Neural network-based detection of esophageal intubation in anesthetized patients
- 25 Downloads
Objective. To test whether a neural network-based method could differentiate between tracheal and esophageal intubation in anesthetized patients by recognizing breathing circuit pressure and flow waveform patterns.Methods. Tracheal tubes were placed in the trachea and in the esophagus of adult patients undergoing elective operations. After ensuring for proper oxygenation, ventilator settings were changed to 5 ml/kg tidal volume (VT) and 15 cpm and circuit pressure and flow were recorded for 15 seconds. Then, the breathing circuit was switched to the tube placed in the esophagus, and signals were recorded for an additional 15-second period. During off-line analysis, individual waveforms were separated. Tracheal breaths were labeled with a score of 1 while esophageal “breaths” were labeled with −1. A neural network was defined to learn to associate waveforms to their corresponding scores. Data from 54% of the patients were used to train the neural network. Data from the remaining subjects were used for testing.Results. Forty-six patients were studied. Neural network training was achieved with 100 tracheal and 94 esophageal waveforms from 25 patients. Neural network performance was tested on 84 tracheal and 76 esophageal waveforms from 21 subjects. The neural network assigned scores of 0.99 ±0.05 (mean ± SD) to tracheal waveforms and −0.99 ± 0.03 to esophageal waveforms. The difference between mean esophageal and tracheal scores was −1.99 with a 99.999% confidence range of −2.01 to −1.96. Any arbitrary cutoff threshold, ranging between −0.76 and 0.7, separated tracheal and esophageal score regions, yielding no false positive or negative results.Conclusion. A neural network differentiated consistently tracheal from esophageal intubation when the ventilation testmode was used. The ventilation mode employed is feasible in most adult patients undergoing elective procedures under general anesthesia. Further research is required to train neural networks to recognize esophageal intubation in different age groups and when different ventilation modes are applied.
Key wordsIntubation, intratracheal: adverse effects Complications: esophageal intubation: artificial intelligence, neural networks (computer) diagnosis, computer-assisted pattern recognition signal processing computer-assisted
Unable to display preview. Download preview PDF.