By Fred Donovan, HIT Infrastructure | November 26, 2018
GE Healthcare has unveiled its Edison healthcare artificial intelligence platform designed to connect data on millions of medical imaging devices.
The company said that clinical partners will be able to use Edison to develop algorithms and technology partners will be able to bring data processing advancements to Edison applications and smart devices.
A full 90 percent of healthcare data comes from imaging technology, yet 97 percent goes unanalyzed or unused, GE Healthcare said.
Edison is designed to harness that data to improve scan consistency, detect and prioritize cases, and extend the lifecycle of devices.
“Edison powers pioneering but practical technologies that improve the workflows and devices of today and target the greatest pain points in the system,” said GE Healthcare Senior Vice President of Edison Portfolio Strategy Keith Bigelow.
“Thanks to advances in computing power and data science, we have entered a new era of medicine,” said Michael Blum, associate vice chancellor for informatics at the University of California (UC), San Diego. “We now have a tremendous opportunity to improve the quality and efficiency of care, and prevention and prediction for an individual are finally going to be possible.”
NEW APPS, SMART DEVICES BUILT ON EDISON PLATFORM
GE Healthcare also announced several healthcare apps and smart devices built on the Edison platform:
- AIRx — This AI-based automated workflow tool is used for MRI brain scanning to improve consistency and productivity. AIRx uses deep learning and anatomy recognition to learn from a database of more than 36,000 brain images to reduce the number of manual steps for radiologists during brain scans. It is designed to produce images that have less variability between technologists and between scans to help reduce the need for repeat scanning due to incorrect slice placement.
- CT Smart Subscription — This subscription service provides continuous access to the latest CT software. Apps can be selected based on a hospital or health system’s needs, with options ranging from intracranial hemorrhage and stroke detection to routine dose reduction and optimization to cardiac function assessment.
- Automated Lesion Segmentation on LOGIQ E10 — This helps eliminate the need for the user to manually measure lesions identified by ultrasound by segmenting a breast, thyroid, or liver lesion and automatically providing a trace of the lesion and corresponding area.
- Critical Care Suite on Optima XR240amx — This device is designed to identify cases of pneumothorax to enable prioritization of image review. It uses a suite of AI algorithms designed to identify pneumothorax in chest X-rays with high accuracy. The algorithms are hosted on the mobile X-ray system designed to share the output through an onscreen notification.
“There’s a lot of hidden meaning in the deep data, but it takes a significant sophistication to extract the value,” said Rachael Callcut, a partner in the development of Critical Care Suite as well as an associate professor of surgery at UC San Francisco, a surgeon at UCSF Health, and director of data science for the Center for Digital Health Innovation. “AI gives us an opportunity to see patterns that we don’t see and change the way we care for patients, which can ultimately improve outcomes,” Callcut added.
Callcut partnered with radiology colleagues and GE Healthcare to create an initial algorithm that can immediately detect pneumothorax, a condition which can be deadly if not diagnosed quickly and accurately. Pneumothorax affects nearly 74,000 US patients each year.
“The concept behind this was to develop an algorithm using artificial intelligence (AI) that could actually learn how to find pneumothorax on a chest X-Ray,” Callcut said. “And by alerting the clinicians immediately, it would allow us to actually speed up the timely diagnosis of a potentially life-threatening condition.”
GE Healthcare said it intends to open the Edison platform and over 100 services to more developers and partners, which could accelerate the development and adoption of AI technology in healthcare.