The US Food and Drug Administration (FDA) has granted 510(k) clearance to GE Healthcare’s artificial intelligence (AI) algorithms, Critical Care Suite, to identify pneumothorax, a type of collapsed lung.
The AI algorithms are based on the company’s Edison platform and incorporated on a mobile X-ray device. The technology is intended to cut the turn-around time required by radiologists to review chest X-rays for suspected pneumothorax.
GE Healthcare has said that review of a prioritised ‘STAT’ X-ray may not be carried out by a radiologist for up to eight hours.
When a patient scans on a device with Critical Care Suite, the system examines the images by instantaneously searching for a pneumothorax.
In case of a suspected pneumothorax, the AI algorithms send a notification and the original X-ray image through picture archiving and communication systems (PACS) to the radiologist.
The system then sends an on-device alert for the prioritised cases.
Critical Care Suite simultaneously analyses, flags protocol and any field of view errors and also auto rotates the images on-device.
GE Healthcare X-ray president and CEO Jie Xue said: “Not only does Critical Care Suite flag images with a suspected pneumothorax with impressive accuracy and enable radiologists to prioritise those cases immediately but it also makes AI accessible.
“Our embedded AI algorithms offer hospitals an opportunity to try AI without making investments into additional IT infrastructure, security assessments or cybersecurity precautions for routing images offsite.”
Development of Critical Care Suite is in alliance with the University of California, San Francisco (UCSF), St. Luke’s University Health Network, Humber River Hospital and CARING - Mahajan Imaging - India.
The AI algorithms deliver results within seconds of imaging, without depending on connectivity or transfer speeds, added the company.
GE Healthcare added that automatic on-device quality checks can take place alongside radiologists’ standard workflow. Furthermore, rejection or reprocessing can be carried out at the patient’s bedside.