Shi Y, Zhang J, Huang Y, et al. - The results showed that among chronic obstructive pulmonary disease (COPD) patients, the random forest model performed better predictive effectiveness for the cardiovascular risk, which may be beneficial for clinicians to guide the clinical practice.

• Researchers retrieved a total of 3,226 COPD patients from National Health and Nutrition Examination Survey (NHANES) 2007–2012, dividing them into the training (n = 2,351) and testing (n = 895) sets.

• They constructed the logistic regression model for predicting the risk of cardiovascular disease (CVD) regarding age, gender, body mass index (BMI), high-density lipoprotein (HDL), glycosylated hemoglobin (HbA1c), family history of heart disease, and stayed overnight in the hospital due to illness last year, which the AUC of the internal validation was 0.741.

• The important variables associated with CVD risk according to the random forest analysis were screened including smoking (NNAL and cotinine), HbA1c, HDL, age, gender, diastolic blood pressure, poverty income ratio, BMI, systolic blood pressure, and sedentary activity per day.

• As per the findings, 0.984 was the AUC of the internal validation, demonstrating the random forest model for predicting the CVD risk in COPD cases was superior to the logistic regression model.