An Enhanced Ant Colony Optimization Mechanism for the Classification of Depressive Disorders

• Published in: Computational intelligence and neuroscience Vol. 2022; pp. 1 - 12
• Main Authors: Saif Alghawli, Abed, Taloba, Ahmed I.
• Format: Journal Article
• Language: English
• Published: United States Hindawi 28.06.2022; John Wiley & Sons, Inc
• Subjects: Accuracy; Affective disorders; Algorithms; Ant colony optimization; Biomarkers; Bipolar disorder; Bipolar Disorder - diagnosis; Brain research; Classification; Convulsions & seizures; Datasets; Decision making; Depression, Mental; Depressive Disorder, Major - diagnosis; Diagnosis; Estimates; Feature extraction; Feature selection; Genetic algorithms; Humans; Machine learning; Medical imaging; Mental depression; Mental disorders; Optimization; Particle swarm optimization; Patients; Signal processing; Support Vector Machine; Support vector machines
• ISSN: 1687-5265; 1687-5273; 1687-5273
• DOI: 10.1155/2022/1332664

Bipolar disorder is marked by mood swings that alternate between mania and depression. The stages of bipolar disorder (BD), as one of the most common mental conditions, are often misdiagnosed as major depressive disorder (MDD), resulting in ineffective treatment and a poor prognosis. As a result, distinguishing MDD from BD at an earlier phase of the disease may aid in more efficient and targeted treatments. In this research, an enhanced ACO (IACO) technique biologically inspired by and following the required ant colony optimization (ACO) was utilized to minimize the number of features by deleting unrelated or redundant feature data. To distinguish MDD and BD individuals, the selected features were loaded into a support vector machine (SVM), a sophisticated mathematical technique for classification process, regression, functional estimates, and modeling operations. In respect of classifications efficiency and frequency of features extracted, the performance of the IACO method was linked to that of regular ACO, particle swarm optimization (PSO), and genetic algorithm (GA) techniques. The validation was performed using a nested cross-validation (CV) approach to produce nearly reliable estimates of classification error.