What does this research mean for the field?

The proposed Voting ensemble method, which integrates hyperparameter-optimized classifiers, significantly improves stroke prediction accuracy while addressing data leakage and class imbalance issues. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The aim is to enhance stroke prediction reliability by addressing data leakage and class imbalance using ensemble learning and explainable AI techniques.

March 6, 20260 citationsOpen Access

Integrating Tuned Ensemble Learning and Explainable AI for Reliable Stroke Prediction

FYFatematuj zohura yasrinBangladesh University of Business and Technology MFMost. Jannatul FerdousBangladesh University of Business and Technology FFatemaBangladesh University of Business and Technology

Key Points

The aim is to enhance stroke prediction reliability by addressing data leakage and class imbalance using ensemble learning and explainable AI techniques.
Applied three balancing techniques to address class imbalance.
Utilized nine classification algorithms, including Random Forest, AdaBoost, and Logistic Regression.
Employed hyperparameter tuning for optimal model configuration.
Developed a novel ensemble method combining hyperparameter-optimized classifiers.
Used LIME and SHAP for feature interpretability.
The ensemble method showed improved performance metrics compared to individual models.
Mitigation of data leakage led to more reliable predictions.
Class imbalance techniques positively impacted model accuracy and precision.

Abstract

A stroke occurs due to a sudden interruption of blood flow to a specific region of the brain. Although extensiveresearch has already been conducted using this dataset, previous studies have not effectively addressed the issue of dataleakage during testing. The primary contribution of this study is to mitigate both the data leakage and class imbalanceproblems byapplying three different balancing techniques. We employed nine classification algorithms in this study: RandomForest (RF), AdaBoost (AB), Logistic Regression (LR), Gradient Boosting (GB), K-Nearest Neighbors (KN), Decision Tree(DT), Naive Bayes (NB), Voting (VT), and Stacking (ST). A key aspect of our approach involved using hyperparametertuning to determine the optimal configuration for each model. Additionally, we proposed a novel ensemble method, namedVoting, which combines hyperparameter-optimized LR, DT, GB, and RF classifiers. The performance of this method wascompared with other models using various evaluation metrics, including accuracy, precision, ROC curve, PR-AUC curve,and more. To enhance the interpretability of important features within the dataset, we also applied two explainable AI (XAI)techniques: Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP).

Ask AI

Helpful

Bookmark

View Full Paper