In recent years, much research has focused on using machine learning (ML) for disease prediction based on gene expression (GE) data. However, many diseases have received considerable attention, whereas some, including Alzheimer’s disease (AD), have not, perhaps due to data shortage. The present work is intended to fill this gap by introducing a symmetric framework to predict AD from GE data, with the aim to produce the most accurate prediction using the smallest number of genes. The framework works in four stages after it receives a training dataset: pre-processing, gene selection (GS), classification, and AD prediction. The symmetry of the model is manifested in all of its stages. In the pre-processing stage gene columns in the training dataset are pre-processed identically. In the GS stage, the same user-defined filter metrics are invoked on every gene individually, and so are the same user-defined wrapper metrics. In the classification stage, a number of user-defined ML models are applied identically using the minimal set of genes selected in the preceding stage. The core of the proposed framework is a meticulous GS algorithm which we have designed to nominate eight subsets of the original set of genes provided in the training dataset. Exploring the eight subsets, the algorithm selects the best one to describe AD, and also the best ML model to predict the disease using this subset. For credible results, the framework calculates performance metrics using repeated stratified k-fold cross validation. To evaluate the framework, we used an AD dataset of 1157 cases and 39,280 genes, obtained by combining a number of smaller public datasets. The cases were split in two partitions, 1000 for training/testing, using 10-fold CV repeated 30 times, and 157 for validation. From the testing/training phase, the framework identified only 1058 genes to be the most relevant and the support vector machine (SVM) model to be the most accurate with these genes. In the final validation, we used the 157 cases that were never seen by the SVM classifier. For credible performance evaluation, we evaluated the classifier via six metrics, for which we obtained impressive values. Specifically, we obtained 0.97, 0.97, 0.98, 0.945, 0.972, and 0.975 for the sensitivity (recall), specificity, precision, kappa index, AUC, and accuracy, respectively.

Gene expression (GE) classification is a research trend as it has been used to diagnose and prognosis many diseases. Employing machine learning (ML) in the prediction of many diseases based on GE data has been a flourishing research area. However, some diseases, like Alzheimer’s disease (AD), have not received considerable attention, probably owing to data scarcity obstacles. In this work, we shed light on the prediction of AD from GE data accurately using ML. Our approach consists of four phases: preprocessing, gene selection (GS), classification, and performance validation. In the preprocessing phase, gene columns are preprocessed identically. In the GS phase, a hybrid filtering method and embedded method are used. In the classification phase, three ML models are implemented using the bare minimum of the chosen genes obtained from the previous phase. The final phase is to validate the performance of these classifiers using different metrics. The crux of this article is to select the most informative genes from the hybrid method, and the best ML technique to predict AD using this minimal set of genes. Five different datasets are used to achieve our goal. We predict AD with impressive values for MultiLayer Perceptron (MLP) classifier which has the best performance metrics in four datasets, and the Support Vector Machine (SVM) achieves the highest performance values in only one dataset. We assessed the classifiers using seven metrics; and received impressive results, allowing for a credible performance rating. The metrics values we obtain in our study lie in the range [.97, .99] for the accuracy (Acc), [.97, .99] for F1-score, [.94, .98] for kappa index, [.97, .99] for area under curve (AUC), [.95, 1] for precision, [.98, .99] for sensitivity (recall), and [.98, 1] for specificity. With these results, the proposed approach outperforms recent interesting results. With these results, the proposed approach outperforms recent interesting results.

Selecting informative genes is essential for building accurate and efficient diagnostic models, especially for high-dimensional gene expression data such as those related to Alzheimer's disease. These datasets typically involve thousands of genes with limited samples, increasing the risk of overfitting and computational complexity. To address this, we propose a LASSO-HHO Gene Selection (LHGS) framework. LASSO is first applied to reduce dimensionality by filtering irrelevant genes. A conditional HHO-based optimization stage is then applied only when the LASSO-selected subset does not achieve sufficient accuracy or remains relatively large. Otherwise, the LASSO-selected features are directly used without further optimization. Experimental results show that the proposed method reduces the number of selected genes by up to 99.9% while maintaining high performance. The experimental results indicate that 100% accuracy can be achieved on specific datasets. In particular, GSE48350 and GSE36980 achieved 100% accuracy using LASSO alone, whereas GSE118553 and GSE132903 required the full LHGS framework to achieve the same performance. The framework also improves computational efficiency within a consistent experimental setup by reducing the optimization search space after LASSO filtering. Overall, LHGS provides a practical and efficient solution for gene selection in high-dimensional biomedical data.