Enhancing cirrhosis detection: A deep learning approach with convolutional neural networks

Abstract

Cirrhosis, a prevalent and life-threatening liver condition, demands early detection for effective intervention. This study investigates the potential of machine learning algorithms, including Convolutional Neural Networks (CNN), Support Vector Machines (SVM), Decision Trees, K-Nearest Neighbors (KNN), Gaussian Naive Bayes (GNB), and Gradient Boosting (GBoost), in cirrhosis prediction using a dataset from Kaggle containing 418 observations and 20 attributes. Performance evaluation involves metrics like accuracy, precision, recall, and F1-score, revealing CNN's superior performance with an 84% accuracy rate. The study highlights the importance of algorithm selection and feature engineering in medical diagnosis. Moreover, a comparison with traditional machine learning techniques underscores CNN's prowess in this domain. Beyond cirrhosis, CNNs offer promise for automating feature extraction from medical imagery and recognizing complex patterns, potentially transforming diagnostic accuracy in healthcare.