Unhealthy Cases Research Articles

MSTAC: A Multi-Stage Automated Classification of COVID-19 Chest X-ray Images Using Stacked CNN Models.

This study introduces a Multi-Stage Automated Classification (MSTAC) system for COVID-19 chest X-ray (CXR) images, utilizing stacked Convolutional Neural Network (CNN) models. Suspected COVID-19 patients often undergo CXR imaging, making it valuable for disease classification. The study collected CXR images from public datasets and aimed to differentiate between COVID-19, non-COVID-19, and healthy cases. MSTAC employs two classification stages: the first distinguishes healthy from unhealthy cases, and the second further classifies COVID-19 and non-COVID-19 cases. Compared to a single CNN-Multiclass model, MSTAC demonstrated superior classification performance, achieving 97.30% accuracy and sensitivity. In contrast, the CNN-Multiclass model showed 94.76% accuracy and sensitivity. MSTAC's effectiveness is highlighted in its promising results over the CNN-Multiclass model, suggesting its potential to assist healthcare professionals in efficiently diagnosing COVID-19 cases. The system outperformed similar techniques, emphasizing its accuracy and efficiency in COVID-19 diagnosis. This research underscores MSTAC as a valuable tool in medical image analysis for enhanced disease classification.

Anthropometrics and Myocardial Infarction Risk: A Misleading Evidence Was Accepted by Cardiovascular Sciences When Errors of Bias Were Overlooked Worldwide. When Should We End Discussion about the Optimal Metric?

Despite the impact of the COVID‑19 pandemic, myocardial infarction remains the leading cause of cardiovascular deaths in Europe. Body mass index (BMI)-defined obesity is a major risk factor for myocardial infarction. However, in the association of anthropometrics and myocardial infarction, the lack of balance between the simple body measurements when comparing healthy and unhealthy cases has demonstrated that affects the outcome. Thus, regardless of association strength of anthropometrics, other criteria to judge the biological causality must be investigated. We aim to assess different studies worldwide to understand the key concepts to demonstrate association biases for anthropometrics when predicting myocardial infarction risk. In this approach, natural mathematical inequalities between simple measurements in healthy subjects were investigated. Weight, height, height/2, waist circumference and hip circumference mathematically represent absolute values that do not express mathematically equality for the true risk. That way, the mathematical concept of fraction or ratio in anthropometrics such as BMI, waist-to-hip ratio (WHR) or waist-to-height ratio (WHtR) plays an important role. Thus, some anthropometrics may be seen as confounding variables when measuring high-risk body composition. Weight is a confounding factor without indicating a high-risk body composition, meaning that BMI is not fully predictive. WHR is a confounding variable concerning waist and WHtR due to imbalances between the mean hip–waist and hip–height, respectively, which indicates a protective overestimation for hip concerning waist and height. Waist measure may be a confounding variable concerning WHtR due to an imbalance in the mean waist–height. This occurs if, and only if, WHtR risk cut-off is >0.5 and if height is ignored as volume factor, therefore creating an overestimation of risk for waist circumference in the tallest people and underestimation in the shortest. Mathematically/anthropometrically, only WHtR-associated risk above BMI, waist and WHR holds true while considering it as a relative risk volume linked to a causal pathway of higher cardiometabolic risk. In conclusion, WHtR is the only metric that is directly associated to a risk volume and having more biological plausibility. It should be used to assess the anthropometrically-measured myocardial infarction risk, once the imbalances between measurements and association biases are recognised.

