Supervised Machine Learning Models to Identify Early-Stage Symptoms of SARS-CoV-2 DOI Creative Commons
Ηλίας Δρίτσας, Μαρία Τρίγκα

Sensors, Journal Year: 2022, Volume and Issue: 23(1), P. 40 - 40

Published: Dec. 21, 2022

The coronavirus disease (COVID-19) pandemic was caused by the SARS-CoV-2 virus and began in December 2019. first reported Wuhan region of China. It is a new strain that until then had not been isolated humans. In severe cases, pneumonia, acute respiratory distress syndrome, multiple organ failure or even death may occur. Now, existence vaccines, antiviral drugs appropriate treatment are allies confrontation disease. present research work, we utilized supervised Machine Learning (ML) models to determine early-stage symptoms occurrence. For this purpose, experimented with several ML models, results showed ensemble model, namely Stacking, outperformed others, achieving an Accuracy, Precision, Recall F-Measure equal 90.9% Area Under Curve (AUC) 96.4%.

Language: Английский

Predicting the Occurrence of Metabolic Syndrome Using Machine Learning Models DOI Creative Commons
Μαρία Τρίγκα, Ηλίας Δρίτσας

Computation, Journal Year: 2023, Volume and Issue: 11(9), P. 170 - 170

Published: Sept. 3, 2023

The term metabolic syndrome describes the clinical coexistence of pathological disorders that can lead to development cardiovascular disease and diabetes in long term, which is why it now considered an initial stage above entities. Metabolic (MetSyn) closely associated with increased body weight, obesity, a sedentary lifestyle. necessity prevention early diagnosis imperative. In this research article, we experiment various supervised machine learning (ML) models predict risk developing MetSyn. addition, predictive ability accuracy using synthetic minority oversampling technique (SMOTE) are illustrated. evaluation ML highlights superiority stacking ensemble algorithm compared other algorithms, achieving 89.35%; precision, recall, F1 score values 0.898; area under curve (AUC) value 0.965 SMOTE 10-fold cross-validation.

Language: Английский

Citations

8
Kidney Failure Detection and Predictive Analytics for ckd Using Machine Learning Procedures DOI
Satyanarayana Murthy Nimmagadda,

Sowmya Sree Agasthi,

Abbas Shai

et al.

Archives of Computational Methods in Engineering, Journal Year: 2022, Volume and Issue: 30(4), P. 2341 - 2354

Published: Dec. 13, 2022

Language: Английский

Citations

13
Sentiment Analysis of TikTok Shop Closure in Indonesia on Twitter Using Supervised Machine Learning DOI Open Access

Noor Zalekha Al Habesyah,

Rudy Herteno, Fatma Indriani

et al.

Journal of Electronics Electromedical Engineering and Medical Informatics, Journal Year: 2024, Volume and Issue: 6(2), P. 148 - 156

Published: April 8, 2024

TikTok Shop is one of the features in application which facilitates users to buy and sell products. The integration with social media has provided new opportunities reach customers increase sales. However, closure caused controversy among public. This study aims analyze views responses Indonesia Shop. dataset used was obtained from Twitter. research methodology consists labeling, oversampling, splitting, machine learning, includes SVM, Random Forest, Decision Tree, Deep Learning (H2O). contribution this enriches our understanding implementation especially sentiment analysis closures. From test results, it known that (H2O) + SMOTE AUC 0.900, without using SMOTE, 0.867. SVM 0.885, 0.881. Forest 0.822, while 0.830. Tree 0.59; 0.646. produces better performance compared Tree. With an 0.900; can be said excellent for significant implications electronic commerce due its potential utilization by analysts.

Language: Английский

Citations

2
Enhancing machine learning-based forecasting of chronic renal disease with explainable AI DOI Creative Commons

Sanjana Singamsetty,

Swetha Ghanta,

S.K. Biswas

et al.

PeerJ Computer Science, Journal Year: 2024, Volume and Issue: 10, P. e2291 - e2291

Published: Sept. 26, 2024

Chronic renal disease (CRD) is a significant concern in the field of healthcare, highlighting crucial need early and accurate prediction order to provide prompt treatments enhance patient outcomes. This article presents an end-to-end predictive model for binary classification CRD addressing predictions Through hyperparameter optimization using GridSearchCV, we significantly improve performance. Leveraging range machine learning (ML) techniques, our approach achieves high accuracy 99.07% random forest, extra trees classifier, logistic regression with L2 penalty, artificial neural networks (ANN). rigorous evaluation, penalty emerges as top performer, demonstrating consistent Moreover, integration Explainable Artificial Intelligence (XAI) such Local Interpretable Model-agnostic Explanations (LIME) SHapley Additive exPlanations (SHAP), enhances interpretability reveals insights into decision-making. By emphasizing development process, from data collection deployment, system enables real-time informed healthcare decisions. comprehensive underscores potential modeling optimize clinical decision-making care

Language: Английский

Citations

2
Supervised Machine Learning Models to Identify Early-Stage Symptoms of SARS-CoV-2 DOI Creative Commons
Ηλίας Δρίτσας, Μαρία Τρίγκα

Sensors, Journal Year: 2022, Volume and Issue: 23(1), P. 40 - 40

Published: Dec. 21, 2022

The coronavirus disease (COVID-19) pandemic was caused by the SARS-CoV-2 virus and began in December 2019. first reported Wuhan region of China. It is a new strain that until then had not been isolated humans. In severe cases, pneumonia, acute respiratory distress syndrome, multiple organ failure or even death may occur. Now, existence vaccines, antiviral drugs appropriate treatment are allies confrontation disease. present research work, we utilized supervised Machine Learning (ML) models to determine early-stage symptoms occurrence. For this purpose, experimented with several ML models, results showed ensemble model, namely Stacking, outperformed others, achieving an Accuracy, Precision, Recall F-Measure equal 90.9% Area Under Curve (AUC) 96.4%.

Language: Английский

Citations

11