Investigators involved in this study sought to identify independent clinical predictors of spinal cord compression (SCC) in cancer patients by analyzing a comprehensive set of potential risk factors based on the results of spine magnetic resonance imaging (MRI). In all, the investigators analyzed 136 episodes of suspected SCC among 134 cancer patients evaluated with spine MRI. Each subject was interviewed within 7 days of the spine MRI to collect accurate self-reported symptom data. Neurologic examination data were detailed by the physician examining the subject prior to the spine MRI; uniform demographic and clinical information regarding the subject's cancer history was abstracted from the medical record. Multivariable logistic regression analysis was used to identify independent predictors of SCC. Clinically significant SCC was defined as thecal sac compression (TSC), which occurred in 50 episodes (37%). Four independent predictors of TSC were identified and included information from the neurologic examination (abnormal neurologic examination), subject-reported symptoms (middle or upper back pain), and the oncologic history (known vertebral metastases and metastatic disease at initial diagnosis). These four predictors stratified patients experiencing episodes into subgroups with varying risks of TSC, ranging from 8% (no risk factors) to 81% (three or four risk factors). These results confirmed earlier retrospective studies indicating that the evaluation of cancer patients with suspected SCC should be based upon clinical information that includes cancer-related history, symptom data,and the presence of pertinent neurologic signs. These predictors may help clinicians to assess risk in this patient population.