ENHANCING THE ACCURACY OF DEPRESSION DIAGNOSIS IN PATIENTS WITH SPINAL-CORD INJURY USING BAYESIAN-ANALYSIS

The accurate diagnosis of depression among patients with spinal cord i njury (SCI) is critical to their rehabilitation. Overlapping symptoms of depression and SCI may obscure the diagnosis, however. It may be us eful to evaluate the likelihood of the diagnosis of depression given t he presence or absence of symptoms. This study compared depressive sym ptoms of patients with paraplegia (N=80) and patients with quadriplegi a (N=53) using Bayesian analysis. Predictive powers and efficiency of symptoms were examined. Differences in the efficiency of predictabilit y for individuals with paraplegia and quadriplegia existed for dysphor ic mood, energy, and suicidal ideation. The results suggest that diffe rential weighing of symptoms of depression may reduce misdiagnosis, th ereby enhancing rehabilitation efforts. Bayesian analysis shows promis e as an alternative approach to evaluating and diagnosing depression i n patients undergoing rehabilitation.