Chronic kidney Disease Classification through Hybrid Feature Selection and Ensemble Deep Learning

International Journal of Statistics in Medical Research, Journal Year: 2025, Volume and Issue: 14, P. 109 - 117

Published: March 3, 2025

Diagnosing and treating at-risk patients for chronic kidney disease (CKD) relies heavily on accurately classifying the disease. The use of deep learning models in healthcare research is receiving much interest due to recent developments field. CKD has many features; however, only some features contribute weightage classification task. Therefore, it required eliminate irrelevant feature before applying This paper proposed a hybrid selection method by combining two techniques: Boruta Recursive Feature Elimination (RFE) method. are ranked according their importance using algorithm refined set RFE, which recursively eliminates least important features. removes with low recursive score. Later, selected given input ensemble classification. experimental model compared Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF) without selection. When used, improves accuracy 2%. Experimental results found that these features, age, pus cell clumps, bacteria, coronary artery disease, do not accurate tasks. Accuracy, precision, recall used evaluate model.

Language: Английский

---

Sustainable Management of Major Fungal Phytopathogens in Sorghum (Sorghum bicolor L.) for Food Security: A Comprehensive Review

Journal of Fungi, Journal Year: 2025, Volume and Issue: 11(3), P. 207 - 207

Published: March 6, 2025

Sorghum (Sorghum bicolor L.) is a globally important energy and food crop that becoming increasingly integral to security the environment. However, its production significantly hampered by various fungal phytopathogens affect yield quality. This review aimed provide comprehensive overview of major affecting sorghum, their impact, current management strategies, potential future directions. The diseases covered include anthracnose, grain mold complex, charcoal rot, downy mildew, rust, with an emphasis on pathogenesis, symptomatology, overall economic, social, environmental impacts. From initial use fungicides shift biocontrol, rotation, intercropping, modern tactics breeding resistant cultivars against mentioned are discussed. In addition, this explores disease management, particular focus role technology, including digital agriculture, predictive modeling, remote sensing, IoT devices, in early warning, detection, management. It also key policy recommendations support farmers advance research thus emphasizing need for increased investment research, strengthening extension services, facilitating access necessary inputs, implementing effective regulatory policies. concluded although pose significant challenges, combined effort innovative policies can mitigate these issues, enhance resilience sorghum facilitate global issues.

Language: Английский

---

Artificial Intelligence in the Healthcare Sector: Possibilities and Problems

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 18

Published: Jan. 1, 2025

Language: Английский

---

Snake-Efficient Feature Selection-Based Framework for Precise Early Detection of Chronic Kidney Disease

Diagnostics, Journal Year: 2023, Volume and Issue: 13(15), P. 2501 - 2501

Published: July 27, 2023

Chronic kidney disease (CKD) refers to impairment of the kidneys that may worsen over time. Early detection CKD is crucial for saving millions lives. As a result, several studies are currently focused on developing computer-aided systems detect in its early stages. Manual screening time-consuming and subject personal judgment. Therefore, methods based machine learning (ML) automatic feature selection used support graders. The goal identify most relevant informative subset features given dataset. This approach helps mitigate curse dimensionality, reduce enhance model performance. use natural-inspired optimization algorithms has been widely adopted develop appropriate representations complex problems by conducting blackbox process without explicitly formulating mathematical formulations. Recently, snake have developed optimal or near-optimal solutions difficult mimicking behavior snakes during hunting. objective this paper novel snake-optimized framework named CKD-SO data analysis. To select classify suitable medical data, five deployed, along with (SO) algorithm, create an extremely accurate prediction liver disease. end result can 99.7% accuracy. These results contribute our understanding preparation pipeline. Furthermore, implementing method will enable health achieve effective prevention providing interventions high burden CKD-related diseases mortality.

Language: Английский

---

Optimizing Heart Attack Prediction Through OHE2LM: A Hybrid Modelling Strategy

Deleted Journal, Journal Year: 2024, Volume and Issue: 20(1), P. 66 - 75

Published: Jan. 25, 2024

Predicting heart attacks stands as a significant concern contributing to global morbidity. Within clinical data analysis, cardiovascular disease emerges pivotal focus for forecasting, wherein Data Science and machine learning (ML) offer invaluable tools. These methodologies aid in predicting by considering various risk factors Just like high blood pressure, increased cholesterol levels, irregular pulse rates, diabetes, this research aims enhance the accuracy of through techniques.This study introduces MLdriven approach, termed ML-ELM, dedicated forecasting analysing diverse factors. The proposed ML-ELM model is compared with alternative Utilizing techniques Support Vector Machines, Logistic Regression, Naïve Bayes, XGBoost key aspect exploration into different approaches predictive modeling., part strategy. dataset utilized symptoms sourced from UCI ML Repository. outcomes reveal that our has demonstrated superior performance among tested. models show notable efficiency identifying attack symptoms, particularly boosting algorithms. Accuracy assessments were employed gauge ability, Our suggested an outstanding rate 96.77%.

Language: Английский

---