Predictive modeling of COPD exacerbation rates using baseline risk factors

Dave Singh, John R Hurst, Fernando J Martinez, Klaus F Rabe, Mona Bafadhel, Martin Jenkins, Domingo Salazar, Paul Dorinsky, Patrick Darken, Dave Singh, John R Hurst, Fernando J Martinez, Klaus F Rabe, Mona Bafadhel, Martin Jenkins, Domingo Salazar, Paul Dorinsky, Patrick Darken

Abstract

Background: Demographic and disease characteristics have been associated with the risk of chronic obstructive pulmonary disease (COPD) exacerbations. Using previously collected multinational clinical trial data, we developed models that use baseline risk factors to predict an individual's rate of moderate/severe exacerbations in the next year on various pharmacological treatments for COPD.

Methods: Exacerbation data from 20,054 patients in the ETHOS, KRONOS, TELOS, SOPHOS, and PINNACLE-1, PINNACLE-2, and PINNACLE-4 studies were pooled. Machine learning was used to identify predictors of moderate/severe exacerbation rates. Important factors were selected for generalized linear modeling, further informed by backward variable selection. An independent test set was held back for validation.

Results: Prior exacerbations, eosinophil count, forced expiratory volume in 1 s percent predicted, prior maintenance treatments, reliever medication use, sex, COPD Assessment Test score, smoking status, and region were significant predictors of exacerbation risk, with response to inhaled corticosteroids (ICSs) increasing with higher eosinophil counts, more prior exacerbations, or additional prior treatments. Model fit was similar in the training and test set. Prediction metrics were ~10% better in the full model than in a simplified model based only on eosinophil count, prior exacerbations, and ICS use.

Conclusion: These models predicting rates of moderate/severe exacerbations can be applied to a broad range of patients with COPD in terms of airway obstruction, eosinophil counts, exacerbation history, symptoms, and treatment history. Understanding the relative and absolute risks related to these factors may be useful for clinicians in evaluating the benefit: risk ratio of various treatment decisions for individual patients.Clinical trials registered with www.clinicaltrials.gov (NCT02465567, NCT02497001, NCT02766608, NCT02727660, NCT01854645, NCT01854658, NCT02343458, NCT03262012, NCT02536508, and NCT01970878).

Keywords: ICS/LAMA/LABA; chronic obstructive pulmonary disease; exacerbations; machine learning; prediction model; triple therapy.

Conflict of interest statement

Conflict of interest statement: The authors declared the following potential conflicts of interest with respect to the research, authorship, and/or publication of this article: DSi reports personal fees from AstraZeneca during the conduct of the study and personal fees from AstraZeneca, Boehringer Ingelheim, Chiesi, Cipla, Genentech, GlaxoSmithKline, Glenmark, Gossamerbio, Menarini, Mundipharma, Novartis, Peptinnovate, Pfizer, Pulmatrix, Theravance, and Verona, outside the submitted work. JRH reports personal fees from AstraZeneca during the conduct of the study and personal fees from AstraZeneca, Boehringer Ingelheim, Chiesi, and Novartis, outside the submitted work. FJM reports grants, personal fees, and non-financial support from AstraZeneca during the conduct of the study; grants, personal fees, and non-financial support from AstraZeneca, Boehringer Ingelheim, GlaxoSmithKline, Novartis, Pearl Therapeutics, Sunovion, Theravance, and Verona; grants and personal fees from Sanofi; personal fees from Circassia, Innoviva, and Mylan; and grants from Altavant, outside the submitted work. KFR reports grants and personal fees from AstraZeneca and Boehringer Ingelheim; personal fees from Chiesi, Novartis, Regeneron, Roche, and Sanofi, outside the submitted work. MB reports grants from AstraZeneca; honoraria from AstraZeneca, Chiesi, and GlaxoSmithKline; and is on the scientific advisory board for AlbusHealth and ProAxsis. MJ, DSa, and PDa are employees of AstraZeneca and hold stock and/or stock options in the company. PDo is a former employee of AstraZeneca and previously held stock and/or stock options in the company.

