Labeling Privacy Protection SVM Using Privileged Information for COVID-19 Diagnosis

Edge/fog computing works at the local area network level or devices connected to the sensor or the gateway close to the sensor. These nodes are located in different degrees of proximity to the user, while the data processing and storage are distributed among multiple nodes. In healthcare applications in the Internet of things, when data is transmitted through insecure channels, its privacy and security are the main issues. In recent years, learning from label proportion methods, represented by inverse calibration (InvCal) method, have tried to predict the class label based on class label proportions in certain groups. For privacy protection, the class label of the sample is often sensitive and invisible. As a compromise, only the proportion of class labels in certain groups can be used in these methods. However, due to their weak labeling scheme, their classification performance is often unsatisfactory. In this article, a labeling privacy protection support vector machine using privileged information, called LPP-SVM-PI, is proposed to promote the accuracy of the classifier in infectious disease diagnosis. Based on the framework of the InvCal method, besides using the proportion information of the class label, the idea of learning using privileged information is also introduced to capture the additional information of groups. The slack variables in LPP-SVM-PI are represented as correcting function and projected into the correcting space so that the hidden information of training samples in groups is captured by relaxing the constraints of the classification model. The solution of LPP-SVM-PI can be transformed into a classic quadratic programming problem. The experimental dataset is collected from the Coronavirus disease 2019 (COVID-19) transcription polymerase chain reaction at Hospital Israelita Albert Einstein in Brazil. In the experiment, LPP-SVM-PI is efficiently applied for COVID-19 diagnosis.

Developing an Explainable Machine Learning-Based Thyroid Disease Prediction Model

Healthcare and medicine are key areas where machine learning algorithms are widely used. The medical decision support systems thus created are accurate enough, however, they suffer from the lack of transparency in decision making and shows a black box behavior. However, transparency and trust are significant in the field of health and medicine and hence, a black box system is sub optimal in terms of widespread applicability and reach. Hence, the explainablility of the research make the system reliable and understandable, thereby enhancing its social acceptability. The presented work explores a thyroid disease diagnosis system. SHAP, a popular method based on coalition game theory is used for interpretability of results. The work explains the system behavior both locally and globally and shows how machine leaning can be used to ascertain the causality of the disease and support doctors to suggest the most effective treatment of the disease. The work not only demonstrates the results of machine learning algorithms but also explains related feature importance and model insights.

Using a Deep Learning Model to Explore the Impact of Clinical Data on COVID-19 Diagnosis Using Chest X-ray

The coronavirus pandemic (COVID-19) is disrupting the entire world; its rapid global spread threatens to affect millions of people. Accurate and timely diagnosis of COVID-19 is essential to control the spread and alleviate risk. Due to the promising results achieved by integrating machine learning (ML), particularly deep learning (DL), in automating the multiple disease diagnosis process. In the current study, a model based on deep learning was proposed for the automated diagnosis of COVID-19 using chest X-ray images (CXR) and clinical data of the patient. The aim of this study is to investigate the effects of integrating clinical patient data with the CXR for automated COVID-19 diagnosis. The proposed model used data collected from King Fahad University Hospital, Dammam, KSA, which consists of 270 patient records. The experiments were carried out first with clinical data, second with the CXR, and finally with clinical data and CXR. The fusion technique was used to combine the clinical features and features extracted from images. The study found that integrating clinical data with the CXR improves diagnostic accuracy. Using the clinical data and the CXR, the model achieved an accuracy of 0.970, a recall of 0.986, a precision of 0.978, and an F-score of 0.982. Further validation was performed by comparing the performance of the proposed system with the diagnosis of an expert. Additionally, the results have shown that the proposed system can be used as a tool that can help the doctors in COVID-19 diagnosis.

Biomedical Applications of Metal−Organic Frameworks for Disease Diagnosis and Drug Delivery: A Review

Metal−organic frameworks (MOFs) are a novel class of porous hybrid organic−inorganic materials that have attracted increasing attention over the past decade. MOFs can be used in chemical engineering, materials science, and chemistry applications. Recently, these structures have been thoroughly studied as promising platforms for biomedical applications. Due to their unique physical and chemical properties, they are regarded as promising candidates for disease diagnosis and drug delivery. Their well-defined structure, high porosity, tunable frameworks, wide range of pore shapes, ultrahigh surface area, relatively low toxicity, and easy chemical functionalization have made them the focus of extensive research. This review highlights the up-to-date progress of MOFs as potential platforms for disease diagnosis and drug delivery for a wide range of diseases such as cancer, diabetes, neurological disorders, and ocular diseases. A brief description of the synthesis methods of MOFs is first presented. Various examples of MOF-based sensors and DDSs are introduced for the different diseases. Finally, the challenges and perspectives are discussed to provide context for the future development of MOFs as efficient platforms for disease diagnosis and drug delivery systems.

