a history of pulmonary/cardiovascular issues, the study analyzed 88 recordings from 44 subjects (26 men, 18 women, mean age 45.34 ± 14.40) during COVID-19 and two months post-recovery. Data preprocessing and scale-based entropy analysis were applied to assess OSV signals. RESULTS: The study found a significant difference in mean OSV during illness (95.08 ± 0.15) compared to post-recovery (95.59 ± 1.03), indicating reduced cardiorespiratory dynamism during COVID-19. Multiscale entropy analyses (MSE, MPE, MFE) confirmed lower entropy values during illness across all time scales, particularly at higher scales. Notably, the maximum distinction between illness and recovery phases was seen at specific time scales and similarity criteria for each entropy measure, showing statistically significant differences. CONCLUSIONS: The study demonstrates that the loss of complexity in OSV signals, quantified using scale-based entropy measures, has the potential to detect malfunctioning of cardiorespiratory control in COVID-19 patients. This finding suggests that OSV signals could serve as a valuable indicator for assessing the cardiorespiratory status of COVID-19 patients and monitoring their recovery progress.

Studying Dynamical Characteristics of Oxygen Saturation Variability Signals Using Haar Wavelet.

An aim of the analysis of biomedical signals such as heart rate variability signals, brain signals, oxygen saturation variability (OSV) signals, etc., is for the design and development of tools to extract information about the underlying complexity of physiological systems, to detect physiological states, monitor health conditions over time, or predict pathological conditions. Entropy-based complexity measures are commonly used to quantify the complexity of biomedical signals; however novel complexity measures need to be explored in the context of biomedical signal classification. In this work, we present a novel technique that used Haar wavelets to analyze the complexity of OSV signals of subjects during COVID-19 infection and after recovery. The data used to evaluate the performance of the proposed algorithms comprised recordings of OSV signals from 44 COVID-19 patients during illness and after recovery. The performance of the proposed technique was compared with four, scale-based entropy measures: multiscale entropy (MSE); multiscale permutation entropy (MPE); multiscale fuzzy entropy (MFE); multiscale amplitude-aware permutation entropy (MAMPE). Preliminary results of the pilot study revealed that the proposed algorithm outperformed MSE, MPE, MFE, and MMAPE in terms of better accuracy and time efficiency for separating during and after recovery the OSV signals of COVID-19 subjects. Further studies are needed to evaluate the potential of the proposed algorithm for large datasets and in the context of other biomedical signal classifications.

A comparative study of medical image enhancement algorithms and quality assessment metrics on COVID-19 CT images.

Medical imaging can help doctors in better diagnosis of several conditions. During the present COVID-19 pandemic, timely detection of novel coronavirus is crucial, which can help in curing the disease at an early stage. Image enhancement techniques can improve the visual appearance of COVID-19 CT scans and speed-up the process of diagnosis. In this study, we analyze some state-of-the-art image enhancement techniques for their suitability in enhancing the CT scans of COVID-19 patients. Six quantitative metrics, Entropy, SSIM, AMBE, PSNR, EME, and EMEE, are used to evaluate the enhanced images. Two experienced radiologists were involved in the study to evaluate the performance of the enhancement techniques and the quantitative metrics used to assess them.

Unified implementation of global high dynamic range image tone-mapping algorithms.

High dynamic range (HDR) images and video require tone-mapping for display on low dynamic range (LDR) screens. Many tone-mapping operators have been proposed to convert HDR content to LDR, but almost each has a different implementation structure and requires a different execution time. We propose a unified structure that can represent any global tone-mapping algorithm with an array of just 256 coefficients. These coefficients extracted offline for every HDR image or video frame can be used to convert them to LDR in real time using linear interpolation. The produced LDR images are identical to the images produced by the original implementation of the algorithm. This unified implementation can replicate any global tone-mapping function and requires very low and fixed execution time, which is independent of algorithm and type of content and depends only on image size. Experimental studies are presented to show the accuracy and time efficiency of the proposed implementation.

Evaluating Quantitative Metrics of Tone-Mapped Images.

