JMIR Publications

ABSTRACT

Background:

Chronic obstructive pulmonary disease (COPD) poses a large burden on healthcare. Severe COPD exacerbations require emergency department visits or inpatient stays, often cause irreversible decline in lung function and health status, and account for 90.3% of the total medical cost related to COPD. Many severe COPD exacerbations are deemed preventable with appropriate outpatient care. Current models for predicting severe COPD exacerbations lack accuracy, making it difficult to effectively target high-risk patients for preventive care management to reduce severe COPD exacerbations and improve outcomes.

Objective:

To develop a more accurate model to predict severe COPD exacerbations.

Methods:

We examined all patients with COPD who visited the University of Washington Medicine (UWM) facilities between 2011 and 2019 and identified 278 candidate features. By doing secondary analysis on 43,576 UWM data instances from 2011 to 2019, we created a machine learning model to predict severe COPD exacerbations in the next year for patients with COPD.

Results:

The final model had an area under the receiver operating characteristic curve of 0.866. When using the top 10.00% (752/7,529) of patients with the largest predicted risk to set the cutoff threshold for binary classification, the model gained an accuracy of 90.33% (6,801/7,529), a sensitivity of 56.6% (103/182), and a specificity of 91.17% (6,698/7,347).

Conclusions:

Our model provided more accurate prediction of severe COPD exacerbations in the next year compared to prior published models. After further improvement of its performance measures (e.g., by adding features extracted from clinical notes), our model could be used in a decision support tool to guide identification of high-risk patients with COPD for care management to improve outcomes.