Skip to main content

Table 2 Main features of the model-agnostic interpretability techniques used in this study

From: On the interpretability of machine learning-based model for predicting hypertension

Feature Importance • Highly compressed global interpretation
• Consider interactions between features
Unclear whether it can be used on training dataset or testing dataset
Partial Dependence Plot Intuitive and clear interpretationAssumption of independence between features
Individual Conditional Expectation Intuitive and easy to understandPlot can become overcrowded to understand
Feature Interaction Detects all interactions been featuresComputationally expensive
Global Surrogate Models Easy to measure the goodness of your surrogate model using R-squared measureNot clear what is the best cut-off for R-squared to trust the resulted surrogate model
Local Surrogate Model (LIME) • Short and comprehensible explanation.
• Explains different types of data (tabular, text and image)
• Instability of the explanation
• Very close points may have totally different explanations
Shapley Value Explanations Explanation is based on strong game theory theoremComputationally very expensive