Subjective evaluation of tone-mapped images is tedious and time-consuming; therefore, it is desirable to have algorithms for automatic quality assessment. Many full-reference and blind metrics have been developed for this purpose, but their performance is generally evaluated on limited benchmark datasets. This leaves a possibility that the observed performance of the metric could be due to overfitting, and it might indeed not perform well for all scenes. In this work, we propose a novel framework using population-based metaheuristics to evaluate the performance of these metrics without requiring any subjectively evaluated reference dataset. The proposed algorithm does not modify the individual image pixels, instead, the tone-mapping curve is modified to synthesize realistic tone-mapped images for evaluation. Moreover, it is not required to know the underlying model of the evaluated metric, which is treated just like a black box and can be replaced by any other metric seamlessly. Therefore, any new metrics designed in the future can also be easily evaluated by simply replacing just one module in the proposed evaluation framework. We evaluate six existing metrics and synthesize images to which the metrics fail to assign appropriate scores for visual quality. We also propose a method to rank the relative performance of evaluated metrics, through a competition in which each metric tries to find the errors in the scores given by other metrics.

A non-uniform quantization scheme for visualization of CT images.

Medical science heavily depends on image acquisition and post-processing for accurate diagnosis and treatment planning. The introduction of noise degrades the visual quality of the medical images during the capturing process, which may result in false perception. Therefore, medical image enhancement is an essential topic of research for the improvement of image quality. In this paper, a clustering-based contrast enhancement technique is presented for computed tomography (CT) images. Our approach uses the recursive splitting of data into clusters targeting the maximum error reduction in each cluster. This leads to grouping similar pixels in every cluster, maximizing inter-cluster and minimizing intra-cluster similarities. A suitable number of clusters can be chosen to represent high precision data with the desired bit-depth. We use 256 clusters to convert 16-bit CT scans to 8-bit images suitable for visualization on standard low dynamic range displays. We compare our method with several existing contrast enhancement algorithms and show that the proposed technique provides better results in terms of execution efficiency and quality of enhanced images.

Machine learning based congestive heart failure detection using feature importance ranking of multimodal features.

In this study, we ranked the Multimodal Features extracted from Congestive Heart Failure (CHF) and Normal Sinus Rhythm (NSR) subjects. We categorized the ranked features into 1 to 5 categories based on Empirical Receiver Operating Characteristics (EROC) values. Instead of using all multimodal features, we use high ranking features for detection of CHF and normal subjects. We employed powerful machine learning techniques such as Decision Tree (DT), Naïve Bayes (NB), SVM Gaussian, SVM RBF and SVM Polynomial. The performance was measured in terms of Sensitivity, Specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), Accuracy, False Positive Rate (FPR), and area under the Receiver Operating characteristic Curve (AUC). The highest detection performance in terms of accuracy and AUC was obtained with all multimodal features using SVM Gaussian with Sensitivity (93.06%), Specificity (81.82%), Accuracy (88.79%) and AUC (0.95). Using the top five ranked features, the highest performance was obtained with SVM Gaussian yields accuracy (84.48%), AUC (0.86); top nine ranked features using Decision Tree and Naïve Bayes got accuracy (84.48%), AUC (0.88); last thirteen ranked features using SVM polynomial obtained accuracy (80.17%), AUC (0.84). The findings indicate that proposed approach with feature ranking can be very useful for automatic detection of congestive heart failure patients and can be very helpful for further decision making by the clinicians and physicians in order to decrease the mortality rate.

Machine learning based classification of normal, slow and fast walking by extracting multimodal features from stride interval time series.

The gait speed affects the gait patterns (biomechanical and spatiotemporal parameters) of distinct age populations. Classification of normal, slow and fast walking is fundamental for understanding the effects of gait speed on the gait patterns and for proper evaluation of alternations associated with it. In this study, we extracted multimodal features such as time domain and entropy-based complexity measures from stride interval signals of healthy subjects moving with normal, slow and fast speeds. The classification between different gait speeds was performed using machine learning classifiers such as classification and regression tree (CART), support vector machine linear (SVM-L), Naïve Bayes, neural network, and ensemble classifiers (random forest (RF), XG boost, averaged neural network (AVNET)). The performance was evaluated in term of accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), p-value, area under the receiver operating characteristic curve (AUC). To distinguish the slow and normal gait walking, the highest performance was yielded in terms of accuracy (100%), p-value (0.004), and AUC (1.00) using RF, XGB-L followed by XGB-Tree with accuracy (88%), p-value (0.04) and AUC (1.00). To classify the fast and normal walking, the highest performance was obtained with accuracy (88%), p-value (0.04) using XGB-L, XGB-Tree and AVNET. The highest AUC (0.94) was obtained using NB. To discriminate the fast and slow gait walking, the highest performance was obtained using SVM-R, NNET, RF, AVNET with accuracy (88%), p-value (0.04) and AUC (0.94) using RF and AUC (0.96) using XGB-L.