Role of Automated Machine Learning approach for lung cancer data classification using modern techniques
Abstract
Medical data classification is the process for categorizing healthcare-related information, such as patient records, medical images, and diagnostic results, into distinct groups based on predefined criteria. Machine learning plays a pivotal role by classifying the medical data. Machine learning and deep learning techniques have become indispensable tools in precision healthcare and automated disease diagnosis, enabling accurate clinical decision-making and predictive analytics [22,23,27]. leveraging algorithms that can detect pattern automatically from the data and can make predictions with less human interference. ML models unlike traditional method analyze vast amount of medical data, recognize complex patterns , and generalize new cases according to learning., This paper therefore seeks to produce informed and precise medical data classification strategy for Lung cancer datasets. For lung cancer data classification Machine learning algorithms like Support vector machine(SVM), Convolutional Neural Networks(CNN), Residual Neural Network(ResNet), and Random Forest(RF) are used in this research paper due to their ability to extract meaningful features from medical images and clinical data. CNN are specifically effective in medical images, making them ideal for detecting lung nodules and classify them as benign or malingnant. ResNet ,which deep learning further enhances classification accuracy by using convolutional layers. SVM is widely used for classification task due to its effectiveness in handling small datasets and high-dimensional spaces. Among them, ResNet50 achieved the highest accuracy of 91.3%, making it the most effective for multi-class classification (Normal, Benign, Malignant). CNN followed with 85.6%, while RF and SVM achieved 84.4% and 83.2% respectively.