Table 3.
|
Components |
|||
---|---|---|---|---|
Predictors | 1 | 2 | 3 | 4 |
Age | 0.12 | 0.30 | 0.15 | −0.19 |
GCS | −0.40 | 0.16 | 0.17 | 0.06 |
SAH/IPH (present/absent) | 0.27 | 0.40 | 0.32 | 0.11 |
SDH (present/absent) | 0.49 | 0.23 | 0.14 | 0.02 |
EDH (present/absent) | 0.02 | −0.08 | 0.13 | 0.75 |
Shift >5 mm (present/absent) | 0.62 | 0.12 | 0.08 | 0.08 |
Cistern effacement | 0.65 | 0.09 | 0.05 | −0.02 |
GOS-E at 6 months | −0.40 | 0.02 | 0.06 | 0.04 |
Loading matrix for principal component analysis of 6-month GOS-E, qualitative CT predictors, age, and GCS. Numbers represent individual loading coefficients of qualitative CT predictors, age, and GCS upon the first four components. Boxes highlight significant loading coefficients with magnitude ≥0.3. This global PCA analysis, performed on outcome and predictor variables together, demonstrates an interdependence of 6-month GOS-E, GCS, and several qualitative CT predictors related to intracranial mass effect (SDH volume, shift, and cistern effacement). Although similar to results for quantitative CT, the loading coefficients for GOS-E and quantitative CT in Table 1 were larger, suggesting stronger covariances among these factors.
PCA, principal component analysis; GOS-E, Extended Glasgow Outcome Score; GCS, Glasgow Coma Scale; SAH, subarachnoid hemorrhage; IPH, intraparenchymal hemorrhage; SDH, subdural hematoma; EDH, epidural hematoma.