The Summit Score Stratifies Mortality and Morbidity in Chronic Obstructive Pulmonary Disease

Abstract

Introduction: Tobacco use and other cardiovascular risk factors often accompany chronic obstructive pulmonary disease (COPD). This study derived and validated the Summit Score to predict mortality in people with COPD and cardiovascular risks.

Methods: SUMMIT trial subjects (N=16,485) ages 40-80 years with COPD were randomly assigned 50%/50% to derivation (N=8181) and internal validation (N=8304). Three external COPD validations from Intermountain Healthcare included outpatients with cardiovascular risks (N=9251), outpatients without cardiovascular risks (N=8551), and inpatients (N=26,170). Cox regression evaluated 40 predictors of all-cause mortality. SUMMIT treatments including combined fluticasone furoate (FF) 100μg/vilanterol 25μg (VI) were not included in the score.

Results: Mortality predictors were FEV₁, heart rate, systolic blood pressure, body mass index, age, smoking pack-years, prior COPD hospitalizations, myocardial infarction, heart failure, diabetes, anti-thrombotics, anti-arrhythmics, and xanthines. Combined in the Summit Score (derivation: c=0.668), quartile 4 vs 1 had HR=4.43 in SUMMIT validation (p<0.001, 95% CI=3.27, 6.01, c=0.662) and HR=8.15 in Intermountain cardiovascular risk COPD outpatients (p<0.001, 95% CI=5.86, 11.34, c=0.736), and strongly predicted mortality in the other Intermountain COPD populations. Among all SUMMIT subjects with scores 14-19, FF 100μg/VI 25μg vs placebo had HR=0.76 (p=0.0158, 95% CI=0.61, 0.95), but FF 100μg/VI 25μg was not different from placebo for scores <14 or >19.

Conclusion: In this post hoc analysis of SUMMIT trial data, the Summit Score was derived and validated in multiple Intermountain COPD populations. The score was used to identify a subpopulation in which mortality risk was lower for FF 100μg/VI 25μg treatment.

Trial registration: The SUMMIT trial is registered at ClinicalTrials.gov as number NCT01313676.

Keywords: IMRS; Intermountain risk score; clinical decision tool; randomized controlled trial; risk score.

Figure 1

Kaplan–Meier survival curves displaying the association of the Summit Risk Score with all-cause mortality among: (A) the validation half of the SUMMIT trial population, N=8304 (for quartiles 4, 3, and 2 compared with quartile 1: Log rank p<0.001, p<0.001, and p=0.002, respectively; c-statistic: c=0.662), (B) an Intermountain Healthcare validation population of outpatients with COPD and cardiovascular risks, N=9251 (for quartiles 4, 3, and 2 compared with quartile 1: Log rank p<0.001, p<0.001, and p<0.001, respectively; c-statistic: c=0.736). Time intervals on the x-axes were designated in 365-day intervals for SUMMIT populations and years for Intermountain populations.

Figure 2

Hazard curves for the effects of the four SUMMIT trial randomized treatments on all-cause mortality among all SUMMIT trial subjects (ie, both the Summit Score derivation and validation groups). Trial randomizations included: once daily inhaled placebo, vilanterol (VI) 25 μg, fluticasone furoate (FF) 100 μg, or the combination of FF 100 μg and VI 25 μg. Here the combination of FF 100 μg/VI 25 μg (n=2347) had a statistically significantly lower mortality compared with placebo (n=2305) (p=0.0158, HR= 0.76, CI=0.61, 0.95) among subjects with a Summit Score ≥14 and ≤19 (n=9243, which is 56.1% of the SUMMIT trial subjects). The hazard curves for subject with Summit Score ≤13 and ≥20 are provided in Supplemental Figures S2B and S2C.