Novel CropdocNet Model for Automated Potato Late Blight Disease Detection from Unmanned Aerial Vehicle-Based Hyperspectral Imagery

The accurate and automated diagnosis of potato late blight disease, one of the most destructive potato diseases, is critical for precision agricultural control and management. Recent advances in remote sensing and deep learning offer the opportunity to address this challenge. This study proposes a novel end-to-end deep learning model (CropdocNet) for accurate and automated late blight disease diagnosis from UAV-based hyperspectral imagery. The proposed method considers the potential disease-specific reflectance radiation variance caused by the canopy’s structural diversity and introduces multiple capsule layers to model the part-to-whole relationship between spectral–spatial features and the target classes to represent the rotation invariance of the target classes in the feature space. We evaluate the proposed method with real UAV-based HSI data under controlled and natural field conditions. The effectiveness of the hierarchical features is quantitatively assessed and compared with the existing representative machine learning/deep learning methods on both testing and independent datasets. The experimental results show that the proposed model significantly improves accuracy when considering the hierarchical structure of spectral–spatial features, with average accuracies of 98.09% for the testing dataset and 95.75% for the independent dataset, respectively.

Nanomaterials-Based Urinary Extracellular Vesicles Isolation and Detection for Non-invasive Auxiliary Diagnosis of Prostate Cancer

Extracellular vesicles (EVs) are natural nanoparticles secreted by cells in the body and released into the extracellular environment. They are associated with various physiological or pathological processes, and considered as carriers in intercellular information transmission, so that EVs can be used as an important marker of liquid biopsy for disease diagnosis and prognosis. EVs are widely present in various body fluids, among which, urine is easy to obtain in large amount through non-invasive methods and has a small dynamic range of proteins, so it is a good object for studying EVs. However, most of the current isolation and detection of EVs still use traditional methods, which are of low purity, time consuming, and poor efficiency; therefore, more efficient and highly selective techniques are urgently needed. Recently, inspired by the nanoscale of EVs, platforms based on nanomaterials have been innovatively explored for isolation and detection of EVs from body fluids. These newly developed nanotechnologies, with higher selectivity and sensitivity, greatly improve the precision of isolation target EVs from urine. This review focuses on the nanomaterials used in isolation and detection of urinary EVs, discusses the advantages and disadvantages between traditional methods and nanomaterials-based platforms, and presents urinary EV-derived biomarkers for prostate cancer (PCa) diagnosis. We aim to provide a reference for researchers who want to carry out studies about nanomaterial-based platforms to identify urinary EVs, and we hope to summarize the biomarkers in downstream analysis of urinary EVs for auxiliary diagnosis of PCa disease in detail.

Effects of medical school on mental health and sleep habits

BACKGROUND and OBJECTIVES: This study aims to define changes in anxiety and depression among medical students while evaluating the association of sleep habits and other risk factors, including exercise habits and a diagnosis of chronic disease. The effect of the COVID-19 pandemic was also evaluated. DESIGN: A cohort of first- and second-year medical students was evaluated longitudinally using survey methods to quantify changes from pre-medical school and summer break to each semester in medical school throughout years one and two. METHODS: Data was analyzed using Generalized Linear Mixed Models (GLMMs) on the numeric responses of General Anxiety Disorder-7 (GAD-7), Patient Health Questionnaire-9 (PHQ-9), and Pittsburg Sleep Quality Index. Additional assessments evaluated exercise habits, chronic disease, and impact of COVID-19 Pandemic. RESULTS: Depression, anxiety, and sleep habits displayed a cyclical change that was associated with the academic cycle. The COVID-19 pandemic was never significant. Medical students who had a chronic disease diagnosis had increased severity. Exercise did not play a role. CONCLUSION: The main driver for depression, anxiety, and poor sleep quality was the academic cycle, while the COVID-19 pandemic did not have an impact on mental health.

Enhancement of the Detection Performance of Paper-Based Analytical Devices by Nanomaterials

Paper-based analytical devices (PADs), including lateral flow assays (LFAs), dipstick assays and microfluidic PADs (μPADs), have a great impact on the healthcare realm and environmental monitoring. This is especially evident in developing countries because PADs-based point-of-care testing (POCT) enables to rapidly determine various (bio)chemical analytes in a miniaturized, cost-effective and user-friendly manner. Low sensitivity and poor specificity are the main bottlenecks associated with PADs, which limit the entry of PADs into the real-life applications. The application of nanomaterials in PADs is showing great improvement in their detection performance in terms of sensitivity, selectivity and accuracy since the nanomaterials have unique physicochemical properties. In this review, the research progress on the nanomaterial-based PADs is summarized by highlighting representative recent publications. We mainly focus on the detection principles, the sensing mechanisms of how they work and applications in disease diagnosis, environmental monitoring and food safety management. In addition, the limitations and challenges associated with the development of nanomaterial-based PADs are discussed, and further directions in this research field are proposed.

Heart Sound Classification Based on Fractal Dimension and MFCC Features Using Hidden Markov Model

Early diagnosis is crucial in the treatment of heart diseases. Researchers have applied a variety of techniques for cardiovascular disease diagnosis, including the detection of heart sounds. It is an efficient and affordable diagnosis technique. Body organs, including the heart, generate several sounds. These sounds are different in different individuals. A number of methodologies have been recently proposed to detect and diagnose normal/abnormal sounds generated by the heart. The present study proposes a technique on the basis of the Mel-frequency cepstral coefficients, fractal dimension, and hidden Markov model. It uses the fractal dimension to identify sounds S1 and S2. Then, the Mel-frequency cepstral coefficients and the first- and second-order difference Mel-frequency cepstral coefficients are employed to extract the features of the signals. The adaptive Hemming window length is a major advantage of the methodology. The S1-S2 interval determines the adaptive length. Heart sounds are divided into normal and abnormal through the improved hidden Markov model and Baum-Welch and Viterbi algorithms. The proposed framework is evaluated using a number of datasets under various scenarios.