Validation of lung function prediction equations from patient survival data

Abstract

Diagnosing and managing pulmonary disease usually requires judging lung function against predicted values. We explored patient survival data to help identify the best equations for our population. The earliest spirometry, lung volumes and gas transfer data for all Caucasian patients were extracted from our database. Survival status was available for 8,139 patients. Lung function as standardised residuals (SR) from various prediction equations was used in Cox regression to predict the hazard ratio (HR) for death. The best lung function predictor of all-cause mortality was diffusing capacity of the lung for carbon monoxide (D(L,CO)), followed by forced vital capacity (FVC). These were best with the equations of Miller, derived from a US population, with Chi-squared values of 1,468 and 1,043 for D(L,CO) and FVC, respectively, having taken age, sex, smoking status and body mass index into account. The HR (95% CI) for SR < -3 were 8.5 (6.0-12.1) and 2.9 (2.3-3.5), respectively. Spirometric equation prediction models varied less than those for D(L,CO), with the Miller equations being slightly better than Lambda-Mu-Sigma (LMS) equations. Some D(L,CO) equations introduced sex bias (male sex HR of 3.0 versus 1.5 for other equations). We conclude that LMS or Miller spirometry equations and Miller's D(L,CO) equations were best for our patient population. Using patient survival data is a new approach to help select which lung function prediction equations to use.