A machine learning approach towards assessing consistency and reproducibility: an application to graft survival across three kidney transplantation eras DOI Creative Commons
Okechinyere J. Achilonu, George Obaido, Blessing Ogbuokiri

и другие.

Frontiers in Digital Health, Год журнала: 2024, Номер 6

Опубликована: Сен. 3, 2024

Background In South Africa, between 1966 and 2014, there were three kidney transplant eras defined by evolving access to certain immunosuppressive therapies as Pre-CYA (before availability of cyclosporine), CYA (when cyclosporine became available), New-Gen (availability tacrolimus mycophenolic acid). As such, factors influencing graft failure may vary across these eras. Therefore, evaluating the consistency reproducibility models developed study variations using machine learning (ML) algorithms could enhance our understanding post-transplant survival dynamics Methods This explored effectiveness nine ML in predicting 10-year We internally validated data spanning specified The predictive performance was assessed area under curve (AUC) receiver operating characteristics (ROC), supported other evaluation metrics. employed local interpretable model-agnostic explanations provide detailed interpretations individual model predictions used permutation importance assess global feature each era. Results Overall, proportion decreased from 41.5% era 15.1% Our best-performing demonstrated high accuracy. Notably, ensemble models, particularly Extra Trees model, emerged standout performers, consistently achieving AUC scores 0.95, 0.97 indicates that achieved outcomes. Among features evaluated, recipient age donor only throughout eras, while such glomerular filtration rate ethnicity showed specific resulting relatively poor historical transportability best model. Conclusions emphasises significance analysing post-kidney outcomes identifying era-specific mitigating failure. proposed framework can serve a foundation for future research assist physicians patients at risk

Язык: Английский

A Survey of Decision Trees: Concepts, Algorithms, and Applications DOI Creative Commons
Ibomoiye Domor Mienye, Nobert Jere

IEEE Access, Год журнала: 2024, Номер 12, С. 86716 - 86727

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

36
Deep Learning for Credit Card Fraud Detection: A Review of Algorithms, Challenges, and Solutions DOI Creative Commons
Ibomoiye Domor Mienye, Nobert Jere

IEEE Access, Год журнала: 2024, Номер 12, С. 96893 - 96910

Опубликована: Янв. 1, 2024

Deep learning (DL), a branch of machine (ML), is the core technology in today's technological advancements and innovations. learning-based approaches are state-of-the-art methods used to analyse detect complex patterns large datasets, such as credit card transactions. However, most fraud models literature based on traditional ML algorithms, recently, there has been rise applications deep techniques. This study reviews recent DL-based presents concise description performance comparison widely DL techniques, including convolutional neural network (CNN), simple recurrent (RNN), long short-term memory (LSTM), gated unit (GRU). Additionally, an attempt made discuss suitable metrics, common challenges encountered when training using architectures potential solutions, which lacking previous studies would benefit researchers practitioners. Meanwhile, experimental results analysis real-world dataset indicate robustness detection.

Язык: Английский

Процитировано

24
Optimized Ensemble Learning Approach with Explainable AI for Improved Heart Disease Prediction DOI Creative Commons
Ibomoiye Domor Mienye, Nobert Jere

Information, Год журнала: 2024, Номер 15(7), С. 394 - 394

Опубликована: Июль 8, 2024

Recent advances in machine learning (ML) have shown great promise detecting heart disease. However, to ensure the clinical adoption of ML models, they must not only be generalizable and robust but also transparent explainable. Therefore, this research introduces an approach that integrates robustness ensemble algorithms with precision Bayesian optimization for hyperparameter tuning interpretability offered by Shapley additive explanations (SHAP). The classifiers considered include adaptive boosting (AdaBoost), random forest, extreme gradient (XGBoost). experimental results on Cleveland Framingham datasets demonstrate optimized XGBoost model achieved highest performance, specificity sensitivity values 0.971 0.989 dataset 0.921 0.975 dataset, respectively.

Язык: Английский

Процитировано

20
Supervised machine learning in drug discovery and development: Algorithms, applications, challenges, and prospects DOI Creative Commons
George Obaido, Ibomoiye Domor Mienye, Oluwaseun Francis Egbelowo

и другие.

