Hypertension Detection via Tree-Based Stack Ensemble with SMOTE-Tomek Data Balance and XGBoost Meta-Learner DOI Creative Commons
Christopher Chukwufunaya Odiakaose,

Fidelis Obukohwo Aghware,

Margaret Dumebi Okpor

et al.

Journal of Future Artificial Intelligence and Technologies, Journal Year: 2024, Volume and Issue: 1(3), P. 269 - 283

Published: Dec. 1, 2024

High blood pressure (or hypertension) is a causative disorder to plethora of other ailments – as it succinctly masks ailments, making them difficult diagnose and manage with targeted treatment plan effectively. While some patients living elevated high can effectively their condition via adjusted lifestyle monitoring follow-up treatments, Others in self-denial leads unreported instances, mishandled cases, now rampant cases result death. Even the usage machine learning schemes medicine, two (2) significant issues abound, namely: (a) utilization dataset construction model, which often yields non-perfect scores, (b) exploration complex deep models have yielded improved accuracy, requires large dataset. To curb these issues, our study explores tree-based stacking ensemble Decision tree, Adaptive Boosting, Random Forest (base learners) while we explore XGBoost meta-learner. With Kaggle retrieved, prediction accuracy 1.00 an F1-score that correctly classified all instances test

Language: Английский

Ensemble learning with explainable AI for improved heart disease prediction based on multiple datasets DOI Creative Commons
Shahid Mohammad Ganie, Pijush Kanti Dutta Pramanik, Zhongming Zhao

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 22, 2025

Heart disease is one of the leading causes death worldwide. Predicting and detecting heart early crucial, as it allows medical professionals to take appropriate necessary actions at earlier stages. Healthcare can diagnose cardiac conditions more accurately by applying machine learning technology. This study aimed enhance prediction using stacking voting ensemble methods. Fifteen base models were trained on two different datasets. After evaluating various combinations, six pipelined develop employing a meta-model (stacking) majority vote (voting). The performance was compared that individual models. To ensure robustness evaluation, we conducted statistical analysis Friedman aligned ranks test Holm post-hoc pairwise comparisons. results indicated developed models, particularly stacking, consistently outperformed other achieving higher accuracy improved predictive outcomes. rigorous validation emphasised reliability proposed Furthermore, incorporated explainable AI (XAI) through SHAP interpret model predictions, providing transparency insight into how features influence prediction. These findings suggest combining predictions multiple or may serve valuable tool in clinical decision-making.

Language: Английский

Citations

1
Citrus diseases detection using innovative deep learning approach and Hybrid Meta-Heuristic DOI Creative Commons
N. M. Butt, Muhammad Munwar Iqbal, Shabana Ramzan

et al.

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(1), P. e0316081 - e0316081

Published: Jan. 22, 2025

Citrus farming is one of the major agricultural sectors Pakistan and currently represents almost 30% total fruit production, with its highest concentration in Punjab. Although economically important, citrus crops like sweet orange, grapefruit, lemon, mandarins face various diseases canker, scab, black spot, which lower quality yield. Traditional manual disease diagnosis not only slow, less accurate, expensive but also relies heavily on expert intervention. To address these issues, this research examines implementation an automated classification system using deep learning optimal feature selection. The incorporates data augmentation transfer pre-trained models such as DenseNet-201 AlexNet to improve diagnostic accuracy, efficiency, cost-effectiveness. Experimental results a leaves dataset show impressive 99.6% accuracy. proposed framework outperforms existing methods, offering robust scalable solution for detection farming, contributing more sustainable practices.

Language: Английский

Citations

0
Automated classification of thyroid disease using deep learning with neuroevolution model training DOI

Mohammad Rashid Dubayan,

Sara Ershadi-Nasab, Mariam Zomorodi‐Moghadam

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 146, P. 110209 - 110209

Published: Feb. 13, 2025

Language: Английский

Citations

0
Hypertension Detection via Tree-Based Stack Ensemble with SMOTE-Tomek Data Balance and XGBoost Meta-Learner DOI Creative Commons
Christopher Chukwufunaya Odiakaose,

Fidelis Obukohwo Aghware,

Margaret Dumebi Okpor

et al.

Journal of Future Artificial Intelligence and Technologies, Journal Year: 2024, Volume and Issue: 1(3), P. 269 - 283

Published: Dec. 1, 2024

High blood pressure (or hypertension) is a causative disorder to plethora of other ailments – as it succinctly masks ailments, making them difficult diagnose and manage with targeted treatment plan effectively. While some patients living elevated high can effectively their condition via adjusted lifestyle monitoring follow-up treatments, Others in self-denial leads unreported instances, mishandled cases, now rampant cases result death. Even the usage machine learning schemes medicine, two (2) significant issues abound, namely: (a) utilization dataset construction model, which often yields non-perfect scores, (b) exploration complex deep models have yielded improved accuracy, requires large dataset. To curb these issues, our study explores tree-based stacking ensemble Decision tree, Adaptive Boosting, Random Forest (base learners) while we explore XGBoost meta-learner. With Kaggle retrieved, prediction accuracy 1.00 an F1-score that correctly classified all instances test

Language: Английский

Citations

0