Waist-to-Height Ratio is an Optimal Metric in Predicting Myocardial Infarction Risk. Other Anthropometrics Widely used by Cardiology to Promote Cardiovascular Health Present Association Biases

Among the components of Life’s Essential 8, body mass index is the anthropometric used in the scoring algorithm of cardiovascular health. Concerning myocardial infarction, the waist-to-hip ratio may show more predictive value than body mass index, waist circumference, and waist-to-height ratio, and has showed a greater excess risk of myocardial infarction in women than in men. However, bias has occurred in global research because of inadequate comparisons with the high-risk body composition. Hence, cardiology may have been confused for a long time because bias-related errors were always overlooked. This situation occurred when risk association was distorted by over- or under-estimating some simple measurements over others. Our aim was to determine whether the historical risk associated with some anthropometrics might provide a bias in causal inferences. Our study design was a review on data of the body of literature. We created new anthropometric variables, which were always omitted in previous large studies. In most studies, mathematical inequalities between the simple measurements in anthropometrically healthy subjects were overlooked, including disparities between lean and fat masses. That way, in omitting the difference in means between the simple measurements of length and body mass components, association findings and causality cannot be assumed. No anthropometric will be equivalent for estimating the same high-risk body composition if the difference in means between the simple measurements present an unbalanced distribution, and besides, being associated as confounding factors. Therefore, after describing new anthropometric variables termed as “x” and demonstrating that the simple measurements showed means of differences differentially distributed between healthy and unhealthy cases worldwide, association biases for the body mass index, waist-to-hip ratio or waist circumference alone may be endorsed, indicating the importance of these results. From a new anthropometric perspective, the waist-to-height ratio may indicate the concrete volume of an abdominal three-dimensional disc in direct-inverse relationship with waist-body height without showing association biases. This index may represent a new construct by defining a risk abdominal volume and avoiding potential confounding factors. In a paradigm shift, only the waist-to-height ratio meets causality criteria as the optimal index to predict myocardial infarction risk and to promote cardiovascular health.

Diabetic foot ulcer classification using mapped binary patterns and convolutional neural networks

Diabetic foot ulcer (DFU) is a major complication of diabetes and can lead to lower limb amputation if not treated early and properly. In addition to the traditional clinical approaches, in recent years, research on automation using computer vision and machine learning methods plays an important role in DFU classification, achieving promising successes. The most recent automatic approaches to DFU classification are based on convolutional neural networks (CNNs), using solely RGB images as input. In this paper, we present a CNN-based DFU classification method in which we showed that feeding an appropriate feature (texture information) to the CNN model provides a complementary performance to the standard RGB-based deep models of the DFU classification task, and better performance can be obtained if both RGB images and their texture features are combined and used as input to the CNN. To this end, the proposed method consists of two main stages. The first stage extracts texture information from the RGB image using the mapped binary patterns technique. The obtained mapped image is used to aid the second stage in recognizing DFU as it contains texture information of ulcer. The stack of RGB and mapped binary patterns images are fed to the CNN as a tensor input or as a fused image, which is a linear combination of RGB and mapped binary patterns images. The performance of the proposed approach was evaluated using two recently published DFU datasets: the Part-A dataset of healthy and unhealthy (DFU) cases [17] and Part-B dataset of ischaemia and infection cases [18]. The results showed that the proposed methods provided better performance than the state-of-the-art CNN-based methods with 0.981% (AUC) and 0.952% (F-Measure) on the Part-A dataset, 0.995% (AUC) and 0.990% (F-measure) for the Part-B ischaemia dataset, and 0.820% (AUC) and 0.744% (F-measure) on the Part-B infection dataset.

The effect of nasal airway obstruction on the dispersion and deposition of inhaled volatile droplets in the human nasal cavity: A numerical study

Nasal airway obstruction (NAO) is one of the main problems in the upper part of the human respiratory system. NAO may considerably affect the airflow and the behavior of droplets in the nasal cavity. In the present study, the effect of septal deviation as a special kind of NAO on the deposition and penetration of initially micron-sized inhaled droplets in the nasal cavities of two patients was numerically investigated. The geometries were constructed using CT scan images, and breathing zones were added to the models to make the inspiratory cycle more physically realistic. The motion of droplets was studied using the Lagrangian trajectory analysis approach, including the drag, Saffman's lift, and Brownian forces, as well as the evaporation process. The results showed that both unhealthy cases with obstruction had less heat transfer than the healthy nasal passage, which results in slower evaporation of droplets. On the other hand, due to the septal deviation, the deposition of droplets increased in the cases with nasal obstruction. Inertial impaction was the primary deposition mechanism, which was more critical than the diffusion in the region in which septal deviations diverted the airflow. The simulation results showed that due to less convoluted turbinate passages and smaller surface area to volume ratio (SAVR) of the nasal cavities with obstruction in comparison with a healthy nose, the size of droplets that escape from the human nasal cavity became smaller. As a result, for patients with septal deviations, small droplets could penetrate deep into the respiratory system and increase the risk of transmission of respiratory diseases.

