In a breakthrough for Artificial Intelligence in healthcare, the US Food and Drug Administration has approved a new artificial intelligence algorithm that works with portable X-ray machines. The system was developed by GE Healthcare in collaboration with University of California San Francisco (UCSF). The AI-powered portable X-ray machines will soon be deployed to diagnose pneumothorax or a collapsed lung- a condition that can be cured if treated early.

According to University of California San Francisco, tens of thousands of Americans suffer pneumothorax each year, which occurs as a result of air leaks into the chest cavity causing the compression of the lungs. With an early diagnosis, pneumothorax can be treated by inserting a tube to remove the leaked air. However, any delay in the diagnosis of pneumothorax can cause breathing difficulty or even death in some conditions.

“This is a potentially life-threatening finding where time to diagnosis is imperative to optimize outcome. In a high-intensity clinical scenario, pneumothorax can be initially overlooked by the bedside providers,” said Rachael Callcut, MD, an associate professor of surgery at UCSF and trauma surgeon at Zuckerberg San Francisco General Hospital.

The lung screening AI tool, called the Critical Care Suite, was developed under the leadership of Rachael Callcut, who is also the director of data science at the Center for Digital Health Innovation (CDHI) at UCSF. The AI-powered portable X-ray machine can be taken to a patient and the chest X-ray is sent immediately to a radiologist as well as providing alert to doctors if it identifies pneumothorax.