Cluster Analyses From the Real-World NOVELTY Study: Six Clusters Across the Asthma-COPD Spectrum

Background Asthma and chronic obstructive pulmonary disease (COPD) are complex diseases whose definitions overlap. Objective To investigate clustering of clinical/physiological features and readily available biomarkers in patients with physician-assigned diagnoses of asthma and/or COPD in NOVELTY (NCT02760329). Methods Two approaches were taken to variable selection, using baseline data: approach A was data-driven, hypothesis-free, using Pearson’s dissimilarity matrix; approach B used an unsupervised Random Forest guided by clinical input. Cluster analyses were conducted across 100 random resamples using partitioning around medoids, followed by consensus clustering. Results Approach A included 3,796 individuals (mean age 59.5 years, 54% female); approach B included 2,934 patients (mean age 60.7 years, 53% female). Each identified six mathematically stable clusters, which had overlapping characteristics. Overall, 67–75% of asthma patients were in three clusters, and ∼90% of COPD patients in three clusters. Although traditional features like allergies and current/ex-smoking (respectively) were higher in these clusters, there were differences between clusters and approaches in features such as sex, ethnicity, breathlessness, frequent productive cough and blood cell counts. The strongest predictors of approach A cluster membership were age, weight, childhood onset, pre-bronchodilator FEV1, duration of dust/fume exposure and number of daily medications. Conclusion Cluster analyses in NOVELTY patients with asthma and/or COPD yielded identifiable clusters, with several discriminatory features that differed from conventional diagnostic characteristics. The overlap between clusters suggests that they do not reflect discrete underlying mechanisms, and points to the need for identification of molecular endotypes and potential treatment targets across asthma and/or COPD.