Smartphone-Based Self-Testing of COVID-19 Using Breathing Sounds.

Telemedicine could be a key to control the world-wide disruptive and spreading novel coronavirus disease (COVID-19) pandemic. The COVID-19 virus directly targets the lungs, leading to pneumonia-like symptoms and shortness of breath with life-threatening consequences. Despite the fact that self-quarantine and social distancing are indispensable during the pandemic, the procedure for testing COVID-19 contraction is conventionally available through nasal swabs, saliva test kits, and blood work at healthcare settings. Therefore, devising personalized self-testing kits for COVID-19 virus and other similar viruses is heavily admired. Many e-health initiatives have been made possible by the advent of smartphones with embedded software, hardware, high-performance computing, and connectivity capabilities. A careful review of breathing sounds and their implications in identifying breathing complications suggests that the breathing sounds of COVID-19 contracted users may reveal certain acoustic signal patterns, which is worth investigating. To this end, acquiring respiratory data solely from breathing sounds fed to the smartphone's microphone strikes as a very appealing resolution. The acquired breathing sounds can be analyzed using advanced signal processing and analysis in tandem with new deep/machine learning and pattern recognition techniques to separate the breathing phases, estimate the lung volume, oxygenation, and to further classify the breathing data input into healthy or unhealthy cases. The ideas presented have the potential to be deployed as self-test breathing monitoring apps for the ongoing global COVID-19 pandemic, where users can check their breathing sound pattern frequently through the app.

Improving Diagnosis of Depression With XGBOOST Machine Learning Model and a Large Biomarkers Dutch Dataset (n = 11,081).

Machine Learning has been on the rise and healthcare is no exception to that. In healthcare, mental health is gaining more and more space. The diagnosis of mental disorders is based upon standardized patient interviews with defined set of questions and scales which is a time consuming and costly process. Our objective was to apply the machine learning model and to evaluate to see if there is predictive power of biomarkers data to enhance the diagnosis of depression cases. In this research paper, we aimed to explore the detection of depression cases among the sample of 11,081 Dutch citizen dataset. Most of the earlier studies have balanced datasets wherein the proportion of healthy cases and unhealthy cases are equal but in our study, the dataset contains only 570 cases of self-reported depression out of 11,081 cases hence it is a class imbalance classification problem. The machine learning model built on imbalance dataset gives predictions biased toward majority class hence the model will always predict the case as no depression case even if it is a case of depression. We used different resampling strategies to address the class imbalance problem. We created multiple samples by under sampling, over sampling, over-under sampling and ROSE sampling techniques to balance the dataset and then, we applied machine learning algorithm “Extreme Gradient Boosting” (XGBoost) on each sample to classify the mental illness cases from healthy cases. The balanced accuracy, precision, recall and F1 score obtained from over-sampling and over-under sampling were more than 0.90.

Breast Cancer Segmentation From Thermal Images Based on Chaotic Salp Swarm Algorithm

