A capnography waveform displays the level of expired carbon dioxide (CO2) over time to show changes in concentrations throughout the respiratory cycle. Capnography waveform abnormalities assist in the detection and diagnosis of specific conditions, such as partial airway obstruction and apnea. Deciphering which capnography waveform abnormalities deserve intervention from those that do not is an essential step towards the successful implementation of this technology into practice. In this study, capnography waveforms collected as part of an international prospective observational trial of opioid-induced respiratory depression on inpatient wards (the PRODIGY study) will be analyzed. A labeled dataset consisting of ~6000 15-second segments of capnography waveform samples has been created. The research student will assist the investigators to determine the accuracy of a neural network for classifying capnography waveforms.