ABSTRACT
The goal of the exhaled breath waveform used in ventilation monitoring is to improve COVID-19 illness detection. Using exhaled breath patterns to differentiate between COVID and non-COVID healthy individuals, an algorithm for valid exhaled breath waveform segmentation and feature computation is created to identify the COVID-19 infection. A two-minute exhaled breath pattern was recorded using a device and a nasal cannula sampling tube, resulting in the collection of exhaled breath waveforms from each subject. The developed algorithm is utilized to evaluate the valid exhaled breath waveforms and compute the features classified to distinguish between individuals who contracted COVID-19 infection and this who are healthy. Slope e2, activity e2 and intersection angle of expiration and inspiration phase showed p-value of 0.000, denoting the strong significance difference between COVID-19 patients and non-COVID healthy individuals. The statistical analyses revealed p-values of 0.039, 0.008, and 0.024 for area e2, mobility of e2 and complexity e3, indicating its significance in differentiating COVID-19 patients with non-COVID healthy individuals. The slope, area, and intersection angle as significant features showed good predictive power for compliance with p-value analysis with area under the receiver operating characteristic curve with 0.667, 0.693, and 0.775. Slope of e2, area of e2, intersection angle of expiration and inspiration phases are identified as the promising features to be chosen in discriminating COVID and non-COVID individuals. Trial registration: Clinical trial approval by Medical Research and Ethics Committee (MREC), 53 Malaysia, NMRR-21-763-59692. Registered 9th June 2021 and valid till 8th June 2023.