Motor-cognitive functions required for driving in post-stroke individuals identified via machine-learning analysis

Table 5 Results of ROC analysis

Analysis method	AUC	Sensitivity	Specificity	Threshold
Proposed network	0.946	0.878	0.929	0.830
LLGMN with partial KLI-based reduction	0.962	0.951	0.857	0.730
Lasso regression	0.753	0.732	0.786	0.808

Sensitivity and specificity were calculated using the threshold values determined by the ROC analysis

ISSN: 1743-0003