Table 3.
Inter-rater reliability between AI method and manual measurements; preoperative n = 94 for mMPTA, mLDTA, FSAmTA, n = 88 for mLDFA, mFAmTA; postoperative n = 102 for mMPTA, mLDTA, n = 100 for FSAmTA, n = 99 for mLDFA, n = 97 for mFAmTA.
Inter-Rater Reliability (AI method vs. Rater 1) | ||||||
---|---|---|---|---|---|---|
Statistical Method | mMPTA [°] | mLDFA [°] | mFAmTA [°] | mLDTA [°] | FSAmTA [°] | |
Preoperative | ICC (95% CI) |
0.86 (0.80–0.91) |
0.84 (0.76–0.89) |
1.0 (0.99–1.0) |
0.88 (0.77–0.93) |
0.99 (0.98–0.99) |
Mean error (95% CI) |
−0.29 (−0.66–0.08) |
0.15 (−0.26–0.56) |
−0.03 (−0.17–0.11) |
0.97 (0.56–1.38) |
0.24 (0.0–0.48) |
|
SD | 1.8 | 1.92 | 0.67 | 1.98 | 1.15 | |
RMSE | 1.83 | 1.93 | 0.67 | 2.2 | 1.18 | |
Pearson correlation r (p-value) |
0.87 (<0.001) |
0.84 (<0.001) |
1.0 (<0.001) |
0.90 (<0.001) |
0.99 (<0.001) |
|
Inter-rater Reliability (AI method vs. Rater 2a) | ||||||
Preoperative | ICC (95% CI) |
0.90 (0.85–0.93) |
0.80 (0.71–0.87) |
0.99 (0.99–1.0) |
0.95 (0.92–0.97) |
0.99 (0.98–0.99) |
Mean error (95% CI) |
−0.19 (−0.53–0.14) |
0.19 (−0.27–0.65) |
0.0 (−0.19–0.19) |
0.49 (0.21–0.78) |
0.26 (0.02–0.49) |
|
SD | 1.61 | 2.16 | 0.89 | 1.38 | 1.14 | |
RMSE | 1.62 | 2.17 | 0.89 | 1.46 | 1.16 | |
Pearson correlation r (p-value) |
0.91 (<0.001) |
0.81 (<0.001) |
0.99 (<0.001) |
0.96 (<0.001) |
0.99 (<0.001) |
|
Postoperative | ICC (95% CI) |
0.83 (0.76–0.88) |
0.87 (0.81–0.91) |
0.99 (0.98–0.99) |
0.94 (0.91–0.96) |
0.99 (0.98–0.99) |
Mean error (95% CI) |
−0.13 (−0.32–0.07) |
−0.31 (−0.63–0.01) |
0.15 (0.05–0.24) |
0.23 (−0.06–0.52) |
−0.07 (−0.17–0.04) |
|
SD | 1.0 | 1.61 | 0.48 | 1.47 | 0.53 | |
RMSE | 1.0 | 1.64 | 0.51 | 1.49 | 0.53 | |
Pearson correlation r (p-value) |
0.83 (<0.001) |
0.88 (<0.001) |
0.99 (<0.001) |
0.94 (<0.001) |
0.99 (<0.001) |
|
Inter-rater Reliability (AI method vs. Rater 2b) | ||||||
Preoperative | ICC (95% CI) |
0.88 (0.83–0.92) |
0.83 (0.75–0.88) |
0.99 (0.99–1.0) |
0.95 (0.92–0.97) |
0.99 (0.98–0.99) |
Mean error (95% CI) |
−0.26 (−0.61–0.08) |
0.19 (−0.24–0.62) |
−0.01 (−0.18–0.17) |
0.35 (0.04–0.65) |
0.2 (−0.02–0.43) |
|
SD | 1.68 | 2.02 | 0.82 | 1.49 | 1.11 | |
RMSE | 1.7 | 2.03 | 0.82 | 1.53 | 1.13 | |
Pearson correlation r (p-value) |
0.89 (<0.001) |
0.83 (<0.001) |
0.99 (<0.001) |
0.95 (<0.001) |
0.99 (<0.001) |
|
Postoperative | ICC (95% CI) |
0.85 (0.78–0.89) |
0.85 (0.79–0.90) |
0.99 (0.98–0.99) |
0.95 (0.92–0.96) |
0.99 (0.98–0.99) |
Mean error (95% CI) |
−0.14 (−0.33–0.04) |
−0.39 (−0.73–−0.06) |
0.16 (0.07–0.25) |
0.37 (0.09–0.65) |
−0.08 (−0.2–0.03) |
|
SD | 0.94 | 1.65 | 0.43 | 1.42 | 0.57 | |
RMSE | 0.95 | 1.7 | 0.46 | 1.46 | 0.58 | |
Pearson correlation r (p-value) |
0.85 (<0.001) |
0.87 (<0.001) |
0.99 (<0.001) |
0.95 (<0.001) |
0.99 (<0.001) |
ICC, intraclass correlation coefficient; CI, confidence interval; SD, standard deviation; RMSE, root mean square error.