Automatic Detection of Endotracheal Intubation During the Anesthesia Procedure

Abstract

This paper is concerned with the mathematical modeling and detection of endotracheal (ET) intubation in children under general anesthesia during surgery. In major pediatric surgeries, the airway is often secured with an endotracheal tube (ETT) followed by initiation of mechanical ventilation. Clinicians utilize auscultation of breath sounds and capnography to verify correct ETT placement. However, anesthesia providers often delay timely charting of ET intubation. This latency in event documentation results in decreased efficacy of clinical decision support systems. In order to target this problem, we collected real inpatient data and designed an algorithm to accurately detect the intubation time within the clinically valid range; the results show that we are able to achieve high accuracy in more than 96% of the cases. Automatic detection of ET intubation time would thus enhance better real-time data capture to support future improvement in clinical decision support systems.

Fig. 1

Top: An example of actual EtCO₂ data collected during a T&A surgery. Bottom: A sample of events during intubation. 1, turning off fresh gas flow; 2, intubation; 3, hand ventilation; and 4, taping.

Fig. 2

Schematic overview of the designed algorithm

Fig. 3

Example time series plot of the three features for a sample case

Fig. 4

Example cases for different cases. The vertical lines represent the flagged intubation based on the three measures.

Fig. 5

Examples of two subjects whose algorithm either (a) incorrectly detects the intubation time or (b) fails to detect the intubation

Fig. 6

Histogram plot of the time difference between actual intubation time and flagged intubation time determined by the algorithm