Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Framework of proposed methodology.

More »

Fig 1 Expand

Fig 2.

Percentage of missing values for each variable with missing data.

More »

Fig 2 Expand

Fig 3.

The process of simulating missingness in the dataset.

More »

Fig 3 Expand

Table 1.

Details and characteristics of continuous variables for patients with MAFLD and patients without MAFLD.

More »

Table 1 Expand

Table 2.

Details and characteristics of binary variables for patients with MAFLD and patients without MAFLD.

More »

Table 2 Expand

Fig 4.

Performance comparison of different imputation methods for binary and continues variables (mean results over five runs).

More »

Fig 4 Expand

Table 3.

Accuracy and number of selected features for each classifier with various feature selection methods.

More »

Table 3 Expand

Fig 5.

Comparison of performance metrics for ensemble methods.

More »

Fig 5 Expand

Fig 6.

Top ten features with the highest mean importance across XGBoost, LightGBM, and Gradient Boosting models.

More »

Fig 6 Expand

Fig 7.

SHapley Additive exPlanations value plot of different features in XGBoost classifier.

More »

Fig 7 Expand