Machine Learning with Applications, Год журнала: 2024, Номер 17, С. 100576 - 100576

Опубликована: Июль 24, 2024

Язык: Английский

Процитировано

20
A deep learning approach for Maize Lethal Necrosis and Maize Streak Virus disease detection DOI Creative Commons

Tony O’Halloran,

George Obaido,

Bunmi Otegbade

и другие.

Machine Learning with Applications, Год журнала: 2024, Номер 16, С. 100556 - 100556

Опубликована: Май 7, 2024

Maize is an important crop cultivated in Sub-Saharan Africa, essential for food security. However, its cultivation faces significant challenges due to debilitating diseases such as Lethal Necrosis (MLN) and Streak Virus (MSV), which can lead severe yield losses. Traditional plant disease diagnosis methods are often time-consuming prone errors, necessitating more efficient approaches. This study explores the application of deep learning, specifically Convolutional Neural Networks (CNNs), automatic detection classification maize diseases. We investigate six architectures: Basic CNN, EfficientNet V2 B0 B1, LeNet-5, VGG-16, ResNet50, using a dataset 15344 images comprising MSV, MLN, healthy leaves. Additionally, performed hyperparameter tuning improve performance models Gradient-weighted Class Activation Mapping (Grad-CAM) model interpretability. Our results show that demonstrated accuracy 99.99% distinguishing between disease-infected plants. The this contribute advancement AI applications agriculture, particularly diagnosing within Africa.

Язык: Английский

Процитировано

13
An Improved Framework for Detecting Thyroid Disease Using Filter-Based Feature Selection and Stacking Ensemble DOI Creative Commons
George Obaido, Okechinyere J. Achilonu, Blessing Ogbuokiri

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 89098 - 89112

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

9
A survey of explainable artificial intelligence in healthcare: Concepts, applications, and challenges DOI Creative Commons
Ibomoiye Domor Mienye, George Obaido, Nobert Jere

и другие.

Informatics in Medicine Unlocked, Год журнала: 2024, Номер unknown, С. 101587 - 101587

Опубликована: Окт. 1, 2024

Язык: Английский

Процитировано

4
ArsenicSkinNet: A Deep Learning Approach for Arsenicosis Skin Lesion Classification DOI

A Aakash,

Tony O’Halloran,

George Obaido

и другие.

Lecture notes in computer science, Год журнала: 2025, Номер unknown, С. 1 - 14

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Effective Credit Risk Prediction Using Ensemble Classifiers With Model Explanation DOI Creative Commons
Idowu Aruleba, Yanxia Sun

IEEE Access, Год журнала: 2024, Номер 12, С. 115015 - 115025

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

2
A machine learning approach towards assessing consistency and reproducibility: an application to graft survival across three kidney transplantation eras DOI Creative Commons
Okechinyere J. Achilonu, George Obaido, Blessing Ogbuokiri

и другие.

Frontiers in Digital Health, Год журнала: 2024, Номер 6

Опубликована: Сен. 3, 2024

Background In South Africa, between 1966 and 2014, there were three kidney transplant eras defined by evolving access to certain immunosuppressive therapies as Pre-CYA (before availability of cyclosporine), CYA (when cyclosporine became available), New-Gen (availability tacrolimus mycophenolic acid). As such, factors influencing graft failure may vary across these eras. Therefore, evaluating the consistency reproducibility models developed study variations using machine learning (ML) algorithms could enhance our understanding post-transplant survival dynamics Methods This explored effectiveness nine ML in predicting 10-year We internally validated data spanning specified The predictive performance was assessed area under curve (AUC) receiver operating characteristics (ROC), supported other evaluation metrics. employed local interpretable model-agnostic explanations provide detailed interpretations individual model predictions used permutation importance assess global feature each era. Results Overall, proportion decreased from 41.5% era 15.1% Our best-performing demonstrated high accuracy. Notably, ensemble models, particularly Extra Trees model, emerged standout performers, consistently achieving AUC scores 0.95, 0.97 indicates that achieved outcomes. Among features evaluated, recipient age donor only throughout eras, while such glomerular filtration rate ethnicity showed specific resulting relatively poor historical transportability best model. Conclusions emphasises significance analysing post-kidney outcomes identifying era-specific mitigating failure. proposed framework can serve a foundation for future research assist physicians patients at risk

Язык: Английский

Процитировано

0