A Machine-learning Approach to Forecast Aggravation Risk in Patients with Acute Exacerbation of Chronic Obstructive Pulmonary Disease with Clinical Indicators

Abstract

Patients with chronic obstructive pulmonary disease (COPD) repeat acute exacerbations (AE). Global Initiative for Chronic Obstructive Lung Disease (GOLD) is only available for patients in stable phase. Currently, there is a lack of assessment and prediction methods for acute exacerbation of chronic obstructive pulmonary disease (AECOPD) patients during hospitalization. To enhance the monitoring and treatment of AECOPD patients, we develop a novel C5.0 decision tree classifier to predict the prognosis of AECOPD hospitalized patients with objective clinical indicators. The medical records of 410 hospitalized AECOPD patients are collected and 28 features including vital signs, medical history, comorbidities and various inflammatory indicators are selected. The overall accuracy of the proposed C5.0 decision tree classifier is 80.3% (65 out of 81 participants) with 95% Confidence Interval (CI):(0.6991, 0.8827) and Kappa 0.6054. In addition, the performance of the model constructed by C5.0 exceeds the C4.5, classification and regression tree (CART) model and the iterative dichotomiser 3 (ID3) model. The C5.0 decision tree classifier helps respiratory physicians to assess the severity of the patient early, thereby guiding the treatment strategy and improving the prognosis of patients.

Figure 1

The receiver operating characteristic of the proposed C5.0 classifier compared with boosting C45, CART and ID3.

Figure 2

The variables importance of the proposed C5.0 classifier. Note that SMK, AGE, NOH, TEMP, PULSE, RES, SP, DP, PHD, BRCH, HTN, DM, CHD, CKD, MT, CD, HBV and CRHS denote smoking history, age, number of hospitalizations, temperature, pulse rate, respiratory rate, systolic pressure, diastolic pressure, pulmonary heart disease, bronchiectasis, yypertension, diabetes mellitus, coronary heart disease, chronic kidney disease, malignant tumor, cerebrovascular disease, viral hepatitis and Cirrhosis, respectively. While CRP, EO, ESR, HCRP,LC, LYM, MONO, NEUT and PCT are C-reactive protein, absolute value of eosinophils, erythrocyte sedimentation rate, high sensitivity c-reactive protein, leukocyte count, lymphocyte absolute value, nuclear cell absolute value, absolute neutrophils and detection of procalcitonin, respectively.

Figure 3

The result of medical laboratory of serious and mild COPD Patients. Note that CRP, EO, ESR, HCRP,LC, LYM, MONO, NEUT and PCT are C-reactive protein, absolute value of eosinophils, erythrocyte sedimentation rate, high sensitivity c-reactive protein, leukocyte count, lymphocyte absolute value, nuclear cell absolute value, absolute neutrophils and detection of procalcitonin. Unknown, Normal and Abnormal represents no test results, the normal results and abnormal results, respectively.