Account

Table 5 Classification results for the GBTree booster-based models

From: Computer-Aided Diagnosis of Graphomotor Difficulties Utilizing Direction-Based Fractional Order Derivatives

Scenario	Tuner	BACC	SEN	SPE	BACC-pos	SEN-pos	SPE-pos	N
Baseline	R	0.82	0.86	0.77	0.83	0.77	0.89	13
	B	0.76	0.82	0.69	0.81	0.80	0.82	17
Novel	R	0.82	0.88	0.77	0.83	0.88	0.78	46
	B	0.79	0.86	0.72	0.87	0.82	0.92	43
Combined	R	0.78	0.81	0.74	0.85	0.77	0.93	106
	B	0.78	0.84	0.72	0.86	0.80	0.92	61

¹BACC, balanced accuracy; SEN, sensitivity; SPE, specificity; BACC-pos, balanced accuracy after decision threshold adjustment; SEN-pos, sensitivity after decision threshold adjustment; SPE-pos, specificity after decision threshold adjustment; N, number of features used to train the model

Back to article page