Table 3.
MIC improvement values determined with the predictive modeling approach adjusted for the proportions of improved patients, the mean change method and the ROC method
| Predictive | Mean change | ||||
|---|---|---|---|---|---|
| modeling approacha | method | ROC method | |||
| MICpred (CIb) | MICMeanChange (CIc) | MICROC (CIb) | Sensitivity | Specificity | |
| Oxford Knee Score | 8 (6–9) | 10 (8–1) | 9 (6–15) | 0.83 | 0.74 |
| Forgotten Joint Score | 14 (10–18) | 23 (17–28) | 17(11–29) | 0.85 | 0.88 |
aadjusted for the proportions improved.
b95% confidence intervals (CI) calculated using 1,000 bootstrap replications, reported as 0.025–0.975 quantiles.
c95% confidence intervals (CI) calculated as Meanchange ± 1.96 (SDchange/(√n)), where n and SDchange correspond