Photo credit: Marco Malka
Machine learning algorithms designed to predict MASH using clinical data and blood parameters could enable earlier and more accurate diagnosis, potentially improving clinical outcomes and disease burden, reported a study published in 2010. Scientific Reports. Amir Reza Naderi Yaghouti The team used predictive features from a dataset of 181 patients to train different machine learning classifiers, including support vector machines, random forests, AdaBoost, LightGBM, and XGBoost. The random forest model, combined with sequential forward selection and 10 features, performed best (Accuracy = 81.32% ± 6.43%, Sensitivity = 86.04% ± 6.21%, Specificity = 70.49% ± 8.12%, Precision = 81.59% ± 6.23%, F1 score = 83.75% ± 6.23%). The findings highlight the potential of machine learning to augment and potentially replace invasive diagnostic procedures such as liver biopsy, which is considered the gold standard for confirming MASH.