Fig 1.
Framework of proposed methodology.
Fig 2.
Percentage of missing values for each variable with missing data.
Fig 3.
The process of simulating missingness in the dataset.
Table 1.
Details and characteristics of continuous variables for patients with MAFLD and patients without MAFLD.
Table 2.
Details and characteristics of binary variables for patients with MAFLD and patients without MAFLD.
Fig 4.
Performance comparison of different imputation methods for binary and continues variables (mean results over five runs).
Table 3.
Accuracy and number of selected features for each classifier with various feature selection methods.
Fig 5.
Comparison of performance metrics for ensemble methods.
Fig 6.
Top ten features with the highest mean importance across XGBoost, LightGBM, and Gradient Boosting models.
Fig 7.
SHapley Additive exPlanations value plot of different features in XGBoost classifier.