Figure 2
From: Machine learning classifies predictive kinematic features in a mouse model of neurodegeneration
Feature importance (FI) scores (%) revealed age-specific kinematic deficits in 4mon and 13mon J20 mice. (a) A summary of FI scores (%) from the 4-month-bilateral (4mon-BL), and 13-month-bilateral (13mon-BL) datasets; (b) ranking of 4mon-BL FI scores (%); and (c) ranking of 13mon-BL FI scores (%). (d) A diagram of the 22 highest-ranked features of the 4mon, 13mon, and full bilateral datasets circled in orange, green, and blue, respectively. (e) A 2.5-degree tilt of the trunk was observed in the 4mon J20 when compared to their littermates in the WT group. Thus, subtle differences between genotypes could be detected even from data acquired at 4 months of age. Panels generated through Python 3.7, MATLAB 9.2, and Adobe Illustrator (2019).
