The aim of this study was to develop and validate a new method: a classification and regression tree (CART) based on easily accessible measures to predict mortality in patients with stable COPD.

Prospective study of two independent prospective cohorts: a derivation cohort with 611 recruited patients and a validation cohort with 348 patients, all followed for 5 years. CART analysis was used to predict 5-year mortality risk using the following covariates from the derivation cohort: age, forced expiratory volume in the first second as a percentage of predicted (FEV1%), dyspnoea, physical activity, general health, and number of hospital admissions for COPD exacerbations in the prior 2 years.

Age (≥75 years or <75) provided the first branch of the COPD-CART. The highest mortality risk (0.74) was seen in patients older than 75 with higher levels of dyspnoea and with FEV1% <50%. Patients with the lowest risk of 5-year mortality (0.04) were those under age 55 years with FEV1% >35% and with 1 or no recent hospitalizations for COPD exacerbations.

A simple decision tree that uses variables generally gathered by physicians can provide a quick assessment of the severity of the disease, as measured by the risk of 5-year mortality.