Breast cancer is one of the most common types of cancer and early detection can significantly decrease the associated mortality rate. Different kinds of segmentation methods were applied to extract regions of interest from breast cancer images that are necessary to improve the classification. In this paper, a segmentation method for breast cancer from thermal images is introduced based on a proposed Chaotic Salp Swarm Algorithm (CSSA). Although the Salp Swarm Algorithm (SSA) shows superiority in single-objective optimization problems, it suffers from a low convergence rate and local optima stagnation. In the proposed method, a segmentation algorithm is formulated using the quick-shift method for superpixels extraction whose parameters are optimized by CSSA. The quick-shift method generates compact and nearly uniform superpixels by clustering the breast thermal image pixels. CSSA algorithm is developed based on ten chaotic maps to enhance the original SSA convergence rate while accuracy could be improved by controlling the balance between exploration and exploitation. The proposed algorithm is applied to real-world thermal images for the breast area. The results demonstrate that the proposed CSSA algorithm achieves fast convergence for the unimodal benchmark functions and outperforms the original SSA algorithm. Moreover, a dataset from Mastology Research with Infrared Image (DMR-IR) is used to test the performance of the proposed algorithm. In experiments, the proposed optimized segmentation algorithm extracts the breast area from the background accurately where the region of interest is focused on the breast area and removes the unwanted area such as underarms and stomach which intern can enhance the results of cancer detection. Furthermore, the proposed algorithms achieve robustness for the segmentation of different healthy and unhealthy cases images compared to the state-of-the-art methods.

Pattern Reconfigurable Metasurface Antenna for Electromagnetic Torso Imaging

A pattern reconfigurable metasurface antenna for an electromagnetic torso imaging system operating at the ultrahigh frequency (UHF) band is presented. To meet the requirements of electromagnetic torso imaging, the antenna can scan the human chest with steerable unidirectional radiation patterns. The designed antenna consists of three rectangular microstrip-fed slot radiators illuminating a metasurface layer with $7\times 5$ unit cells to cover the whole chest. Six p-i-n diodes are used to switch the radiating slots creating different beams. The unit cell dimensions are $0.125\lambda _{0}\times 0.125\lambda _{0}$ and the antenna has a low profile of $0.9\lambda _{0}\times 0.7\lambda _{0}\times 0.06\lambda _{0}$ ( $\lambda _{0}$ is the wavelength of the lowest operating frequency of the antenna). The antenna creates three distinct beams with a peak gain of 8 dBi at 1 GHz and 2 dBi gain variations across different beams over its measured wide operating frequency bandwidth of 27% at 0.8–1.05 GHz. A complete electromagnetic torso imaging system, which utilizes the designed antenna, is built and is successfully tested to detect 20 mL of fluid (water) inside the torso, thus differentiating between healthy and unhealthy cases.

A case-study of NIRS application for infant cerebral hemodynamic monitoring: A report of data analysis for feature extraction and infant classification into healthy and unhealthy

Abstract This paper reports the results of cerebral hemodynamic data analysis gathered from infant foreheads in selected case-studies. These studies were utilized for extracting relevant features aimed for discriminatory classification of infants into healthy and unhealthy cases. The principal objective of the study was to examine the effectiveness and accuracy of using near-infrared spectroscopy for measuring cerebral blood flow in infants and for health monitoring purposes. A total of 41 infants from several age groups varying from 2 h to several days since birth were participated for experimental data recordings. Both healthy and unhealthy infants of similar age groups were selected for the study. Selection was made without consideration as to the type of disorder in unhealthy infants, or any consideration as to being under any particular monitoring action. Data were collected during the rest state with no external stimulus. Several data analysis approaches were applied including temporal and time-frequency analyses, which were used for feature extraction of hemodynamic data and for identifying selective features to be used during data classification. We utilized SVM for pattern recognition and feature extraction aimed at discriminatory classification of healthy infants from unhealthy cases. This was followed by the application of the t-test for statistical analysis and accuracy evaluation. The results show a 94% accuracy in classification. A clear relationship was also found between oxy- and deoxy-hemoglobin concentration data belonging to healthy infants as shown in 2D data clustering illustration that can be used for infant classification. Similar correlation results were also observed with other physiological data.

