• Confusion-based voting
• Ensemble classier
• Grey Wolf
• Monkeypox
• Neural network

• Mpox, Monkeypox/diagnosis
• Humans
• COVID-19/diagnosis
• SARS-CoV-2/isolation & purification
• Algorithms
• Monkeypox virus

• Project #11202202 This work supported by the Center for Equitable Artificial Intelligence and Machine Learning Systems (CEAMLS), Morgan State University, Project #11202202, Morgan State University

• Computed tomography
• Machine learning
• Non-small cell lung cancer
• Radiomics
• Subcarinal lymph node metastasis

• Humans
• Carcinoma, Non-Small-Cell Lung/diagnostic imaging
• Carcinoma, Non-Small-Cell Lung/pathology
• Carcinoma, Non-Small-Cell Lung/surgery
• Carcinoma, Non-Small-Cell Lung/secondary
• Lung Neoplasms/diagnostic imaging
• Lung Neoplasms/pathology
• Lung Neoplasms/surgery
• Machine Learning
• Male
• Female
• Retrospective Studies
• Lymphatic Metastasis
• Tomography, X-Ray Computed/methods
• Middle Aged
• Aged
• Follow-Up Studies
• Prognosis
• Adult
• Lymph Nodes/pathology
• Lymph Nodes/diagnostic imaging
• Lymph Nodes/surgery
• Aged, 80 and over
• Lymph Node Excision
• Pneumonectomy
• Radiomics

• S202210634084 the College Students' Innovative Entrepreneurial Training Plan Program in Sichuan Province

• image segmentation
• labeled patches
• mouse eye in vivo
• optical coherence tomography

• Tomography, Optical Coherence/methods
• Animals
• Mice
• Bayes Theorem
• Algorithms
• Image Processing, Computer-Assisted/methods
• Eye/diagnostic imaging

• Humans
• COVID-19/diagnostic imaging
• COVID-19 Testing
• Artificial Intelligence
• Deep Learning
• Neural Networks, Computer

• COVID-19
• classification
• data preprocessing
• feature selection
• machine learning

• BGWO
• Covid-19
• Diagnosis
• Feature selection
• KNN
• NB

• Mansoura University

• COVID‐19
• K‐nearest neighbors
• Naive Bayes
• decision tree
• machine learning
• random forest

• Fasa University of Medical Sciences

• COVID-19 diagnosis
• Chest X-rays
• Chimp Optimization Algorithm
• Convolutional neural networks
• Deep learning
• Machine learning

• COVID-19 diagnosis
• Chest X-rays
• Chimp Optimization Algorithm
• Convolutional neural networks
• Deep learning
• Machine learning

• ANN + orthogonal vector plans
• ML algorithms
• hyperinsulinemia

• Covid-19
• NetLogo
• Situation-awareness
• ambient intelligence
• belief-desire-intention (BDI)
• healthcare

• CNN
• COVID-19
• Chest X-Ray
• Cloud computing
• DCNN

• Artificial Intelligence
• COVID-19
• Classification
• Data mining
• Machine Learning

For patients with stage T1-T2 esophageal squamous cell carcinoma (ESCC), accurately predicting lymph node metastasis (LNM) remains challenging. We aimed to investigate the performance of machine learning (ML) models for predicting LNM in patients with stage T1-T2 ESCC.

Patients with T1-T2 ESCC at three centers between January 2014 and December 2019 were included in this retrospective study and divided into training and external test sets. All patients underwent esophagectomy and were pathologically examined to determine the LNM status. Thirty-six ML models were developed using six modeling algorithms and six feature selection techniques. The optimal model was determined by the bootstrap method. An external test set was used to further assess the model’s generalizability and effectiveness. To evaluate prediction performance, the area under the receiver operating characteristic curve (AUC) was applied.

Of the 1097 included patients, 294 (26.8%) had LNM. The ML models based on clinical features showed good predictive performance for LNM status, with a median bootstrapped AUC of 0.659 (range: 0.592, 0.715). The optimal model using the naive Bayes algorithm with feature selection by determination coefficient had the highest AUC of 0.715 (95% CI: 0.671, 0.763). In the external test set, the optimal ML model achieved an AUC of 0.752 (95% CI: 0.674, 0.829), which was superior to that of T stage (0.624, 95% CI: 0.547, 0.701).

ML models provide good LNM prediction value for stage T1-T2 ESCC patients, and the naive Bayes algorithm with feature selection by determination coefficient performed best.

