A multiobjective optimization approach to pulmonary rehabilitation effectiveness in COPD

Abstract

Chronic obstructive pulmonary disease (COPD) is a common disease that accounts for a significant individualand societal burden. Pulmonary rehabilitation (PR) is a key management strategy but it is highly inaccessible, makingprioritisation highly needed. This study aimed to determine and optimize predictive models of PR outcomes and builda tool to help healthcare professionals in their clinical decision-making about PR prioritisation. Data from patients whoperformed a 12-week community-based PR programme were analysed. Exercise capacity with the six-minutes walk testdistance (6MWD), isometric quadriceps muscle strength with the handheld dynamometry (QMS) and dyspnoea with themodified Medical Research Council dyspnoea scale (mMRC) were assessed before and after PR. Multiple linear regressionmodels were determined based on the Akaike information criteria and a cross-validation method. The resultant multiobjectiveproblem was solved using the Nondominated Sorting Genetic Algorithm-II.R Shinypackage was used to create a web-baseduser interface. Data from 95 patients with COPD (median age of 69 years, 19 female and generally overweight), resulted inlinear predictive models for the post-pre difference of the 6MWD, QMS and mMRC with cross-validationR2of 0.49, 0.53and 0.51, respectively. 6MWD and mMRC were common statistically significant predictors. Pareto front patients were obeseex-smoker women that do not do long-term oxygen therapy and that performed PR. The distance to the Pareto front alongwith the estimates given by our models are easily obtained using the designedR Shinyinterface and may help healthcareprofessionals decide on the prioritisation to PR programmes.