Detecting abnormality in heart dynamics from multifractal analysis of ECG signals

The characterization of heart dynamics with a view to distinguish abnormal from normal behavior is an interesting topic in clinical sciences. Here we present an analysis of the Electro-cardiogram (ECG) signals from several healthy and unhealthy subjects using the framework of dynamical systems approach to multifractal analysis. Our analysis differs from the conventional nonlinear analysis in that the information contained in the amplitude variations of the signal is being extracted and quantified. The results thus obtained reveal that the attractor underlying the dynamics of the heart has multifractal structure and the variations in the resultant multifractal spectra can clearly separate healthy subjects from unhealthy ones. We use supervised machine learning approach to build a model that predicts the group label of a new subject with very high accuracy on the basis of the multifractal parameters. By comparing the computed indices in the multifractal spectra with that of beat replicated data from the same ECG, we show how each ECG can be checked for variations within itself. The increased variability observed in the measures for the unhealthy cases can be a clinically meaningful index for detecting the abnormal dynamics of the heart.

Foam Embedded Wideband Antenna Array for Early Congestive Heart Failure Detection With Tests Using Artificial Phantom With Animal Organs

A foam-embedded wideband antenna array is used to build a portable system for congestive heart failure (CHF) detection. In addition to the array, which has a pair of four-element antenna subarrays, the system includes a portable vector network analyzer (VNA), a switching system, and a laptop, which contains control, signal processing, and image formation algorithms. The main aim of the built system is to provide a noninvasive, convenient, low cost, fast, and reliable platform for detection and monitoring of CHF. In that regard, the antenna elements are built using a three-dimensional (3-D) structure, which utilizes a combination of loop, monopole, and parasitic patches to cover the needed band (0.7–1 GHz) while keeping the size compact. A differential technique is utilized to distinguish between healthy and unhealthy cases. The performance of the system is tested on an artificial phantom and a phantom with a pair of lamb lungs, which are confirmed to have electrical properties close to those of humans. Several possible cases are investigated to validate the reliability of the system in the early detection of CHF.

Optimization-Based Confocal Microwave Imaging in Medical Applications

An optimization-based confocal algorithm for microwave imaging aimed at medical applications is presented. Due to complexity of human body tissues, microwave signals that enter a human organ from different angles and are reflected at different depths inside that organ face different effective dielectric constants. An accurate estimation of those dielectric constants is vital for an accurate estimation of signal speed within the imaged object and thus accurate resultant images. The traditional confocal algorithm uses one preassumed effective dielectric constant and thus its resultant image is sensitive to that assumption. In the proposed approach, position-dependent dielectric constants are used to generate a highly focused image that accurately maps scatterers within an imaged object. To that end, an objective equation based on the focusing degree of the obtained initial image is created. Then, particle swarm optimization (PSO) uses that equation to find the effective dielectric constants facing signals penetrating the object according to their entrance point. Those optimized effective dielectric constants are used to produce a highly focused image without the risk of creating false-positive targets irrespective of the initial values of the effective dielectric constants. The proposed algorithm is evaluated in head imaging via full-wave electromagnetic simulations and experiments. The simulations are based on using an accurate numerical head model, whereas the experiments are conducted using realistic artificial head phantoms. The obtained images indicate that the quality of the images is significantly improved with more accurate localization of targets in unhealthy cases and less probability of positive false alarms in healthy cases compared with the traditional approach.

Microwave System for the Early Stage Detection of Congestive Heart Failure

Fluid accumulation inside the lungs, known as cardiac pulmonary edema, is one of the main early symptoms of congestive heart failure (CHF). That accumulation causes significant changes in the electrical properties of the lung tissues, which in turn can be detected using microwave techniques. To that end, the design and implementation of an automated ultrahigh-frequency microwave-based system for CHF detection and monitoring is presented. The hardware of the system consists of a wideband folded antenna attached to a fully automated vertical scanning platform, compact microwave transceiver, and laptop. The system includes software in the form of operational control, signal processing, and visualizing algorithms. To detect CHF, the system is designed to vertically scan the rear side of the human torso in a monostatic radar approach. The collected data from the scanning is then visualized in the time domain using the inverse Fourier transform. These images show the intensity of the reflected signals from different parts of the torso. Using a differential based detection technique, a threshold is defined to differentiate between healthy and unhealthy cases. This paper includes details of developing the automated platform, designing the antenna with the required properties imposed by the system, developing a signal processing algorithm, and introducing differential detection technique besides investigating miscellaneous probable CHF cases.