Figures

Figure 1.
Figure 1.
Predictive factors of annual moderate/severe exacerbation rates: (a) main effects and (b) interaction terms with budesonide. CAT, COPD Assessment Test; CI, confidence interval; COPD, chronic obstructive pulmonary disease; F, female; FEV1, forced expiratory volume in 1 s; ICS, inhaled corticosteroid; LABA, long-acting β2-agonist; LAMA, long-acting muscarinic antagonist; M, male; N, no; Y, yes.
Figure 2.
Figure 2.
Predicted annual moderate/severe exacerbation rate by blood eosinophil count (cells/mm3) according to prior therapy and exacerbation history. BFF, budesonide/formoterol fumarate; BGF, budesonide/glycopyrrolate/formoterol fumarate; CAT, COPD Assessment Test; COPD, chronic obstructive pulmonary disease; exacs, moderate/severe exacerbations; FEV1, forced expiratory volume in 1 s; GFF, glycopyrrolate/formoterol fumarate; ICS, inhaled corticosteroid; LABA, long-acting β2-agonist; LAMA, long-acting muscarinic antagonist. Banded areas denote the standard error. For all panels, results are for a patient with COPD with the following characteristics: 65-year-old, former smoker, from North America, FEV1 45% of predicted, CAT score of 20, using three puffs/day of reliever. For the training set, each panel represents the following proportion of patients in the source population: LAMA only, 0 exacs = 3.8%; LAMA only, 1 exacs = 1.3%; LAMA only, 2 exacs = 0.5%; ICS/LABA, 0 exacs = 9.7%; ICS/LABA, 1 exacs = 11.7%; ICS/LABA, 2 exacs = 9.4%; ICS/LAMA/LABA, 0 exacs = 4.5%; ICS/LAMA/LABA, 1 exacs = 12.0%; ICS/LAMA/LABA, 2 exacs = 9.9%.

