Table 3.

DL models training and testing results on the mutation classification task.

	AUC[95% CI]
	CV from training in center 1		independant testing in center 2
	All samples	Stomach only	All samples	Stomach only
KIT	0.81[0.78, 0.84]	0.87[0.84, 0.90]	0.84[0.76, 0.91]	0.85[0.77, 0.93]
PDGFRA	0.91[0.90, 0.94]	0.92[0.90, 0.94]	0.93[0.88, 0.97]	0.92[0.86, 0.97]
WT	0.71[0.66, 0.75]	0.72[0.64, 0.80]	0.56[0.42, 0.70]	0.63[0.45, 0.82]
PDGFRA exon18	0.90[0.87, 0.92]	0.88[0.85, 0.91]	0.90[0.84, 0.96]	0.89[0.82, 0.96]
KIT exon11	0.74[0.71, 0.77]	0.87[0.84, 0.90]	0.77[0.70, 0.85]	0.85[0.77, 0.93]
KIT exon9	0.71[0.66, 0.75]	NA[NA, NA]	0.73[0.56, 0.89]	0.87[NA, NA]
Other mutations	0.60[0.53, 0.67]	0.69[0.61, 0.76]	0.59[0.39, 0.79]	0.69[0.36, 1]
PDGFRA_Exon18 D842V	0.87[0.84, 0.90]	0.82[0.78, 0.86]	0.90[0.84, 0.96]	0.87[0.79, 0.95]
PDGFRA_Exon18 other mutation	0.86[0.83, 0.90]	0.82[0.78, 0.86]	0.78[0.67, 0.88]	0.72[0.58, 0.85]
KIT_del-inc557-558	0.69[0.65, 0.72]	0.79[0.75, 0.83]	0.74[0.66, 0.82]	0.76[0.66, 0.87]
KIT_Exon11 other mutation	0.62[0.59, 0.65]	0.72[0.69, 0.76]	0.66[0.57, 0.75]	0.78[0.66, 0.88]