Table 3.
Logistic regression predicting likelyhood of rebleeding based on active bleeding, visible haemoclips, Rockall score, normal anatomy and standard embolization procedure
| B | SE | Wald | p | Odds Ratio | 95% CI for Odds Ratio | ||
|---|---|---|---|---|---|---|---|
| Lower | Upper | ||||||
| Active bleeding | − 0.550 | 0.446 | 1.519 | 0.218 | 0.577 | 0.241 | 1.383 |
| Visible haemoclips | 0.507 | 0.389 | 1.695 | 0.193 | 1.659 | 0.774 | 3.557 |
| Rockall score | 0.179 | 0.375 | 0.228 | 0.633 | 1.196 | 0.574 | 2.492 |
| Normal anatomy | 0.268 | 0.386 | 0.483 | 0.487 | 1.308 | 0.614 | 3.082 |
| Standard embolization procedure | 1.193 | 0.407 | 8.583 | 0.003 | 3.298 | 1.484 | 6.579 |
| > 1 endoscopy before embolization | 0.862 | 0.397 | 4.720 | 0.030 | 2.369 | 1.088 | 5.158 |
| Constant | − 4.335 | 1.622 | 7.142 | 0.008 | 0.013 | ||
B unstandardized regression weight, SE standard error, Wald Wald test, CI confidence interval
The bold values are highlighted because they show statistically significant p-values