• Covid-19
• Naïve Bayes
• Prediction
• Prudential Expectation

• Anesthesia
• Bayes Theorem
• Dexmedetomidine/pharmacology
• Heart Rate
• Humans
• Hypnotics and Sedatives/pharmacology
• Hypnotics and Sedatives/therapeutic use

• COVID-19
• feature selection
• imbalanced data
• machine learning
• predictive model

• COVID-19/epidemiology
• Humans
• Machine Learning
• Neural Networks, Computer
• Pandemics
• SARS-CoV-2

• Consejo Nacional de Ciencia y Tecnología

There are more than 228,394,572 confirmed cases and 4,690,186 confirmed deaths caused by COVID-19 worldwide. The magnitude of the COOVID-19 pandemic has stimulated research on the treatment and diagnosis of COVID-19 patients.

In this report, a battery of specific parameters was used to develop a model that allows prediction of the outcome of the COVID-19 treatment. These parameters are C-reactive protein, procalcitonin, fibrinogen, D-dimers, immature granulocytes, and interleukin-6.

The study was carried out on a sample of N = 49 survivors (22 men, 27 women) and 83 deceased patients (62 men, 21 women). The distribution of means and differences in means of the parameters studied between survivors and deceased patients were evaluated using the bootstrap method.

A mathematical model that allows for the prediction of hospitalization outcome was obtained using the Naive Bayes model. The results demonstrated a statistically significant difference between survivors and deceased patients in all parameters studied. A mathematical model employing a battery of parameters provided a 97% precision in predicting the outcome of hospitalization.

This study showed that the cross-correlation of survivability with absolute levels of C-reactive protein, procalcitonin, fibrinogen, D-dimers, immature granulocytes, and interleukin-6 could be used successfully in the hospital setting as a diagnostic tool.

• C-reactive protein
• Covid-19
• D-dimers
• biological markers
• fibrinogen
• immature granulocytes
• interleukin-6
• procalcitonin

Because vaccine hesitancy is a dynamic trait, it is critical to identify and compare the contributing factors at the different stages of a pandemic. The prediction of vaccine decision making and the interpretation of the analytical relationships among variables that encompass public perceptions and attitudes towards the COVID-19 pandemic have been extensively limited to the studies conducted after the administration of the first FDA-approved vaccine in December of 2020. In order to fill the gap in the literature, we used six predictive models and identified the most important factors, via Gini importance measures, that contribute to the prediction of COVID-19 vaccine acceptors and refusers using a nationwide survey that was administered in November 2020, before the widespread use of COVID-19 vaccines. Concerns about (re)contracting COVID-19 and opinions regarding mandatory face covering were identified as the most important predictors of vaccine decision making. By investigating the vaccine acceptors and refusers before the introduction of COVID-19 vaccines, we can help public health officials design and deliver individually tailored and dynamic vaccination programs that can increase the overall vaccine uptake.

• COVID-19 vaccination
• mask mandate
• predictive modeling
• vaccine hesitancy

Clinical methods are used for diagnosing COVID-19 infected patients, but reports posit that, several people who were initially tested positive of COVID-19, and who had some underlying diseases, turned out having negative results after further tests. Therefore, the performance of clinical methods is not always guaranteed. Moreover, chest X-ray image data of COVID-19 infected patients are mostly used in the computational models for COVID-19 diagnosis, while the use of common symptoms, such as fever, cough, fatigue, muscle aches, headache, etc. in computational models is not yet reported. In this study, we employed seven classification algorithms to empirically test and verify their efficacy when applied to diagnose COVID-19 using the aforementioned symptoms. We experimented with Logistic Regression (LR), Support Vector Machine (SVM), Naïve Byes (NB), Decision Tree (DT), Multilayer Perceptron (MLP), Fuzzy Cognitive Map (FCM) and Deep Neural Network (DNN) algorithms. The techniques were subjected to random undersampling and oversampling. Our results showed that with class imbalance, MLP and DNN outperform others. However, without class imbalance, MLP, FCM and DNN outperform others with the use of random undersampling, but DNN has the best performance by utilizing random oversampling. This study identified MLP, FCM and DNN as better classifiers over LR, NB, DT and SVM, so that healthcare software system developers can adopt them to develop intelligence-based expert systems which both medical personnel and patients can use for differential diagnosis of COVID-19 based on the aforementioned symptoms. However, the test of performance must not be limited to the traditional performance metrics.

• infection
• health care

• COVID-19/blood
• COVID-19/diagnosis
• COVID-19 Testing/methods
• Datasets as Topic
• Deep Learning
• Hematologic Tests
• Humans
• Mass Screening/methods
• ROC Curve

• Applications of AI
• Artificial intelligence
• COVID-19
• Deep learning
• Machine learning

• Feature selection
• Hyper-heuristics
• Metaheuristic algorithm
• Optimization
• Text classification