Using Machine Learning to Unravel the Value of Radiographic Features for the Classification of Bone Tumors

Figure 3

The most ten important features influencing the classification of bone tumors in the binary (a) and tertiary (b) models. The features are presented in descending order according to their absolute impact on the classification of bone tumor. The SHAP model takes into account all possible combinations of features in the presence/absence of a specific feature to evaluate its contribution to the prediction.

(a)

(b)