Ensemble Learning for Disease Prediction: A Review

Healthcare, Journal Year: 2023, Volume and Issue: 11(12), P. 1808 - 1808

Published: June 20, 2023

Machine learning models are used to create and enhance various disease prediction frameworks. Ensemble is a machine technique that combines multiple classifiers improve performance by making more accurate predictions than single classifier. Although numerous studies have employed ensemble approaches for prediction, there lack of thorough assessment commonly against highly researched diseases. Consequently, this study aims identify significant trends in the accuracies techniques (i.e., bagging, boosting, stacking, voting) five hugely diseases diabetes, skin disease, kidney liver heart conditions). Using well-defined search strategy, we first identified 45 articles from current literature applied two or four any these were published 2016-2023. stacking has been fewest number times (23) compared with bagging (41) boosting (37), it showed most (19 out 23). The voting approach second-best approach, as revealed review. Stacking always reviewed diabetes. Bagging demonstrated best (five six times) diabetes (four times). results show greater accuracy other three candidate algorithms. Our also demonstrates variability perceived different frequently datasets. findings work will assist researchers better understanding hotspots employ learning, well determining suitable model predictive analytics. This article discusses

Language: Английский

---

Enhancing Heart Disease Prediction Accuracy through Machine Learning Techniques and Optimization

Processes, Journal Year: 2023, Volume and Issue: 11(4), P. 1210 - 1210

Published: April 14, 2023

In the medical domain, early identification of cardiovascular issues poses a significant challenge. This study enhances heart disease prediction accuracy using machine learning techniques. Six algorithms (random forest, K-nearest neighbor, logistic regression, Naïve Bayes, gradient boosting, and AdaBoost classifier) are utilized, with datasets from Cleveland IEEE Dataport. Optimizing model accuracy, GridsearchCV, five-fold cross-validation employed. dataset, regression surpassed others 90.16% while excelled in Dataport achieving 90% accuracy. A soft voting ensemble classifier combining all six further enhanced resulting 93.44% for dataset 95% dataset. performance classifiers on both datasets. study’s novelty lies use GridSearchCV hyperparameter optimization, determining best parameters model, assessing negative log loss metrics. also examined each fold to evaluate model’s benchmark The approach improved accuracies and, when compared existing studies, this method notably exceeded their results.

Language: Английский

---

An Improved Ensemble Learning Approach for Heart Disease Prediction Using Boosting Algorithms

Computer Systems Science and Engineering, Journal Year: 2023, Volume and Issue: 46(3), P. 3993 - 4006

Published: Jan. 1, 2023

Language: Английский

---

An Improved Ensemble-Based Cardiovascular Disease Detection System with Chi-Square Feature Selection

Computers, Journal Year: 2024, Volume and Issue: 13(6), P. 126 - 126

Published: May 22, 2024

Cardiovascular disease (CVD) is a leading cause of death globally; therefore, early detection CVD crucial. Many intelligent technologies, including deep learning and machine (ML), are being integrated into healthcare systems for prediction. This paper uses voting ensemble ML with chi-square feature selection to detect early. Our approach involved applying multiple classifiers, naïve Bayes, random forest, logistic regression (LR), k-nearest neighbor. These classifiers were evaluated through metrics accuracy, specificity, sensitivity, F1-score, confusion matrix, area under the curve (AUC). We created an model by combining predictions from different mechanism, whose performance was then measured against individual classifiers. Furthermore, we applied method 303 records across 13 clinical features in Cleveland cardiac dataset identify 5 most important features. improved overall accuracy our reduced computational load considerably more than 50%. Demonstrating superior effectiveness, achieved remarkable 92.11%, representing average improvement 2.95% over single highest classifier (LR). results indicate as viable practical improve

Language: Английский

---

A comparative evaluation of machine learning ensemble approaches for disease prediction using multiple datasets

