JMIR Publications

ABSTRACT

Background:

Chronic obstructive pulmonary disease (COPD) has two courses with different options for medical treatment: the acute exacerbation phase and the stable phase. Stable patients can use the Global Initiative for Chronic Obstructive Lung Disease (GOLD) to guide treatment strategies. However, GOLD could not classify and guide the treatment of acute exacerbation as acute exacerbation of chronic obstructive pulmonary disease (AECOPD) is a complex process.

Objective:

In order to strengthen monitoring and medical interventions in advance, this paper proposes a fast severity assessment and risk prediction approach.

Methods:

The proposed method uses a classification and regression tree (CART), has been validated using the AECOPD inpatient’s medical history and first measured vital signs at admission that can be collected within minutes. We identify 552 inpatients with AECOPD from February 2011 to June 2018 retrospectively and use the classifier to predict the outcome and prognosis of this hospitalization.

Results:

The overall accuracy of the proposed CART classifier is 76.2% (83 out of 109 participants) with 95% Confidence Interval (CI): (0.6703, 0.8379). The precision, recall, and F-Measure for the mild AECOPD are 76.9% (50 out of 65 participants), 82 % (50 out of 61 participants) and 0.7936, respectively, and those severe AECOPD are 75% (33 out of 44 participants), 68.8% (33 out of 48 participants) and 0.7174, respectively.

Conclusions:

This fast prediction CART classifier for early exacerbation detection could trigger the initiation of timely treatment, thereby potentially reduce exacerbation severity and recovery time and improving the patients’ health.