CNN-Based Analytical Approach for Liver Disease Classification and Prediction

Liver disease is a major global health concern, and effective treatment requires an early and accurate diagnosis. Deep learning (DL) and Machine Learning (ML) techniques have been widely applied to improve disease prediction and classification. A range of models, including Convolutional Neural Networks (CNN), Support Vector Machines (SVM), Logistic Regression (LR), and K-Nearest Neighbours (KNN), were trained using the Indian Liver Patient Dataset (ILPD) from Kaggle in order to diagnose cases of liver illness. With an accuracy rate of 96.21%, precision rate of 74.76%, recall rate of 92.77%, and F1-score rate of 82.80%, the CNN model outperforms all others, demonstrating its ability to extract complex patterns for accurate categorization. Experimental results prove that Deep Learning (DL) methodologies, especially CNN, can enhance predictive power extensively compared to Machine Learning (ML) methods.