Skip to main content
Fig. 5 | Orphanet Journal of Rare Diseases

Fig. 5

From: Identification of risk features for complication in Gaucher’s disease patients: a machine learning analysis of the Spanish registry of Gaucher disease

Fig. 5

Decision tree related to the development of bone disease. The information that appears in each node includes (top down): the value of the target variable assigned by the algorithm: develops bone disease: yes/no. the ratio of patients in this node who had (left) / did not have (right) bone disease. percentage of the total population included in this node. For the prediction of bone complications, a mild bone marrow infiltration of 2.5 points by the Spanish Magnetic Resonance Imaging Score (S-MRI) with the delay of the start therapy over an age 9.5 years were the two characteristics selected by the prediction model

Back to article page
\