bioRxiv2019
BackgroundAccurate 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. MethodsWe 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. ResultsThe development dataset included 2,380 patients (mean 64{middle dot}7 years, 1373 [57{middle dot}7%] men, mean exacerbation rate 1{middle dot}42/year, 0{middle dot}29/year [20{middle dot}5%] severe). When validated against all COPD patients in ECLIPSE (n=1819, mean 63{middle dot}3 years, 1186 [65{middle dot}2%] men, mean exacerbation rate 1{middle dot}20/year, 0{middle dot}27/year [22{middle dot}2%] severe), the area-under-curve was 0{middle dot}81 (95%CI 0{middle dot}79-0{middle dot}83) for [≥]2 exacerbations and 0{middle dot}77 (95%CI 0{middle dot}74-0{middle dot}80) for [≥]1 severe exacerbation. Predicted rates were 0{middle dot}25/year for severe and 1{middle dot}31/year for all exacerbations, close to the observed rates (0{middle dot}27/year and 1{middle dot}20/year, respectively). In ECLIPSE patients with a prior exacerbation history (n=996, mean 63{middle dot}6 years, 611 (61{middle dot}3%) men, mean exacerbation rate 1{middle dot}82/year, 0{middle dot}40/year [22{middle dot}0%] severe), the area-under-curve was 0{middle dot}73 (95%CI 0{middle dot}70-0{middle dot}76) for [≥]2 exacerbations and 0{middle dot}74 (95%CI 0{middle dot}70-0{middle dot}78) for [≥]1 severe exacerbation. Calibration was accurate for severe exacerbations (predicted=0{middle dot}37/year, observed=0{middle dot}40/year) and all exacerbations (predicted=1{middle dot}80/year, observed=1{middle dot}82/year). The model is accessible at http://resp.core.ubc.ca/ipress/accept. InterpretationThis model can be used as a decision tool to personalise COPD treatment and prevent exacerbations. Research in contextO_ST_ABSEvidence before this studyC_ST_ABSPreventing future exacerbations is a major goal in COPD care. Because of adverse effects, preventative treatments should be reserved for those at a higher risk of future exacerbations. Predicting exacerbation risk in individual patients can guide these clinical decisions. A 2017 systematic review reported that of the 27 identified COPD exacerbation prediction tools, only two had reported external validation and none was ready for clinical implementation. To find the studies that were published afterwards, we searched PubMed for articles on development and validation of COPD exacerbation prediction since 2015, using the search terms "COPD", "exacerbation", "model", and "validation". We included studies that reported prediction of either the risk or the rate of exacerbations and excluded studies that did not report external validation. Our literature search revealed two more prediction models neither of which was deemed generalisable due to lack of methodological rigour, or local and limited nature of the data available to investigators. Added value of this studyWe used data from three randomised trials to develop ACCEPT, a clinical prediction tool based on routinely available predictors for COPD exacerbations. We externally validated ACCEPT in a large, multinational prospective cohort. To our knowledge, ACCEPT is the first COPD exacerbation prediction tool that jointly estimates the individualised rate and severity of exacerbations. Successful external validation of ACCEPT showed that its generalisability can be expanded across geography and beyond the setting of therapeutic trials. ACCEPT is designed to be easily applicable in clinical practice and is readily accessible as a web application. Implications of all the available evidenceCurrent guidelines rely on a history of exacerbations as the sole predictor of future exacerbations. Simple clinical and demographic variables, in aggregate, can be used to predict COPD exacerbations with improved accuracy. ACCEPT enables a more personalised approach to treatment based on routinely collected clinical data by allowing clinicians to objectively differentiate risk profiles of patients with similar exacerbation history. Care providers and patients can use individualised exacerbation risk estimates to decide on preventive therapies based on objectively-established or patient-specific thresholds for treatment benefit and harm. COPD clinical researchers can use this tool to target enriched populations for enrolment in clinical trials.