Diagnosing Coronary Artery Disease on the Basis of Hard Ensemble Voting Optimization.

Background and Objectives: Recently, many studies have focused on the early diagnosis of coronary artery disease (CAD), which is one of the leading causes of cardiac-associated death worldwide. The effectiveness of the most important features influencing disease diagnosis determines the performance of machine learning systems that can allow for timely and accurate treatment. We performed a Hybrid ML framework based on hard ensemble voting optimization (HEVO) to classify patients with CAD using the Z-Alizadeh Sani dataset. All categorical features were converted to numerical forms, the synthetic minority oversampling technique (SMOTE) was employed to overcome imbalanced distribution between two classes in the dataset, and then, recursive feature elimination (RFE) with random forest (RF) was used to obtain the best subset of features. Materials and Methods: After solving the biased distribution in the CAD data set using the SMOTE method and finding the high correlation features that affected the classification of CAD patients. The performance of the proposed model was evaluated using grid search optimization, and the best hyperparameters were identified for developing four applications, namely, RF, AdaBoost, gradient-boosting, and extra trees based on an HEV classifier. Results: Five fold cross-validation experiments with the HEV classifier showed excellent prediction performance results with the 10 best balanced features obtained using SMOTE and feature selection. All evaluation metrics results reached > 98% with the HEV classifier, and the gradient-boosting model was the second best classification model with accuracy = 97% and F1-score = 98%. Conclusions: When compared to modern methods, the proposed method perform well in diagnosing coronary artery disease, and therefore, the proposed method can be used by medical personnel for supplementary therapy for timely, accurate, and efficient identification of CAD cases in suspected patients.

Real-time data of COVID-19 detection with IoT sensor tracking using artificial neural network.

The coronavirus pandemic has affected people all over the world and posed a great challenge to international health systems. To aid early detection of coronavirus disease-2019 (COVID-19), this study proposes a real-time detection system based on the Internet of Things framework. The system collects real-time data from users to determine potential coronavirus cases, analyses treatment responses for people who have been treated, and accurately collects and analyses the datasets. Artificial intelligence-based algorithms are an alternative decision-making solution to extract valuable information from clinical data. This study develops a deep learning optimisation system that can work with imbalanced datasets to improve the classification of patients. A synthetic minority oversampling technique is applied to solve the problem of imbalance, and a recursive feature elimination algorithm is used to determine the most effective features. After data balance and extraction of features, the data are split into training and testing sets for validating all models. The experimental predictive results indicate good stability and compatibility of the models with the data, providing maximum accuracy of 98% and precision of 97%. Finally, the developed models are demonstrated to handle data bias and achieve high classification accuracy for patients with COVID-19. The findings of this study may be useful for healthcare organisations to properly prioritise assets.

Hybrid Feature Selection Framework for the Parkinson Imbalanced Dataset Prediction Problem.

Background and Objectives: Recently, many studies have focused on the early detection of Parkinson's disease (PD). This disease belongs to a group of neurological problems that immediately affect brain cells and influence the movement, hearing, and various cognitive functions. Medical data sets are often not equally distributed in their classes and this gives a bias in the classification of patients. We performed a Hybrid feature selection framework that can deal with imbalanced datasets like PD. Use the SOMTE algorithm to deal with unbalanced datasets. Removing the contradiction from the features in the dataset and decrease the processing time by using Recursive Feature Elimination (RFE), and Principle Component Analysis (PCA). Materials and Methods: PD acoustic datasets and the characteristics of control subjects were used to construct classification models such as Bagging, K-nearest neighbour (KNN), multilayer perceptron, and the support vector machine (SVM). In the prepressing stage, the synthetic minority over-sampling technique (SMOTE) with two-feature selection RFE and PCA were used. The PD dataset comprises a large difference between the numbers of the infected and uninfected patients, which causes the classification bias problem. Therefore, SMOTE was used to resolve this problem. Results: For model evaluation, the train-test split technique was used for the experiment. All the models were Grid-search tuned, the evaluation results of the SVM model showed the highest accuracy of 98.2%, and the KNN model exhibited the highest specificity of 99%. Conclusions: the proposed method is compared with the current modern methods of detecting Parkinson's disease and other methods for medical diseases, it was noted that our developed system could treat data bias and reach a high prediction of PD and this can be beneficial for health organizations to properly prioritize assets.

