The U.S. Food and Drug Administration has given clearance to suite of of artificial intelligence algorithms embedded on a mobile X-ray device from GE Healthcare.

WHY IT MATTERS
The platform, Critical Care Suite, developed in partnership with UC San Francisco and powered by GE's Edison AI technology, can help radiologists prioritize cases involving collapsed lungs.

When a patient is scanned on a device with Critical Care Suite, the platform provides triage notifications that are then sent to PACS systems upon transfer of the original diagnostic image.

The suite also enables PACS worklist prioritization, and offers an on-device notification to the technologist – the aim is to drastically cut the average review time, which currently takes up to eight hours.

GE Healthcare claims the platform can detect nearly all large pneumothoraxes (96 percent sensitivity), with 75 percent for small pneumothoraxes while sharply limiting false alerts.

In addition, the Edison platform's embedded data processing analytics provide for automated AI quality check features, which can detect acquisition errors.

That means images will be flagged for technologist review, allowing them to make corrections, such as rejections or reprocessing—or even auto rotate the images on-device, before they go to radiologists for review.

THE LARGER TREND
Given the high number or STAT priority portable chest radiographs ordered, prioritizing acquisition and interpretation of true STATs has become challenging for technologists and radiologists.

In many cases these this has leads to process inefficiencies, long turnaround times communication failures, and patient-safety errors, as evidenced by a radiology case study published last year.

GE's announcement comes as AI technology continues to advance into advanced medical technology, with tech giants like IBM and its Watson platform developing predictive algorithms, while Nuance is using AI to help surgeons with documentation.

Last month, Progknowse announced it is working with LifeBridge Health, Riverside Health and St. Luke's University Health Network to develop new machine learning algorithms for personalized care.

However, AI's future in healthcare is not entirely rosy, and numerous challenges, including data security and interoperability issues, could hinder AI growth in healthcare unless the industry improves, according to an August report published in Nature partner journal Digital Medicine.

ON THE RECORD
"When a patient X-ray is taken, the minutes and hours it takes to process and interpret the image can impact the outcome in either direction," said UCSF surgeon Dr. Rachael Callcut in a statement. "AI gives us an opportunity to speed up diagnosis, and change the way we care for patients, which could ultimately save lives and improve outcomes."

“Currently, 62 percent of exams are marked ‘STAT’ or for urgent reading, but they aren’t all critical," explained Jie Xue, President & CEO, X-ray, GE Healthcare. "Not only does Critical Care Suite flag images with a suspected pneumothorax with impressive accuracy and enable radiologists to prioritize 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."