Double-Lumen Endotracheal Tube—Predicting Insertion Depth and Tube Size Based on Patient’s Chest X-ray Image Data and 4 Other Body Parameters

Abstract

In thoracic surgery, the double lumen endotracheal tube (DLT) is used for differential ventilation of the lung. DLT allows lung collapse on the surgical side that requires access to the thoracic and mediastinal areas. DLT placement for a given patient depends on two settings: a tube of the correct size (or ‘size’) and to the correct insertion depth (or ‘depth’). Incorrect DLT placements cause oxygen desaturation or carbon dioxide retention in the patient, with possible surgical failure. No guideline on these settings is currently available for anesthesiologists, except for the aid by bronchoscopy. In this study, we aimed to predict DLT ‘depths’ and ‘sizes’ applied earlier on a group of patients (n = 231) using a computer modeling approach. First, for these patients we retrospectively determined the correlation coefficient (r) of each of the 17 body parameters against ‘depth’ and ‘size’. Those parameters having r > 0.5 and that could be easily obtained or measured were selected. They were, for both DLT settings: (a) sex, (b) height, (c) tracheal diameter (measured from X-ray), and (d) weight. For ‘size’, a fifth parameter, (e) chest circumference was added. Based on these four or five parameters, we modeled the clinical DLT settings using a Support Vector Machine (SVM). After excluding statistical outliers (±2 SD), 83.5% of the subjects were left for ‘depth’ in the modeling, and similarly 85.3% for ‘size’. SVM predicted ‘depths’ matched with their clinical values at a r of 0.91, and for ‘sizes’, at an r of 0.82. The less satisfactory result on ‘size’ prediction was likely due to the small target choices (n = 4) and the uneven data distribution. Furthermore, SVM outperformed other common models, such as linear regression. In conclusion, this first model for predicting the two DLT key settings gave satisfactory results. Findings would help anesthesiologists in applying DLT procedures more confidently in an evidence-based way.

Keywords

• double lumen endotracheal tube
• medical imaging
• machine learning
• predictive modeling
• support vector machine