Classification of melanonychia, Beau's lines, and nail clubbing based on nail images and transfer learning techniques.

Background: Nail diseases are malformations that appear on the nail plate and are classified according to their own signs and symptoms that may be related to other medical conditions. Although most nail diseases have distinct symptoms, making a differential diagnosis of nail problems can be challenging for medical experts. Method: One early diagnosis method for any dermatological disease is designing an image analysis system based on artificial intelligence (AI) techniques. This article implemented a novel model using a publicly available nail disease dataset to determine the occurrence of three common types of nail diseases. Two classification models based on transfer learning using visual geometry group (VGGNet) were utilized to detect and classify nail diseases from images. Result and Finding: The experimental design results showed good accuracy: VGG16 had a score of 94% accuracy and VGG19 had a 93% accuracy rate. These findings suggest that computer-aided diagnostic systems based on transfer learning can be used to identify multiple-lesion nail diseases.

Multi-objective deep learning framework for COVID-19 dataset problems.

Background: It has been reported that a deadly virus known as COVID-19 has arisen in China and has spread rapidly throughout the country. The globe was shattered, and a large number of people on the planet died. It quickly became an epidemic due to the absence of apparent symptoms and causes for patients, confusion appears due to the lack of sufficient laboratory results, and its intelligent algorithms were used to make decisions on clinical outcomes. Methods: This study developed a new framework for medical datasets with high missing values based on deep-learning optimization models. The robustness of our model is achieved by combining: Data Missing Care (DMC) Framework to overcome the problem of high missing data in medical datasets, and Grid-Search optimization used to develop an improved deep predictive training model for patients with COVID-19 by setting multiple hyperparameters and tuning assessments on three deep learning algorithms: ANN (Artificial Neural Network), CNN (Convolutional Neural Network), and Recurrent Neural Networks (RNN). Results: The experiment results conducted on three medical datasets showed the effectiveness of our hybrid approach and an improvement in accuracy and efficiency since all the evaluation metrics were close to ideal for all deep learning classifiers. We got the best evaluation in terms of accuracy 98%, precession 98.5%, F1-score 98.6%, and ROC Curve (95% to 99%) for the COVID-19 dataset provided by GitHub. The second dataset is also Covid-19 provided by Albert Einstein Hospital with high missing data after applying our approach the accuracy reached more than 91%. Third dataset for Cervical Cancer provided by Kaggle all the evaluation metrics reached more than 95%. Conclusions: The proposed formula for processing this type of data can replace the traditional formats in optimization while providing high accuracy and less time to classify patients. Whereas, the experimental results of our approach, supported by comprehensive statistical analysis, can improve the overall evaluation performance of the problem of classifying medical data sets with high missing values. Therefore, this approach can be used in many areas such as energy management, environment, and medicine.

Targeting SARS-CoV-2 Nsp12/Nsp8 interaction interface with approved and investigational drugs: an in silico structure-based approach.

In this study, the Nsp12-Nsp8 complex of SARS-CoV-2 was targeted with structure-based and computer-aided drug design approach because of its vital role in viral replication. Sequence analysis of RNA-dependent RNA polymerase (Nsp12) sequences from 30,366 different isolates were analysed for possible mutations. FDA-approved and investigational drugs were screened for interaction with both mutant and wild-type Nsp12-Nsp8 interfaces. Sequence analysis revealed that 70.42% of Nsp12 sequences showed conserved P323L mutation, located in the Nsp8 binding cleft. Compounds were screened for interface interaction, any with XP GScores lower than -7.0 kcal/mol were considered as possible interface inhibitors. RX-3117 (fluorocyclopentenyl cytosine) and Nebivolol had the highest binding affinities in both mutant and wild-type enzymes, therefore they were selected and resultant protein-ligand complexes were simulated for analysis of stability over 100 ns. Although the selected ligands had partial mobility in the binding cavity, they were not removed from the binding pocket after 100 ns. The ligand RX-3117 remained in the same position in the binding pocket of the mutant and wild-type enzyme after 100 ns MD simulation. However, the ligand Nebivolol folded and embedded in the binding pocket of mutant Nsp12 protein. Overall, FDA-approved and investigational drugs are able to bind to the Nsp12-Nsp8 interaction interface and prevent the formation of the Nsp12-Nsp8 complex. Interruption of viral replication by drugs proposed in this study should be further tested to pave the way for in vivo studies towards the treatment of COVID-19.Communicated by Ramaswamy H. Sarma.

