TABLE 2.

Net Reclassification of Patients with CAD-DL (Explainable Deep Learning Model) Compared With the Same Readers Without CAD-DL

	Reclassified 5-point scale likelihood with CAD-DL			Reclassified likelihood (%)
5-point scale likelihood without CAD-DL	Normal	Probably normal	Equivocal	Probably abnormal	Definitely abnormal	Increased likelihood	Decreased likelihood	Net correctly reclassified
Obstructive CAD (n = 360)						47 (13.1%)	25 (6.9%)	6.1% (95% CI 1.4%–10.3%)
Normal	22	4	2	0	0
Probably normal	4	34	10	3	3
Equivocal	0	6	10	14	0
Probably abnormal	0	1	4	24	11
Definitely abnormal	0	0	0	10	198
No Obstructive CAD (n = 360)						40 (11.1%)	80 (22.2%)	11.1% (95% CI 4.8%–16.8%)
Normal	64	11	0	0	0
Probably normal	18	84	11	5	2
Equivocal	1	13	11	6	1
Probably abnormal	0	9	15	29	4
Definitely abnormal	1	2	6	15	52			Overall NRI + 17.2% (95% CI 9.2%–24.4%, P < 0.001)

Boldface text indicates studies were reclassified in the correct direction and italicized text indicates studies were reclassified in the incorrect direction. A color version of Table 2 appears in the online supplemental materials.

NRI = net reclassification index.