Fig. 3From: Machine learning in Huntington’s disease: exploring the Enroll-HD dataset for prognosis and driving capability predictionThe mean R2 and F1 scores of the best performing imputation models. This is shown for each variable in each data type, namely a continuous, b ordinal, and c categorical. The trained models were: random forest (RF), linear/logistic regression (Linear), and K-nearest neighbours (Knn)Back to article page