Ant Colony Optimization–Rain Optimization Algorithm Based on Hybrid Deep Learning for Diagnosis of Lung Involvement in Coronavirus Patients

With today's rapid increase in population, automatic diagnosis of disease has emerged as a critical subject in the field of medicine. An automatic disease detection framework gives correct, accurate, and rapid outputs, supporting clinicians in making accurate diagnoses while also reducing the number of deaths from disease. This paper aims to develop a system for detecting anomalies, and to reach this objective, various concepts of machine learning, for example, support vector machines, are employed for the construction of a detection system with a deep learning algorithm, termed long short-term memory. Accordingly, the study proposes an approach for detecting lung involvement. A dataset consisting of 4575 CT scan pictures, of which 1525 were from the COVID-19 virus, was employed in the current investigation. The proposed system attained 99.9487% accuracy, 99.9485% specificity, 99.9485% sensitivity, and a 99.8787% F1-score based on experimental results. Based on the data provided, the system was able to accomplish the expected results. The experimental findings highlight the favorable features in improving classification accuracy and selecting the best attributes. The method thus shows promise as a convenient diagnostic tool to aid physicians in clinical decision-making.