Table 2 Inter-observer reliability of the radiologic parameters according to different institutes: Comparison of the deep learning model measurements with an orthopedic specialist (ground-truth)

HKAA

1.00 (1.00–1.00)

0.995 (0.99–1.00)

0.998 (1.00–1.00)

0.994 (0.99–1.00)

0.997 (1.00–1.00)

LDFA

1.00 (1.00–1.00)

0.969 (0.93–0.98)

0.976 (0.96–0.98)

0.982 (0.97–0.99)

0.976 (0.97–0.98)

MPTA

1.00 (1.00–1.00)

0.966 (0.95–0.98)

0.962 (0.94–0.97)

0.956 (0.93–0.97)

0.963 (0.95–0.97)

JLCA

1.00 (1.00–1.00)

0.892 (0.84–0.93)

0.950 (0.93–0.97)

0.913 (0.87–0.94)

0.936 (0.92–0.95)

WBL ratio

1.00 (1.00–1.00)

0.993 (0.91–1.0)

0.998 (1.00–1.00)

0.997 (1.00–1.00)

0.987 (0.98–0.99)

JLOA

1.00 (1.00–1.00)

0.986 (0.98–0.99)

0.979 (0.97–0.99)

0.989 (0.98–0.99)

0.987 (0.98–0.99)

LDTA

1.00 (1.00–1.00)

0.979 (0.91–0.99)

0.977 (0.97–0.99)

0.977 (0.96–0.99)

0.979 (0.96–0.99)