Thesis Supervisor Accepted by:

Existing methods for extracting diagnostic information from carbon dioxide in the ex-haled breath are qualitative, through visual inspection, and therefore imprecise. In this thesis, we quantify the CO 2 waveform, or capnogram, in order to discriminate among various lung disorders. Quantitative analyses of the capnogram are conducted by ex-tracting several physiological waveform features and performing classification by dis-criminant analysis with voting. Our classification methods are tested in distinguishing between records from subjects with normal lung function and patients with cardiores-piratory disease. In a second step, we discriminate between capnograms from patients with obstructive lung disease (chronic obstructive pulmonary disease) and those with re-strictive lung disease (congestive heart failure). Our results demonstrate the diagnostic potential of capnography