Differential features for a neural network based anesthesia alarm system.

Abstract

We have developed a neural network based alarm system that identifies 19 specific faults in the anesthesia breathing circuit, such as "Inspiratory Hose Leak," or "Y-Piece Disconnection." CO2, pressure, and expired flow waveforms, along with ventilator settings, were sampled by a personal computer. Fifty-two features, such as "maximum CO2" or "minimum pressure", were extracted from each breath, converted to "differential" features, normalized, and used as the inputs of a three layered feed-forward neural network. The network was trained, using backward error propagation with momentum, to classify each breath as normal or containing one of 19 faults. To collect the neutral network training set, seven dogs were anesthetized and ventilated using controlled ventilation. Each of 19 faults were created over a range of ventilator settings and fresh gas flows. The neural network correctly identified 83.1% of 550 events presented to it during testing. These preliminary results are an encouraging example of neural network applications in the field of clinical monitoring.