Prediction of Endotracheal Tube Depth by Using Deep Convolutional Neural Networks

The Prediction of Proper Depth of Endotracheal Tube Fixation Before Intubation by Using Deep Convolutional Neural Networks and Chest Radiographs

Malposition of an endotracheal tube (ETT) may lead to a great disaster. Developing a handy way to predict the proper depth of ETT fixation is in need. Deep convolutional neural networks (DCNNs) are proven to perform well on chest radiographs analysis. The investigators hypothesize that DCNNs can also evaluate pre-intubation chest radiographs to predict suitable ETT depth and no related studies are found. The authors evaluated the ability of DCNNs to analyze pre-intubation chest radiographs along with patients' data to predict the proper depth of ETT fixation before intubation.

Study Overview

• Status: Completed
• Conditions: Intubation; Machine Learning
• Intervention / Treatment: Diagnostic test: Deep convolutional neural networks analysis

Detailed Description

This was a retrospective, IRB-approved study using chest radiographs images obtained from Picture Archive and Communication System (PACS) at Chang Gung Memorial Hospital, Linkou branch, Taiwan.

A total of 595 de-identified patients' chest radiographs was obtained for this study. The inclusion criteria for this study are patients 18 years or older who were orotracheal intubated within November 2019 to October 2020 and had taken chest radiographs before and immediately after the intubation (<24 hours). Both pre-intubation and post-intubation chest radiographs of a same patient were obtained. Clinical data including age, sex, body height, body weight, depth of ETT fixation were also recorded. All ETT tip to carina distance was manually measured by a same anesthesiologist from post-intubation films and documented. Lip to carina length of each patient can be calculated by adding ETT fixation depth and ETT tip to carina distance.

Pre-intubation chest radiographs (n=595) along with clinical data including age, sex, body height, body weight, and measured lip to carina length are collected for model building. For this study, 476/595 (80%) of those were used for training and 119/595 (20%) for validation randomly selected by AI model. In training process, images and related clinical data along with the measured lip to carina length are fed into and used to fit out AI model. Then, in validation process, the investigators evaluate the model accuracy and efficacy of predicting the lip to carina length with images and clinical data of those unforeseen cases.

• Study Type: Observational
• Enrollment (Actual): 595

Contacts and Locations

Study Locations

• Taiwan
  • Guishan Township
    • Taoyuan, Guishan Township, Taiwan, 333
      • Chang Gung Memorial Hospital, Linkou Branch

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Probability Sample

Study Population

Patients 18 years or older who were orotracheal intubated at Chang Gung Memorial Hospital, Linkou branch, Taiwan.

Description

Inclusion Criteria:

• 18 years or older
• orotracheal intubated within November 2019 to October 2020
• had taken chest radiographs before and within 24hr after intubation

Exclusion Criteria:

• Bad chest radiographs quality that patients' carina can not be recognized
• Patient with bronchial insertions found in post-intubation films
• Nasal intubation

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Training; Images and related clinical data along with the measured lip to carina length of the training group are fed into and used to fit out deep convolutional neural networks model.	Diagnostic test: Deep convolutional neural networks analysis; using Deep convolutional neural networks to analyze pre-intubation chest radiographs along with patients' data to predict the proper depth of ETT fixation
Validation; We evaluate the model accuracy and efficacy of predicting the lip to carina length with images and clinical data of those unforeseen cases in the validation group.	Diagnostic test: Deep convolutional neural networks analysis; using Deep convolutional neural networks to analyze pre-intubation chest radiographs along with patients' data to predict the proper depth of ETT fixation

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
The lip to carina length predicted by AI model	The mean absolute error of AI-predicted length in comparison with measured length is used to evaluate AI performance	1 minute after DCNNs analysis

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Rate of endotracheal tube malpositioning according to AI model recommendation	Endotracheal tube malpositioning is used to elevate the safty of AI recommendation.	1 minute after DCNNs analysis

Collaborators and Investigators

• Sponsor: Chang Gung Memorial Hospital

Publications and helpful links

General Publications

• Lakhani P. Deep Convolutional Neural Networks for Endotracheal Tube Position and X-ray Image Classification: Challenges and Opportunities. J Digit Imaging. 2017 Aug;30(4):460-468. doi: 10.1007/s10278-017-9980-7.
• Lakhani P, Flanders A, Gorniak R. Endotracheal Tube Position Assessment on Chest Radiographs Using Deep Learning. Radiol Artif Intell. 2020 Nov 18;3(1):e200026. doi: 10.1148/ryai.2020200026. eCollection 2021 Jan.
• Eagle CC. The relationship between a person's height and appropriate endotracheal tube length. Anaesth Intensive Care. 1992 May;20(2):156-60. doi: 10.1177/0310057X9202000206.
• Varshney M, Sharma K, Kumar R, Varshney PG. Appropriate depth of placement of oral endotracheal tube and its possible determinants in Indian adult patients. Indian J Anaesth. 2011 Sep;55(5):488-93. doi: 10.4103/0019-5049.89880.
• Techanivate A, Rodanant O, Charoenraj P, Kumwilaisak K. Depth of endotracheal tubes in Thai adult patients. J Med Assoc Thai. 2005 Jun;88(6):775-81.
• Herway ST, Benumof JL. The tracheal accordion and the position of the endotracheal tube. Anaesth Intensive Care. 2017 Mar;45(2):177-188. doi: 10.1177/0310057X1704500207.
• Chong DY, Greenland KB, Tan ST, Irwin MG, Hung CT. The clinical implication of the vocal cords-carina distance in anaesthetized Chinese adults during orotracheal intubation. Br J Anaesth. 2006 Oct;97(4):489-95. doi: 10.1093/bja/ael186. Epub 2006 Jul 27.
• Conrardy PA, Goodman LR, Lainge F, Singer MM. Alteration of endotracheal tube position. Flexion and extension of the neck. Crit Care Med. 1976 Jan-Feb;4(1):8-12. doi: 10.1097/00003246-197601000-00002. No abstract available.

Study record dates

Study Major Dates

• Study Start (Actual): November 1, 2019
• Primary Completion (Actual): October 31, 2020
• Study Completion (Actual): October 31, 2020

Study Registration Dates

• First Submitted: September 24, 2021
• First Submitted That Met QC Criteria: October 6, 2021
• First Posted (Actual): October 20, 2021

Study Record Updates

• Last Update Posted (Actual): October 20, 2021
• Last Update Submitted That Met QC Criteria: October 6, 2021
• Last Verified: October 1, 2021

More Information

Terms related to this study

• Keywords: Depth of ETT fixation; Deep convolutional neural networks; Chest radiographs
• Other Study ID Numbers: 202002007B0

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No