Table 2.

Comparison of common Level 1 BCI-based AAC performance metrics

Metric	Description/Equation	Evaluation criteria
		Throughput	Categorical outputs	Unbiased	Practicality
Accuracy/Error Rate	Acc = P; Err = (1 - P)		✓		✓
Cohen’s Kappa	$\kappa =\frac{P-1/N}{1-1/N}$		✓		✓
Confusion Matrix	A matrix with intended (true) outputs as rows, actual outputs as columns, and the number of occurrences in the intersections.		✓	✓
IMutual Information or the formulation in [97]	$I\left(X;Y\right)={\displaystyle \sum _Y{\displaystyle \sum _{X}p\left(x,y\right)\times log\left(\frac{p\left(x,y\right)}{p\left(x\right)*p\left(y\right)}\right)}}$ (Note this can be used to measure throughput rate by simply dividing by the time per trial)	✓	✓	✓
Information Transfer Rate (ITR)	$\mathit{ITR}=\frac{1}{c}\left({log}_2\left(N\right)+P{log}_2\left(P\right)+\left(1-P\right){log}_2\left(\frac{1-P}{N-1}\right)\right)$	✓	✓		✓

P: probability of correct selection; N: number of choices; p(x): marginal distribution of X; p(x,y): joint distribution of X and Y; c: time per selection.

Check marks indicate that the metric fulfills the evaluation criterion.