We analyzed breath data from 84 volunteers, each of them suffering from chronic obstructive pulmonary disease (COPD), as well as 35 healthy volunteers, comprising a control group (CG).
Our results suggests a strong potential for separating MCC/IMS chromatograms of healthy controls and COPD patients (best accuracy COPD vs. CG: 94%). Furthermore, we extracted a set of high-scoring VOCs that allow differentiating of COPD patients from healthy controls. Our findings demonstrate a generally high but improvable accuracy of statistical learning methods when applied to well-structured, medical MCC/IMS data.