Fig 1.
Semantic representation of the vestibular rotation task.
Table 1.
The vestibular rotation task rotations.
Table 2.
Features.
Fig 2.
Machine learning models and feature importance.
A F1 scores for the best performing algorithm are shown. A random predictor would score 0.57, with a score of above 0.57 representing better-than-chance APOE status classification performance. Blue line includes all features. Red line excludes the path integration feature, end error. B Importance scores are represented by the circle diameter and were derived for the best performing model on each of the trials shown. Scores vary between 0 and 1 depending on the proportion of influence the feature has for that trial. RF = Random Forest, SVM = Support Vector Machine, MLP = Multi-Layer Perception.
Table 3.
Primary demographic and neuropsychology characteristics of the sample.
Table 4.
Machine learning F1 and accuracy scores.