A Genetic Folding Strategy Based Support Vector Machine to Optimize Lung Cancer Classification

Area of Science:

• Oncology
• Bioinformatics
• Artificial Intelligence

Background:

• Lung cancer exhibits significant heterogeneity, complicating genomic classification and targeted therapy development.
• Delayed diagnosis due to ambiguous symptoms and reliance on invasive procedures hinder effective lung cancer treatment.
• Artificial Intelligence (AI) and Machine Learning (ML) offer promising avenues for improving cancer classification and diagnosis.

Purpose of the Study:

• To develop and evaluate a novel Genetic Folding Strategy (GFS) model for enhanced lung cancer prediction.
• To improve the performance of Support Vector Machines (SVM) classification by integrating the GFS.
• To compare the GFS-SVM model's accuracy against traditional SVM kernels for lung cancer classification.

Main Methods:

• Development and implementation of a Genetic Folding Strategy (GFS) to enhance SVM kernel functions.
• Application of the GFS-enhanced SVM model to a real-world lung cancer dataset.
• Comparative analysis of classification performance using GFS-SVM against linear, polynomial, and radial basis function SVM kernels.

Main Results:

• The GFS-enhanced SVM model demonstrated superior performance in classifying lung cancer.
• Achieved a classification accuracy of 96.2% for lung cancer prediction using the GFS model.
• The GFS model significantly outperformed standard linear, polynomial, and radial basis function SVM kernels.

Conclusions:

• The proposed Genetic Folding Strategy (GFS) model offers a highly accurate method for lung cancer classification.
• This AI-driven approach holds potential for improving early lung cancer detection and guiding personalized treatment strategies.
• The GFS model represents a significant advancement in applying machine learning to oncological diagnostics.