Optimized Liver Disease Classification Using Random Forest with Hyperparameter Tuning and SMOTE

The current research work provides a highly efficient machine learning system for multi-class classification of liver diseases utilizing random forest, SMOTE technique, and grid search cross-validation (GridSearchCV). This combination helps ensure high accuracy and efficiency of the model, which is very essential in dealing with different cases in clinical settings. Class balancing and hyperparameter optimization contribute to addressing class imbalance and improving prediction efficiency. In terms of future research, there is an opportunity to improve the existing model using deep learning algorithms and ensemble modeling techniques. With the use of large amounts of data, it is possible to train a model that will be highly generalized and precise. In addition, explainable artificial intelligence (XAI) may be used to improve the interpretability of the model and boost confidence in the medical decision-making process. Deployment of the current model on the Internet and medical websites should also be considered

1.        Institute for Health Metrics and Evaluation (IHME): Global Age-Sex-Specific All-Cause Mortality and Life Expectancy, 1950–2023. Global Burden of Disease Collaborative Network, Seattle, WA, USA (2024). Available online: https://www.healthdata.org/research-analysis/library/global-age-sex-specific-all-cause-mortality-and-life-expectancy-estimates 2.        Powell, E.E. et al.: Non-alcoholic fatty liver disease. The Lancet 397(10290) (2021) 2212–2224 3.        Loomba, R., Adams, L.A.: Advances in non-invasive assessment of hepatic fibrosis. Gut 69(7) (2020) 1343–1352 4.        Ahmed, M.N., Singh, G., Badoni, P., Walia, R., Rahi, P., Saddiqui, A.T.: An efficient ADA Boost and CNN hybrid model for weed detection and removal. In: Proc. 10th Int. Conf. Computing for Sustainable Global Development (INDIACom), New Delhi, India (2023) 244–250 5.        Shaban, W.M.: Early diagnosis of liver disease using improved binary butterfly optimization and machine learning algorithms. Multimedia Tools and Applications 83 (2024) 30867–30895 6.        Wu, N., Feng, M., Zhao, H., Wei, S. et al.: Prediction of metabolic dysfunction-associated steatotic liver disease via advanced machine learning among Chinese Han population. Obesity Surgery 35 (2025) 4192–4204 7.        Park, I.-G., Yoon, S.J., Won, S.-M., Oh, K.-K., Hyun, J.Y., Suk, K.T., Lee, U.: Gut microbiota-based machine-learning signature for the diagnosis of alcohol-associated and metabolic dysfunction-associated steatotic liver disease. Scientific Reports 14 (2024) 16122 8.        Rahi, P., Kang, S.S., Singh, A.P., Singh, I.: A random forest framework for predicting cardiovascular disease in diverse populations. In: Proc. 2nd Int. Conf. Advanced Computing & Communication Technologies (ICACCTech), Sonipat, India (2024) 472–478 9.        Volovăț, S.R., Matei, A.: Comparative performance of autoencoders and traditional machine learning algorithms in clinical data analysis. Diagnostics 14(4) (2024) 810 10.     Elreedy, D., Atiya, A.F., Kamalov, F.: A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning. Machine Learning 112 (2023) 4903–4923