Differential prognostic impact of comorbidity

Abstract

Purpose: Cancer patients with concurrent comorbid conditions have worse outcomes than patients with no comorbidities. We hypothesized that the prognostic impact of comorbidities would be greatest for patients with cancers associated with a long natural history and least in patients with aggressive cancers.

Patients and methods: Using the Barnes-Jewish Hospital Oncology Data Services cancer registry, we grouped 11,558 patients with breast, lung, colon, or prostate cancer by morphologic stage at diagnosis and then determined the 1-year overall survival rate for each group. Overall, severity of comorbidity was assessed from chart review and classified into one of four groups: none, mild, moderate, or severe. The relative prognostic impact of comorbidity was measured by the hazard ratio and adjusted for the prognostic impact of age, race, and sex.

Results: One-year overall survival rate ranged from 20% for 1,005 patients with distant spread of lung cancer to 98% for 3,325 patients with localized prostate cancer. Adjusted hazard ratio of moderate/severe comorbidity (relative to none/mild) ranged from 1.04 to 4.48. The correlation between overall survival rate and severity of comorbidity was statistically significant (r2 = 0.56; P < .001). The proportion of variance in outcome explained by comorbidity ranged from less than 1% to almost 9%, depending on tumor site and stage.

Conclusion: Concurrent comorbidities had the greatest prognostic impact among groups with the highest survival rate and the least impact in groups with the lowest survival rate. These findings can be used to help determine the role comorbidity information should play in studies of cancer outcomes.