Splitting Subject Data in train, validation and test set for 3D Human Pose Estimation

This is a 3D Human Pose Estimation problem.

There are totally 15 normal subjects in train set, 7 normal subjects in validation set and 7 normal subjects in test set.

There are 7 impaired subjects totally.

How can the splitting of these impaired subjects be done to get a higher accuracy by adding these in train, validation and test set respectively?