Real time noninvasive estimation of work of breathing using facemask leak-corrected tidal volume during noninvasive pressure support: validation study

• Published in: Journal of clinical monitoring and computing 2016-06, Vol.30 (3), p.285-294
• Main Authors: Banner, Michael J., Tams, Carl G., Euliano, Neil R., Stephan, Paul J., Leavitt, Trevor J., Martin, A. Daniel, Al-Rawas, Nawar, Gabrielli, Andrea
• Format: Article
• Language: English
• Subjects: Acute Lung Injury - physiopathology; Acute Lung Injury - therapy; Algorithms; Anesthesiology; Breathing; Computer Systems - statistics & numerical data; Critical Care Medicine; Health Sciences; Humans; In vitro testing; In vivo methods and tests; Intensive; Leaks; Learning theory; Medicine; Medicine & Public Health; Monitoring, Physiologic - statistics & numerical data; Neural networks; Neural Networks (Computer); Original Research; Pressure; Respiration, Artificial - instrumentation; Respiration, Artificial - statistics & numerical data; Statistics for Life Sciences; Tidal Volume - physiology; Ventilators; Work of Breathing - physiology
• ISSN: 1387-1307; 1573-2614
• DOI: 10.1007/s10877-015-9716-5

We describe a real time, noninvasive method of estimating work of breathing (esophageal balloon not required) during noninvasive pressure support (PS) that uses an artificial neural network (ANN) combined with a leak correction (LC) algorithm, programmed to ignore asynchronous breaths, that corrects for differences in inhaled and exhaled tidal volume (V T ) from facemask leaks (WOB ANN,LC /min). Validation studies of WOB ANN,LC /min were performed. Using a dedicated and popular noninvasive ventilation ventilator (V60, Philips), in vitro studies using PS (5 and 10 cm H 2 O) at various inspiratory flow rate demands were simulated with a lung model. WOB ANN,LC /min was compared with the actual work of breathing, determined under conditions of no facemask leaks and estimated using an ANN (WOB ANN /min). Using the same ventilator, an in vivo study of healthy adults (n = 8) receiving combinations of PS (3–10 cm H 2 O) and expiratory positive airway pressure was done. WOB ANN,LC /min was compared with physiologic work of breathing/min (WOB PHYS /min), determined from changes in esophageal pressure and V T applied to a Campbell diagram. For the in vitro studies, WOB ANN,LC /min and WOB ANN /min ranged from 2.4 to 11.9 J/min and there was an excellent relationship between WOB ANN,LC /breath and WOB ANN /breath, r = 0.99, r 2  = 0.98 ( p