Evaluating Triple Therapy Treatment Pathways in Chronic Obstructive Pulmonary Disease (COPD): A Machine-Learning...

Area of Science:

• Pulmonary Medicine
• Pharmacology
• Data Science

Background:

• Inhaled triple therapy (TT), combining long-acting muscarinic antagonists, long-acting β2 agonists, and inhaled corticosteroids, is recommended for symptomatic COPD patients.
• Predictors of future exacerbation risk in patients initiating TT are not fully understood.

Purpose of the Study:

• To identify patient characteristics that predict future exacerbation time after initiating inhaled triple therapy (TT) for COPD.
• To assess the impact of baseline patient factors on exacerbation risk post-TT initiation.

Main Methods:

• Retrospective cohort study utilizing a large US health claims database.
• Analysis of 73,625 COPD patients initiating TT between 2008 and 2018.
• Machine learning platform used to predict future COPD exacerbation time based on baseline data.

Main Results:

• Prior exacerbations were strongly correlated with future exacerbation time; ≥4 baseline exacerbations increased post-index time by 32.4 days.
• ≥2 inpatient visits (27.1 days), xanthine use (11.5 days), and rheumatoid arthritis (6.4 days) also increased exacerbation time.
• Anemia (-5.68 days) and recent oral corticosteroid use (-3.43 days) were associated with reduced exacerbation time.

Conclusions:

• Frequent prior exacerbations, healthcare utilization, xanthine use, and rheumatoid arthritis are key predictors of increased future exacerbations in COPD patients on TT.
• These findings enhance understanding of exacerbation risk factors in COPD patients initiating triple therapy.