Table 1 Results of the variable importance ranking from the information-driven and human-driven variable selection.
From: VENturing into machine learning for the morphological analysis of von Economo neurons
Importance ranking | Information-driven variable selection | Human-driven variable selection |
|---|---|---|
1 | Average length | Overall width |
2 | Number of stems | Total number of trees |
3 | Average diameter | Overall depth |
4 | Average fragmentation | Max path distance |
5 | Max fragmentation | Overall height |
6 | Average Rall’s ratio | Average Contraction |
7 | Soma surface | Soma surface |
8 | Number of branches | Average Rall’s ratio |
9 | Partition asymmetry | Total number of branches |
10 | Total Volume | Max branch order |
11 | Average branch order | Average diameter |
