Table 6.

Performance of the classification model for the training, internal test and external test sets

Training (CLEANED)
	Balanced Accuracy		Cohen´s Kappa		Sensitivity		Specificity
	Mean	Std	Mean	Std	Mean	Std	Mean	Std
Training Set	0.94	0.00	0.90	0.01	0.98	0.01	0.92	0.01
Internal Test Set (RELIABLE)	0.88	0.01	0.78	0.01	0.96	0.01	0.80	0.01
External Set I (All)	0.80	0.01	0.60	0.04	0.89	0.01	0.71	0.02
TS1	0.85	0.01	0.61	0.01	0.83	0.01	0.78	0.01
TS2	0.79	0.01	0.71	0.01	1.00	0.01	0.71	0.01
TS3	0.74	0.01	0.46	0.05	0.85	0.01	0.61	0.01
TS4	0.96	0.01	0.86	0.01	0.91	0.01	0.91	0.01
CONCATENATED training (CLEANED + RELIABLE)
	Balanced Accuracy		Cohen´s Kappa		Sensitivity		Specificity
	Mean	Std	Mean	Std	Mean	Std	Std	Std
External Set I (All)	0.81	0.01	0.61	0.04	0.92	0.01	0.70	0.01
TS1	0.85	0.01	0.70	0.01	0.92	0.01	0.78	0.01
TS2	0.86	0.01	0.71	0.01	1.0	0.01	0.71	0.01
TS3	0.76	0.01	0.50	0.05	0.88	0.02	0.64	0.01
TS4	0.91	0.01	0.74	0.01	1.00	0.01	0.82	0.01

Std: standard deviation obtained from a five-iteration loop, RMSE: root mean squared error. TS1-TS4: test set 1 to 4.