Table 1.

Intraclass correlation coefficient indicating the consistency of lesion parameters between AI-QCA versus manual QCA by different observers in phase 1 pilot study (n = 15).

	AI-QCA vs. Manual QCA (1)		AI-QCA vs. Manual QCA (2)		AI-QCA vs. Manual QCA (3)		Between observers
	ICC	p	ICC	p	ICC	p	ICC	p
Proximal reference diameter (mm)	0.62 (0.17–0.85)	0.006	0.58 (0.12–0.84)	0.009	0.54 (0.06–0.82)	0.015	0.70 (0.44–0.87)	<0.001
Distal reference diameter (mm)	0.58 (0.12–0.84)	0.009	0.72 (0.34–0.90)	0.001	0.80 (0.50–0.93)	<0.001	0.55 (0.24–0.80)	<0.001
Reference diameter (mm)	0.34 (−0.19–0.71)	0.101	0.75 (0.40–0.91)	<0.001	0.75 (0.40–0.91)	<0.001	0.60 (0.31–0.83)	<0.001
Minimum lumen diameter (mm)	0.81 (0.51–0.93)	<0.001	0.93 (0.81–0.98)	<0.001	0.79 (0.48–0.92)	<0.001	0.73 (0.49–0.89)	<0.001
Percent diameter stenosis (%)	0.68 (0.27–0.88)	0.002	0.71 (0.32–0.89)	0.001	0.61 (0.16–0.85)	0.006	0.60 (0.31–0.83)	<0.001
Lesion length (mm)	0.19 (−0.34–0.63)	0.238	0.19 (−0.34–0.63)	0.243	0.23 (−0.30–0.65)	0.195	0.43 (0.11–0.73)	0.003

AI-QCA: artificial intelligence-based quantitative coronary angiography; ICC: intraclass correlation coefficients.