Liver diseases represent a significant health problem worldwide, affecting millions of individuals and potentially resulting in mortality. Early treatment and identification of these diseases help to reduce the chance of patient health complications. In cases of severe liver disease, liver transplantation is the only viable treatment option. The integration of artificial intelligence into medicine has driven significant advances suggesting a highly interconnected and promising future for medical practices. This work explores the Indian Liver Patients Database to develop a hepatic disease detection system based on seven machine learning classifiers: Extra Trees, Logistic Regression, Support Vector Classifier, Extreme Gradient Boosting, Multi-layer Perceptron, k-Nearest Neighbors, and Gaussian Naive Bayes. The combination of these models was used to build a voting system that increases the system’s robustness, flexibility, resistance to noise, and generalization. The proposed system results in 76% of accuracy, whereas in terms of individual classifiers, the best performance is achieved by the Extra Trees Classifier with a value of 70.8%. Thereby, the results indicate that developing a system based on the combination of classifiers is more advantageous in this context. The approach highlights the importance of combining several algorithms to deal with the complexities of medical data, clearing the way for more effective and scalable healthcare solutions in the future.