Table 6.

Fusion model results compared to individual task model results, reported in AUC ± standard deviation.

Feature Set	Modality	N	GNB	LR	RF
Pupil Calibration (novel task)	Eye	126	0.71 ± 0.02	0.68 ± 0.02	0.63 ± 0.05
Picture Description	Eye	126	0.71 ± 0.02	0.73 ± 0.03	0.64 ± 0.04
	Lang	162	0.78 ± 0.01	0.77 ± 0.02	0.74 ± 0.02
	Eye + Lang	162	0.80 ± 0.02	0.79 ± 0.01	0.77 ± 0.02
Reading	Eye	126	0.70 ± 0.02	0.73 ± 0.02	0.72 ± 0.03
	Lang	162	0.79 ± 0.01	0.78 ± 0.01	0.78 ± 0.03
	Eye + Lang	162	0.78 ± 0.01	0.80 ± 0.01	0.82 ± 0.02
Memory (novel task)	Lang	162	0.78 ± 0.01	0.72 ± 0.02	0.72 ± 0.04
Task Fusion	Eye + Lang	162	0.82 ± 0.01	0.83 ± 0.01	0.83 ± 0.02

The highest classification performance for each task is in bold. Mod, modality; Eye, eye-movement alone; Lang, language alone; Eye + Lang, eye-movement and language aggregate model. More evaluation metrics such as specificity and sensitivity are reported in Supplementary Table 3. The data in gray background represent unimodal model results when multimodal data were available. So, they were not used for our statistical analysis when we compared task models.