Three-Dimensional Open-Ended Slot Antenna for Heart Failure Detection System Employing Differential Technique

The design of a folded open-ended slot antenna for an early-stage congestive heart failure (CHF) detection system operating at ultra-high frequency (UHF) is presented. The antenna is formed using a three-dimensional open-ended slot with a compact size of 0.24 λ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> × 0.09λ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> × 0.04 λ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> (λ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> is the lowest operating frequency of the antenna), and a slotted microstrip feeder used to achieve wide operating bandwidth of 58% (550-1000 MHz). A CHF detection system is then built using the proposed antenna, a compact microwave sensor, and a differential detection technique. The main objective of such a system is to map the torso area searching for any fluid accumulation in the lungs as the main symptom of CHF. To that end, a pair of the proposed antenna is attached to an adjustable platform to vertically scan the torso. A differential detection technique is applied on the backscattered signals to map the scattering profile of the torso and detect any changes in the electrical properties of the lungs caused by fluid accumulation. A detection threshold is applied to differentiate between healthy and unhealthy cases. The obtained images have a pixel resolution of 0.1 cm in depth and 1 cm in height. The experimental results on an artificial torso indicate that the system can detect fluid differences as small as 4 mL, with a measurement error of less than 3%.

An Intelligent Diagnostic System for Congenital Heart Defects

Congenital heart disease is the most common birth defect. The article describes detection and classification of congenital heart defect using classification and regressing trees. The ultimate goal of this research can decrease risk of cardiac arrest and mortality in compared with healthy children. The intelligent system proposed in three stages technique for automate diagnosis:(i) pre-processing(ii), feature extraction, and (iii) classification of congenital heart defects (CHD) using data mining tools. The intelligent diagnostic system has been validated with a representative dataset of 110 heart sound signals, taken from healthy and unhealthy medical cases. This system was evaluated in the test dataset with the following performance measurements global accuracy: 98.18%, sensitivity, 96.36% and specificity 100%. This results show the feasibility of classification based on optimized feature extraction and classifier. This paper follows the Association for the recommendations of the Advancement of Medical Instrumentation.

Support Vectors Machine-based identification of heart valve diseases using heart sounds

Taking into account that heart auscultation remains the dominant method for heart examination in the small health centers of the rural areas and generally in primary healthcare set-ups, the enhancement of this technique would aid significantly in the diagnosis of heart diseases. In this context, the present paper initially surveys the research that has been conducted concerning the exploitation of heart sound signals for automated and semi-automated detection of pathological heart conditions. Then it proposes an automated diagnosis system for the identification of heart valve diseases based on the Support Vector Machines (SVM) classification of heart sounds. This system performs a highly difficult diagnostic task (even for experienced physicians), much more difficult than the basic diagnosis of the existence or not of a heart valve disease (i.e. the classification of a heart sound as ‘healthy’ or ‘having a heart valve disease’): it identifies the particular heart valve disease. The system was applied in a representative global dataset of 198 heart sound signals, which come both from healthy medical cases and from cases suffering from the four most usual heart valve diseases: aortic stenosis (AS), aortic regurgitation (AR), mitral stenosis (MS) and mitral regurgitation (MR). Initially the heart sounds were successfully categorized using a SVM classifier as normal or disease-related and then the corresponding murmurs in the unhealthy cases were classified as systolic or diastolic. For the heart sounds diagnosed as having systolic murmur we used a SVM classifier for performing a more detailed classification of them as having aortic stenosis or mitral regurgitation. Similarly for the heart sounds diagnosed as having diastolic murmur we used a SVM classifier for classifying them as having aortic regurgitation or mitral stenosis. Alternative classifiers have been applied to the same data for comparison (i.e. back-propagation neural networks, k-nearest-neighbour and naïve Bayes classifiers), however their performance for the same diagnostic problems was lower than the SVM classifiers proposed in this work.