Radiographic AI Helps Assess Endotracheal Tube Placement

The AI algorithm automatically detects ETTs in CXR images and generates accurate measurements--along with an image overlay--with an average error of less than one mm, when calculating the ETT tip-to-carina vertical distance.

The measurements are displayed on the monitor of the x-ray system, and are also accessible in the picture archiving and communication system (PACS) within seconds of image acquisition. With the aid of these measurements, clinicians can determine if the ETT is placed correctly, or if additional attention is required for proper placement. Several quality-focused AI algorithms automatically run checks on-device, enabling technologist actions, such as rejections or reprocessing at the patient’s bedside, and before the images are sent to PACS.

“At GE Healthcare, we saw the potential role of Critical Care Suite 2.0 in helping hospitals manage the crisis caused by the number of patients who needed ETT placements during the pandemic,” said Jan Makela, president and CEO of Imaging at GE Healthcare. “The pandemic has proven what we already knew – that data, AI, and connectivity are central to helping front line clinicians deliver intelligently efficient care.”

“Seconds and minutes matter when dealing with a collapsed lung or assessing ETT positioning in a critically ill patient,” said Amit Gupta, MD, modality director of diagnostic radiography at University Hospital Cleveland Medical Center (OH, USA). “In several COVID-19 patient cases, the pneumothorax AI algorithm has proved prophetic, accurately identifying pneumothoraces/barotrauma in intubated COVID-19 patients, flagging them to radiologist and radiology residents, and enabling expedited patient treatment.”

Studies have shown that up to 25% of patients intubated outside of the operating room (OR) have misplaced ETTs, which can lead to severe complications such as hyperinflation, pneumothorax, cardiac arrest, and death. Moreover, up to 45% of ICU patients, including 5-15% of COVID-19 patients, require intensive care surveillance and intubation for ventilatory support.

Related Links:
GE Healthcare