References

    1. Halpin DMG, Decramer M, Celli BR, et al.. Effect of a single exacerbation on decline in lung function in COPD. Respir Med 2017; 128: 85–91.
    1. Suissa S, Dell’Aniello S, Ernst P. Long-term natural history of chronic obstructive pulmonary disease: severe exacerbations and mortality. Thorax 2012; 67: 957–963.
    1. Seemungal TAR, Donaldson GC, Paul EA, et al.. Effect of exacerbation on quality of life in patients with chronic obstructive pulmonary disease. Am J Respir Crit Care Med 1998; 157: 1418–1422.
    1. Blasi F, Cesana G, Conti S, et al.. The clinical and economic impact of exacerbations of chronic obstructive pulmonary disease: a cohort of hospitalized patients. PLOS ONE 2014; 9: e101228.
    1. Global Initiative for Chronic Obstructive Lung Disease. Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease. Report, 2021.
    1. Müllerová H, Shukla A, Hawkins A, et al.. Risk factors for acute exacerbations of COPD in a primary care population: a retrospective observational cohort study. BMJ Open 2014; 4: e006171.
    1. Santibáñez M, Garrastazu R, Ruiz-Nuñez M, et al.. Predictors of hospitalized exacerbations and mortality in chronic obstructive pulmonary disease. PLOS ONE 2016; 11: e0158727.
    1. Hurst JR, Vestbo J, Anzueto A, et al.. Susceptibility to exacerbation in chronic obstructive pulmonary disease. New Engl J Med 2010; 363: 1128–1138.
    1. Bafadhel M, Peterson S, De Blas MA, et al.. Predictors of exacerbation risk and response to budesonide in patients with chronic obstructive pulmonary disease: a post-hoc analysis of three randomised trials. Lancet Respir Med 2018; 6: 117–126.
    1. Pascoe S, Barnes N, Brusselle G, et al.. Blood eosinophils and treatment response with triple and dual combination therapy in chronic obstructive pulmonary disease: analysis of the IMPACT trial. Lancet Respir Med 2019; 7: 745–756.
    1. Pascoe S, Locantore N, Dransfield MT, et al.. Blood eosinophil counts, exacerbations, and response to the addition of inhaled fluticasone furoate to vilanterol in patients with chronic obstructive pulmonary disease: a secondary analysis of data from two parallel randomised controlled trials. Lancet Respir Med 2015; 3: 435–442.
    1. Ferguson GT, Rabe KF, Martinez FJ, et al.. Triple therapy with budesonide/glycopyrrolate/formoterol fumarate with co-suspension delivery technology versus dual therapies in chronic obstructive pulmonary disease (KRONOS): a double-blind, parallel-group, multicentre, phase 3 randomised controlled trial. Lancet Respir Med 2018; 6: 747–758.
    1. Rabe KF, Martinez FJ, Ferguson GT, et al.. Triple inhaled therapy at two glucocorticoid doses in moderate-to-very-severe COPD. New Engl J Med 2020; 383: 35–48.
    1. Hoogendoorn M, Feenstra TL, Boland M, et al.. Prediction models for exacerbations in different COPD patient populations: comparing results of five large data sources. Int J Chron Obstruct Pulmon Dis 2017; 12: 3183–3194.
    1. Adibi A, Sin DD, Safari A, et al.. The Acute COPD Exacerbation Prediction Tool (ACCEPT): a modelling study. Lancet Respir Med 2020; 8: 1013–1021.
    1. Annavarapu S, Goldfarb S, Gelb M, et al.. Development and validation of a predictive model to identify patients at risk of severe COPD exacerbations using administrative claims data. Int J Chron Obstruct Pulmon Dis 2018; 13: 2121–2130.
    1. Yii ACA, Loh CH, Tiew PY, et al.. A clinical prediction model for hospitalized COPD exacerbations based on ‘treatable traits’. Int J Chron Obstruct Pulmon Dis 2019; 14: 719–728.
    1. Ichinose M, Fukushima Y, Inoue Y, et al.. Long-term safety and efficacy of budesonide/glycopyrrolate/formoterol fumarate metered dose inhaler formulated using co-suspension delivery technology in Japanese patients with COPD. Int J Chron Obstruct Pulmon Dis 2019; 14: 2993–3002.
    1. Kerwin EM, Ferguson GT, Mo M, et al.. Bone and ocular safety of budesonide/glycopyrrolate/formoterol fumarate metered dose inhaler in COPD: a 52-week randomized study. Respir Res 2019; 20: 167.
    1. Ferguson GT, Papi A, Anzueto A, et al.. Budesonide/formoterol MDI with co-suspension delivery technology in COPD: the TELOS study. Eur Respir J 2018; 52: 1801334.
    1. Hanania NA, Papi A, Anzueto A, et al.. Efficacy and safety of two doses of budesonide/formoterol fumarate metered dose inhaler in COPD. ERJ Open Res 2020; 6: 00187-2019.
    1. Martinez FJ, Rabe KF, Ferguson GT, et al.. Efficacy and safety of glycopyrrolate/formoterol metered dose inhaler formulated using co-suspension delivery technology in patients with COPD. Chest 2017; 151: 340–357.
    1. Hanania NA, Tashkin DP, Kerwin EM, et al.. Long-term safety and efficacy of glycopyrrolate/formoterol metered dose inhaler using novel Co-Suspension™ Delivery Technology in patients with chronic obstructive pulmonary disease. Respir Med 2017; 126: 105–115.
    1. Lipworth BJ, Collier DJ, Gon Y, et al.. Improved lung function and patient-reported outcomes with co-suspension delivery technology glycopyrrolate/formoterol fumarate metered dose inhaler in COPD: a randomized Phase III study conducted in Asia, Europe, and the USA. Int J Chron Obstruct Pulmon Dis 2018; 13: 2969–2984.
    1. Friedman JH. Stochastic gradient boosting. Comput Stat Data An 2002; 38: 367–378.
    1. Foster JC, Taylor JM, Ruberg SJ. Subgroup identification from randomized clinical trial data. Stat Med 2011; 30: 2867–2880.
    1. Lipkovich I, Dmitrienko A, D’Agostino BR, Sr. Tutorial in biostatistics: data-driven subgroup identification and analysis in clinical trials. Stat Med 2017; 36: 136–196.
    1. Hothorn T, Zeileis A. partykit: a modular toolkit for recursive partytioning in R. J Mach Learn Res 2015; 16: 3905–3909.
    1. Zeileis A, Hothorn T, Hornik K. Model-based recursive partitioning. J Comput Graph Stat 2008; 17: 492–514.
    1. Zeileis A, Hothorn T. Parties, models, mobsters: a new implementation of model-based recursive partitioning in R. Comprehensive R Archive Network.
    1. Loh WY, He X, Man M. A regression tree approach to identifying subgroups with differential treatment effects. Stat Med 2015; 34: 1818–1833.
    1. Loh WY, Man M, Wang S. Subgroups from regression trees with adjustment for prognostic effects and postselection inference. Stat Med 2019; 38: 545–557.
    1. Hastie T, Tibshirani R, Friedman J. The elements of statistical learning: data mining, inference and prediction. Springer, 2001. .
    1. Halpin DMG, Dransfield MT, Han MK, et al.. The effect of exacerbation history on outcomes in the IMPACT trial. Eur Respir J 2020; 55: 1901921.
    1. Kerkhof M, Freeman D, Jones R, et al.. Predicting frequent COPD exacerbations using primary care data. Int J Chron Obstruct Pulmon Dis 2015; 10: 2439–2450.
    1. Bertens LC, Reitsma JB, Moons KG, et al.. Development and validation of a model to predict the risk of exacerbations in chronic obstructive pulmonary disease. Int J Chron Obstruct Pulmon Dis 2013; 8: 493–499.
    1. Stanford RH, Nag A, Mapel DW, et al.. Claims-based risk model for first severe COPD exacerbation. Am J Manag Care 2018; 24: e45–e53.
    1. Ställberg B, Lisspers K, Larsson K, et al.. Predicting hospitalization due to COPD exacerbations in Swedish primary care patients using machine learning – based on the ARCTIC study. Int J Chron Obstruct Pulmon Dis 2021; 16: 677–688.
    1. Tavakoli H, Chen W, Sin DD, et al.. Predicting severe chronic obstructive pulmonary disease exacerbations. Developing a population surveillance approach with administrative data. Ann Am Thorac Soc 2020; 17: 1069–1076.

Source: PubMed

Sponsors and Collaborators

Medical Conditions

Drug Interventions

3
Subscribe