Background: Accurate prediction of exacerbation risk enables personalised chronic obstructive pulmonary disease (COPD) care. We developed and validated a generalisable model to predict the individualised rate and severity of COPD exacerbations.
Methods:We pooled data from three COPD trials on patients with a history of exacerbations.We developed a mixed-effect model to predict exacerbations over one-year. Severe exacerbations were those requiring inpatient care. Predictors were a history of exacerbations, age, sex, body mass index, smoking status, domiciliary oxygen therapy, lung function, symptom burden, and current medication use. ECLIPSE, a multicentre cohort study, was used for external validation.
Results: The development dataset included 2,380 patients (mean 64·7 years, 1373 [57·7%] men, mean exacerbation rate 1·42/year, 0·29/year [20·5%] severe). When validated against all COPD patients in ECLIPSE (n=1819, mean 63·3 years, 1186 [65·2%] men, mean exacerbation rate 1·20/year, 0·27/year [22·2%] severe), the area-under-curve was 0·81 (95%CI 0·79-0·83) for ≥2 exacerbations and 0·77 (95%CI 0·74-0·80) for ≥1 severe exacerbation. Predicted rates were 0·25/year for severe and 1·31/year for all exacerbations, close to the observed rates (0·27/year and 1·20/year, respectively). In ECLIPSE patients with a prior exacerbation history (n=996, mean 63·6 years, 611 (61·3%) men, mean exacerbation rate 1·82/year, 0·40/year [22·0%] severe), the area-under-curve was 0·73 (95%CI 0·70-0·76) for ≥2 exacerbations and 0·74 (95%CI 0·70-0·78) for ≥1 severe exacerbation. Calibration was accurate for severe exacerbations (predicted=0·37/year, observed=0·40/year) and all exacerbations (predicted=1·80/year, observed=1·82/year). The model is accessible at http://resp.core.ubc.ca/ipress/accept. Interpretation: This model can be used as a decision tool to personalise COPD treatment and prevent exacerbations.