Genomic chronicle of SARS-CoV-2: a mutational analysis with over 1 million genome sequences.

Use of information technologies to analyse big data on SARS-CoV-2 genome provides an insight for tracking variations and examining the evolution of the virus. Nevertheless, storing, processing, alignment and analyses of these numerous genomes are still a challenge. In this study, over 1 million SARS-CoV-2 genomes have been analysed to show distribution and relationship of variations that could enlighten development and evolution of the virus. In all genomes analysed in this study, a total of over 215M SNVs have been detected and average number of SNV per isolate was found to be 21.83. Single nucleotide variant (SNV) average is observed to reach 31.25 just in March 2021. The average variation number of isolates is increasing and compromising with total case numbers around the world. Remarkably, cytosine deamination, which is one of the most important biochemical processes in the evolutionary development of coronaviruses, accounts for 46% of all SNVs seen in SARS-CoV-2 genomes within 16 months. This study is one of the most comprehensive SARS-CoV-2 genomic analysis study in terms of number of genomes analysed in an academic publication so far, and reported results could be useful in monitoring the development of SARS-CoV-2.

An updated analysis of variations in SARS-CoV-2 genome.

A novel pathogen, named SARS-CoV-2, has caused an unprecedented worldwide pandemic in the first half of 2020. As the SARS-CoV-2 genome sequences have become available, one of the important focus of scientists has become tracking variations in the viral genome. In this study, 30366 SARS-CoV-2 isolate genomes were aligned using the software developed by our group (ODOTool) and 11 variations in SARS-CoV-2 genome over 10% of whole isolates were discussed. Results indicated that, frequency rates of these 11 variations change between 3.56%-88.44 % and these rates differ greatly depending on the continents they have been reported. Despite some variations being in low frequency rate in some continents, C14408T and A23403G variations on Nsp12 and S protein, respectively, observed to be the most prominent variations all over the world, in general, and both cause missense mutations. It is also notable that most of isolates carry C14408T and A23403 variations simultaneously and also nearly all isolates carrying the G25563T variation on ORF3a, also carry C14408T and A23403 variations, although their location distributions are not similar. All these data should be considered towards development of vaccine and antiviral treatment strategies as well as tracing diversity of virus in all over the world.

Evaluation of the potency of FDA-approved drugs on wild type and mutant SARS-CoV-2 helicase (Nsp13).

SARS-CoV-2 has caused COVID-19 outbreak with nearly 2 M infected people and over 100K death worldwide, until middle of April 2020. There is no confirmed drug for the treatment of COVID-19 yet. As the disease spread fast and threaten human life, repositioning of FDA approved drugs may provide fast options for treatment. In this aspect, structure-based drug design could be applied as a powerful approach in distinguishing the viral drug target regions from the host. Evaluation of variations in SARS-CoV-2 genome may ease finding specific drug targets in the viral genome. In this study, 3458 SARS-CoV-2 genome sequences isolated from all around the world were analyzed. Incidence of C17747T and A17858G mutations were observed to be much higher than others and they were on Nsp13, a vital enzyme of SARS-CoV-2. Effect of these mutations was evaluated on protein-drug interactions using in silico methods. The most potent drugs were found to interact with the key and neighbor residues of the active site responsible from ATP hydrolysis. As result, cangrelor, fludarabine, folic acid and polydatin were determined to be the most potent drugs which have potency to inhibit both the wild type and mutant SARS-CoV-2 helicase. Clinical data supporting these findings would be important towards overcoming COVID-19.