Clinical Outcome Prediction in Aneurysmal Subarachnoid Hemorrhage Using Bayesian Neural Networks with Fuzzy Logic Inferences

Table 3

Results of Bayesian hierarchical meta-analysis using WinBUGS version 1.4.3 generate posterior distributions of consensus odds ratios with representative medians, standard deviations, and 95% credible intervals, for predictor variables age, neurological grade, and aneurysm size.

Prognostic cariable	OR; mean	SD	2.5%	Median	97.5%
Age	1.33	0.18	1.01	1.32	1.73
Neurological grade	2.17	0.40	1.67	2.09	3.13
Aneurysm size	1.29	0.21	1.03	1.24	1.81