The comparative analysis of analgesic interventions for cancer pain is greatly compromised by the lack of well-validated and clinically acceptable tools, which allow a composite classification of pain and patient population characteristics. Although the Edmonton Staging System (ESS) for cancer pain was developed for this purpose, clinical and research utility has been limited due to problems associated with the assessment of some items, especially in relation to definitions and terminology. To overcome these limitations, we designed a revised ESS (rESS) and conducted a multicenter study to determine its inter-rater reliability and predictive value. In revising the rESS, we hypothesized that patients with less problematic pain features would require a shorter time to achieve stable pain control, require less complicated analgesic regimens, be more responsive to opioid therapy, and use lower opioid doses. The rESS items include mechanism of pain, presence or absence of incidental pain, presence or absence of psychological distress and addictive behavior, and level of cognitive function. Patients with cancer pain who were consecutively admitted to two different hospice centers, an acute care consultation service in a teaching hospital or a tertiary palliative care unit in a second teaching hospital were evaluated for study entry. Two independent palliative care specialists completed the rESS where possible within 24 hours of each other. Patients' pain ratings and opioid consumption were recorded daily until the study endpoint (i.e. achievement of stable pain control, discharge or death). Seven hundred and forty-six patients were eligible for study entry and of these, 619 (83%) had a pain syndrome. Inter-rater reliability estimates ranged from 0.67 (pain mechanism) to 0.95 (presence of addiction). In the univariate Cox regression analysis, younger patients (<60), as well as patients with neuropathic pain, incidental pain, psychological distress, or co-morbid psychological distress and addiction, required a significantly longer time to achieve stable pain control (P<0.05). In the multivariate Cox regression analysis, only age (<60), neuropathic pain and incidental pain were significantly associated with time to reach stable pain control (P<or=0.05). Patients with neuropathic or incidental pain used significantly more modalities to achieve stable pain control (P<0.01). Patients with neuropathic pain, incidental pain, as well as the presence of psychological distress or addiction, required a higher final mean morphine equivalent daily dose (MEDD) (P<0.001). A comparison of the rESS with the ESS demonstrated the ineffectiveness of the ESS prognostic staging system for predicting achievement of stable pain control. These findings confirm the study hypothesis, suggesting that the rESS appears to have good predictive value and a moderate to high inter-rater reliability. We suggest the rESS should prove to be a useful tool in clinical practice, and in the comparison of cancer pain populations in research studies.