by John R. Fischer
, Senior Reporter | November 18, 2021
GE Healthcare has scored FDA clearance for a new AI algorithm designed to help clinicians properly position endotracheal tubes.
One of the five algorithms in GE’s Critical Care Suite 2.0, a set of AI tools embedded on a mobile X-ray device, the technology is expected to be especially helpful in caring for critically ill COVID-19 patients who require ventilation. This is because X-ray images show ETTs are misplaced in 25% of patients intubated outside of operating rooms, which puts them at risk for severe complications, including hyperinflation, pneumothorax (collapsed lung), cardiac arrest and death.
The algorithm automatically detects ETTs in chest X-ray images and within seconds of acquiring the image, shows an accurate and automated measurement for positioning them. The results are displayed on the X-ray system’s monitor, with the AI-generated measurements and image overlay accessible in the PACS systems.
The technology has been used by 200 hospitals in the last year and the FDA 510(k) clearance allows for it to be sold outside of the public health emergency, says Dr. Amit Gupta, modality director of diagnostic radiography at University Hospital Cleveland Medical Center and assistant professor of radiology at Case Western Reserve University. “Seconds and minutes matter when dealing with a collapsed lung or assessing endotracheal tube positioning in a critically ill patient. 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.”
With an average error of less than 1.0 mm when calculating endotracheal tube tip-to-carina vertical distance, the algorithm can determine if the ETT is placed correctly or not. Additionally, in cases of a suspected pneumothorax, Critical Care Suite 2.0 sends an alert with the original chest X-ray to a radiologist to review it in the PACS, as well as a subsequent on-device notification to the technologist to prioritize the case. This reduces the time patients spend waiting for reviews, which may take up to eight hours.
Critical Care Suite 2.0 is embedded on GE’s AMX 240 and AMX Navigate mobile X-ray device, which allows providers to try out its AI solutions without investing in additional IT infrastructure, security assessments or cybersecurity tools for routing images offsite. Furthermore, Critical Care Suite 2.0 comes with several quality-focused AI algorithms that flag protocol and field of view errors and auto-rotate the images on-device to integrate them into the technologist’s standard workflow, so that they can react to suspicious findings at the patient’s bedside, and before images are sent to PACS.
Up to 45% of ICU patients, including those with severe cases of COVID-19, require ETT intubation for ventilation. As COVID-19 cases continue to increase, 5%-15% of these patients will require intubation for ventilation support and intensive care surveillance.
“The pandemic has proven what we already knew — that data, AI and connectivity are central to helping front line clinicians deliver intelligently efficient care,” said Jan Makela, president and CEO of imaging at GE Healthcare, in a statement.