Health and Technology, Journal Year: 2024, Volume and Issue: 14(3), P. 597 - 613

Published: March 27, 2024

Abstract Purpose Machine learning models are used to develop and improve various disease prediction systems. Ensemble is a machine technique that combines many classifiers increase performance by making more accurate predictions than single classifier. Although several researchers have employed ensemble techniques for prediction, comprehensive comparative study of these still needs be provided. Methods Using 16 datasets from Kaggle the UCI Learning Repository, this compares 15 variants prediction. The comparison was performed using six measures: accuracy, precision, recall, F1 score, AUC (Area Under receiver operating characteristics Curve) AUPRC Precision-Recall Curve). Results Stacking variant Multi-level stacking showed superior compared with other bagging boosting variants, followed another (Classical stacking). Overall, outperformed Logit Boost worst performance. Conclusion findings can help select an appropriate approach future studies focusing on

Language: Английский

---

Cloud computing-based framework for heart disease classification using quantum machine learning approach

Journal of Intelligent Systems, Journal Year: 2024, Volume and Issue: 33(1)

Published: Jan. 1, 2024

Abstract Accurate early identification and treatment of cardiovascular diseases can prevent heart failure problems reduce mortality rates. This study aims to use quantum learning predict increase the accuracy traditional prediction classification methods. Machine (ML) deep (DL) techniques need quickly accurately analyze massive volumes complex data. With computing, suggested DL ML algorithms change their predictions on basis changes in dataset. approach could help with accurate detection chronic diseases. The Cleveland disease dataset is undergoing preliminary processing validate missing values precision rate incorrect forecasts. examined feasibility employing deploying a (QML) framework via cloud computing categorize cardiac conditions. research was divided into four sections. First, principal component analysis used preprocess dataset, recursive feature elimination select features, min–max normalization give high-dimensional value. Second, we compared classifiers, such as support vector machine (SVM) artificial neural network, verify approach’s efficiency. Third, two unique QML methods: networks (QNNs) SVM (QSVM). Fourth, bagging-QSVM developed deployed an ensemble model. Experimental results using QNN show 77%, 76%, recall 73%, F 1 score 75%. 85%, 79%, 90%, 1-score 84%, QSVM method demonstrated much better performance than QNN. Particularly, Bagging_QSVM model exhibited outstanding performance, flawless 100% across all critical measures. shows that bagging for solid way increasing predictions.

Language: Английский

---

Cardiovascular disease detection using a novel stack-based ensemble classifier with aggregation layer, DOWA operator, and feature transformation

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 173, P. 108345 - 108345

Published: March 27, 2024

Language: Английский

---

A snake optimization algorithm-based feature selection framework for rapid detection of cardiovascular disease in its early stages

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 102, P. 107417 - 107417

Published: Dec. 24, 2024

Language: Английский

---

Advanced AI and Machine Learning Techniques for Time Series Analysis and Pattern Recognition

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(6), P. 3165 - 3165

Published: March 14, 2025

Time series analysis and pattern recognition are cornerstones for innovation across diverse domains. In finance, these techniques enable market prediction risk assessment. Astrophysicists use them to detect various phenomena analyze data. Environmental scientists track ecosystem changes pollution patterns, while healthcare professionals monitor patient vitals disease progression. Transportation systems optimize traffic flow predict maintenance needs. Energy providers balance grid loads forecast consumption. Climate model atmospheric extreme weather events. Cybersecurity experts identify threats through anomaly detection in network patterns. This editorial introduces this Special Issue, which explores state-of-the-art AI machine learning (ML) techniques, including Long Short-Term Memory (LSTM) networks, Transformers, ensemble methods, AutoML frameworks. We highlight innovative applications data-driven astrophysical event reconstruction, cloud masking, monitoring. Recent advancements feature engineering, unsupervised frameworks Transformer-based time forecasting demonstrate the potential of technologies. The papers collected Issue showcase how integrating domain-specific knowledge with computational innovations provides a pathway achieving higher accuracy scientific disciplines.

Language: Английский

---

Rolling force prediction during FGC process of tandem cold rolling based on IQGA-WNN ensemble learning

The International Journal of Advanced Manufacturing Technology, Journal Year: 2023, Volume and Issue: 125(5-6), P. 2869 - 2884

Published: Jan. 27, 2023

Language: Английский

---