Table 4 Comparison of C2–C7 Angle Errors Between AI and Surgeons for Randomly Selected Cases*

From: Development of artificial intelligence for automated measurement of cervical lordosis on lateral radiographs

Absolute Error (degree)

AI

Surgeon 1

Surgeon 2

P-value† (AI vs. Surgeons)

vs. Surgeon 1

vs. Surgeon 2

Mean

3.1

3.9

3.8

0.002

0.036

Median

2.4

3.0

2.9

Maximum

34.3

22.1

74.0

SD

3.4

3.4

4.7

  1. *168 cases with a total of 415 x-rays. † The p-values were adjusted by the Bonferroni method.
  2. AI, artificial intelligence; SD, standard deviation.
Back to article page