Shap-driven explainable AI with simulated annealing for optimized seizure detection using multichannel EEG signal

• Published in: Cognitive neurodynamics Vol. 19; no. 1; p. 85
• Main Authors: Dokare, Indu, Gupta, Sudha
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.12.2025; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Automation; Biochemistry; Biomedical and Life Sciences; Biomedicine; Cognitive Psychology; Computer Science; Convulsions & seizures; Datasets; Decision making; Decision trees; Decomposition; Discrete Wavelet Transform; EEG; Electroencephalography; Epilepsy; Explainable artificial intelligence; Feature extraction; Feature selection; Foraging behavior; Fourier transforms; Genetic algorithms; Heuristic methods; Machine learning; Methods; Neurosciences; Optimization; Optimization techniques; Research Article; Seizures; Sensitivity; Signal processing; Simulated annealing; Social behavior; Support vector machines; Wavelet transforms; Random forest; Multichannel EEG; Explainable artificial intelligence (XAI); Epilepsy; SHAP-RELFR; Simulated annealing
• ISSN: 1871-4080; 1871-4099; 1871-4099
• DOI: 10.1007/s11571-025-10269-3

The aim of this research is to combine Explainable AI (XAI) with advanced optimization techniques to provide a unique framework for seizure detection. This proposed work investigates how to enhance patient-specific and patient-non-specific seizure detection models by combining multiband feature extraction, SHAP-based feature selection, SMOTE, and a metaheuristic algorithm for hyperparameter tuning.The discrete wavelet transform (DWT) is used to decompose EEG signals to retrieve entropy-based and statistical information. Simulated Annealing (SA) is employed to optimize the Random Forest (RF) classifier’s hyperparameters, and SHAP (SHapley Additive exPlanations) values are utilized for feature selection. Furthermore, a novel technique SHAP-RELFR has been demonstrated to select patient-non-specific features. Additionally, SMOTE is employed to handle imbalanced data. The proposed methodology is evaluated on the CHB-MIT and Siena datasets using both patient-specific and patient-non-specific feature selection approaches. Experimental findings demonstrate that the proposed methodology significantly improves the performance of seizure detection. The average accuracy, precision, sensitivity, specificity, F1-score, and AUC obtained for a patient-non-specific case are 96.58%, 95.19%, 94.52%, 98.02%, 94.72%, and 0.9452, respectively, using the CHB-MIT dataset. For the Seina dataset, the average accuracy, precision, sensitivity, specificity, F1-score, and AUC obtained for a patient-non-specific case are 94.81%, 94.51%, 94.04%, 96.87%, 94.28%, and 0.9400, respectively. Explainable AI combined with SMOTE and a metaheuristic optimization algorithm facilitates an enhanced seizure detection. The novel SHAP-RELFR method provides an effective patient-non-specific feature selection, enabling this approach to be applicable across diverse patients. This proposed framework offers a step toward enhancing clinical decision-making by providing interpretable and versatile seizure detection models.