Towards individualised medicine for airways disease: identifying clinical phenotype groups

COPD phenotypes and machine learning cluster analysis: A systematic review and future research agenda

Chronic Obstructive Pulmonary Disease (COPD) is a highly heterogeneous condition projected to become the third leading cause of death worldwide by 2030. To better characterize this condition, clinicians have classified patients sharing certain symptomatic characteristics, such as symptom intensity and history of exacerbations, into distinct phenotypes. In recent years, the growing use of machine learning algorithms, and cluster analysis in particular, has promised to advance this classification through the integration of additional patient characteristics, including comorbidities, biomarkers, and genomic information. This combination would allow researchers to more reliably identify new COPD phenotypes, as well as better characterize existing ones, with the aim of improving diagnosis and developing novel treatments. Here, we systematically review the last decade of research progress, which uses cluster analysis to identify COPD phenotypes. Collectively, we provide a systematized account of the extant evidence, describe the strengths and weaknesses of the main methods used, identify gaps in the literature, and suggest recommendations for future research.

Treatment responsiveness of phenotypes of symptomatic airways obstruction in adults

BACKGROUND

Asthma and chronic obstructive pulmonary disease (COPD) are heterogeneous disorders encompassing different phenotypes of airflow obstruction, which might differ in their response to treatment.

OBJECTIVE

The aim of this study was to determine distinct phenotypes comprising the syndromes of asthma and COPD and the treatment responsiveness of these phenotypes to inhaled β-agonist, antimuscarinic, and corticosteroid therapy.

METHODS

We undertook a cross-sectional study with 3 phases. In phase 1, 1,264 participants aged 18 to 75 years with self-reported current wheeze and breathlessness were identified from a random population sample of 16,459. In phase 2, 451 participants attended for detailed assessment, including responsiveness to inhaled salbutamol and ipratropium bromide. In phase 3, 168 steroid-naive participants were enrolled in a 12-week trial of inhaled budesonide. Cluster analysis was performed in 389 participants who completed phase 2 with full data. Treatment responsiveness was compared between phenotypes.

RESULTS

Cluster analysis identified 5 phenotypes: moderate-to-severe childhood-onset atopic asthma, asthma-COPD overlap, obese-comorbid, mild childhood-onset atopic asthma, and mild intermittent. Bronchodilation after salbutamol was equal to or greater than that after ipratropium for all phenotypes. The moderate-to-severe childhood-onset atopic asthma, asthma-COPD overlap, and obese-comorbid phenotypes had greater efficacy with inhaled corticosteroid treatment than the mild intermittent group.

CONCLUSION

Cluster analysis of adults with symptomatic airflow obstruction identifies 5 disease phenotypes, including asthma-COPD overlap and obese-comorbid phenotypes, and provides evidence that patients with the asthma-COPD overlap syndrome might benefit from inhaled corticosteroid therapy.

Inhaled corticosteroids in COPD: the clinical evidence

In this article, we focus on the scientific evidence from randomised trials supporting treatment with inhaled corticosteroids (ICS) in chronic obstructive pulmonary disease (COPD), including treatment with combinations of long-acting β-agonist (LABA) bronchodilators and ICS. Our emphasis is on the methodological strengths and limitations that guide the conclusions that may be drawn. The evidence of benefit of ICS and, therefore, of the LABA/ICS combinations in COPD is limited by major methodological problems. From the data reviewed herein, we conclude that there is no survival benefit independent of the effect of long-acting bronchodilation and no effect on FEV1 decline, and that the possible benefit on reducing severe exacerbations is unclear. Our interpretation of the data is that there are substantial adverse effects from the use of ICS in patients with COPD, most notably severe pneumonia resulting in excess deaths. Currently, the most reliable predictor of response to ICS in COPD is the presence of eosinophilic inflammation in the sputum. There is an urgent need for better markers of benefit and risk that can be tested in randomised trials for use in routine specialist practice. Given the overall safety and effectiveness of long-acting bronchodilators in subjects without an asthma component to their COPD, we believe use of such agents without an associated ICS should be favoured.

Risk of pneumonia with inhaled corticosteroid/long-acting β2 agonist therapy in chronic obstructive pulmonary disease: a cluster analysis

Background

Pneumonia poses a significant risk in patients with moderate to severe chronic obstructive pulmonary disease but data are limited on the disease phenotypes most susceptible to pneumonia.

Methods

Cluster analysis using a data-driven recursive partitioning algorithm was employed using baseline data from two pooled one-year randomized exacerbation trials (n=3,255) of fluticasone furoate/vilanterol or vilanterol alone to identify distinct patient groups at greatest risk of pneumonia or serious (hospitalization or death) pneumonia.

Results

Five clusters were identified. Patients at greater risk of first pneumonia had more severe obstruction (forced expiratory volume in one second/forced vital capacity <46%) and either a body mass index <19 kg/m² (hazard ratio 7.8, 95% confidence interval 4.7–13.0; n=144) or a pneumonia history and greater comorbidities (hazard ratio 4.8, 95% confidence interval 3.0–7.7; n=374) relative to the cluster with the lowest pneumonia risk (reference; n=1310). Multiple comorbidities and use of psychoanaleptics also contributed to an increased risk of pneumonia in more obstructed patients. Independent of cluster, use of inhaled corticosteroids was associated with pneumonia (hazard ratio 1.89, 95% confidence interval 1.25–2.84) and serious pneumonia (hazard ratio 2.92, 95% confidence interval 1.40–6.01).

Conclusion

Cluster analysis can identify patient populations at risk for serious safety outcomes and inform risk management strategies to optimize patient management. The greatest risk for pneumonia was in subjects with multiple pneumonia risk factors.