Enhancing lung cancer prediction through crow search, artificial bee colony algorithms, and support vector machine

Abstract

Lung cancer is one of the leading causes of death worldwide. According to statistics from the World Health Organization (WHO) for the year 2020, lung cancer has caused the death of about 1.80 million people. It is the most common form of cancer, and it is often diagnosed in later stages when metastatic spread to other areas of the body has occurred. Early detection and treatment can help reduce the high death rate. In this research, we present a novel approach for predicting lung cancer using artificial intelligence (AI) techniques. We evaluated and compared several machine learning (ML) models, including artificial neural networks (ANN), K-nearest neighbors (KNN), and support vector machine (SVM), to identify the best-performing model. However, to enhance accuracy and efficiency, we introduced a hybridization optimization approach known as Crow Search Algorithm -Artificial Bee Colony-Support Vector Machine (CSABC-SVM). The CSABC-SVM algorithm combines the strengths of the CSABC Optimizer and SVM to create a powerful predictive model. Our study yielded a remarkable accuracy of 98.36%, demonstrating the effectiveness of the CSABC-SVM hybrid model in lung cancer prediction. These results underscore the potential of AI in transforming medical diagnostics, helping to improve healthcare outcomes