Electromagnetic Interaction Algorithm (EIA)-Based Feature Selection With Adaptive Kernel Attention Network (AKAttNet) for Autism Spectrum Disorder Classification.

Researchers created a new computer program that can help identify autism by analyzing data patterns. The program combines two advanced techniques to select the most important information and make accurate predictions. When tested on existing autism datasets, it performed better than traditional computer methods, correctly identifying autism cases 90-98% of the time. The system also works faster and uses less computer power than other approaches.

This computational study developed a novel machine learning approach combining the Electromagnetic Interaction Algorithm (EIA) for feature selection with an Adaptive Kernel Attention Network (AKAttNet) for autism spectrum disorder classification. The integrated framework was evaluated on four publicly available datasets and compared against traditional machine learning methods (logistic regression, SVM, random forest) and other deep learning models. The proposed method achieved high accuracy scores ranging from 0.901 to 0.9827, with Cohen's kappa values between 0.7789 and 0.9685 across datasets. The EIA algorithm effectively reduced feature dimensionality while maintaining performance, and the overall approach demonstrated lower computational time and enhanced generalizability compared to conventional methods.

While promising for computational screening, this approach requires clinical validation before implementation. The high accuracy and efficiency suggest potential as a supplementary diagnostic tool, but cannot replace comprehensive clinical assessment. Further research needed to evaluate performance with diverse populations and real-world clinical data.

Study uses only existing datasets without clinical validation. Sample sizes and dataset characteristics not reported. No comparison with actual clinical diagnostic processes. Limited information about real-world applicability and potential biases in training data.

Autism spectrum disorder (ASD) is a complex neurological condition that impacts cognitive, social and behavioural abilities. Early and accurate diagnosis is crucial for effective intervention and treatment. Traditional diagnostic methods lack accuracy, efficient feature selection and computational efficiency. This study proposes an integrated approach that combines the electromagnetic interaction algorithm (EIA) for feature selection with the adaptive kernel attention network (AKAttNet) for classification, aiming to improve ASD detection performance across multiple datasets.

The proposed methodology consists of two core components: (1) EIA, which optimises feature selection by identifying the most relevant attributes for ASD classification, and (2) AKAttNet, a deep learning model leveraging adaptive kernel attention mechanisms to enhance classification accuracy. The framework is evaluated using four publicly available ASD datasets. The classification performance of AKAttNet is compared against traditional machine learning methods, including logistic regression (LR), support vector machine (SVM) and random forest (RF), as well as competing deep learning models. Statistical evaluation includes precision, recall (sensitivity), specificity and overall accuracy metrics.

The proposed model outperforms conventional machine learning and deep learning approaches, demonstrating higher classification accuracy and robustness across multiple datasets. AKAttNet, combined with EIA-based feature selection, achieves an accuracy improvement ranging from 0.901 to 0.9827, Cohen's kappa values between 0.7789 and 0.9685 and Jaccard similarity scores from 0.8041 to 0.9709 across four different datasets. Comparative analysis highlights the efficiency of the EIA algorithm in reducing feature dimensionality while maintaining high model performance. Additionally, the proposed method exhibits lower computational time and enhanced generalizability, making it a promising approach for ASD detection.

This study presents a practical ASD detection framework integrating EIA for feature selection with AKAttNet for classification. The results indicate that this hybrid approach enhances diagnostic accuracy while reducing computational overhead, making it a promising tool for early ASD diagnosis. The findings support the potential of deep learning and optimisation techniques in developing more efficient and reliable ASD screening systems. Future work can explore real-world clinical applications and further refinement of the feature selection process.