NM Turns to AI to Revolutionize Healthcare

Northwestern Medicine is moving beyond traditional specialized software tools, opting instead to harness artificial intelligence (AI) for integrating its data assets and sources in an effort to boost caregiver effectiveness and expedite healthcare delivery.

The medical staff recognized the “transformative potential of AI in healthcare” and evolved their Generative AI (GenAI) practice to implement solutions “capable of potentially saving lives by identifying critical conditions swiftly and streamlining tasks such as medical imaging reviews,” the company said in a case study performed by Dell Technologies.

Northwestern Medicine created its GenAI solution in collaboration with the AI engineers and thought leaders at the Dell Technologies AI Innovation Lab in Round Rock, Texas.

“GenAI and AI offer a tremendous opportunity to help us take better care of our patients and give time back to care providers,” said Dr. Mozziyar Etemadi, clinical director of advanced technologies at Northwestern Medicine.

“Cloud technology can quickly get costly, and it’s also more rigid in terms of how you need to access and provision resources. We find it’s less expensive and more convenient to deploy GenAI solutions directly on our on-premises infrastructure. Partnering with Dell Technologies makes that even easier,” Etemadi said.

By integrating Dell’s AI infrastructure with NVIDIA’s graphics processing units (GPUs), Northwestern Medicine enabled the secure development and deployment of GenAI at scale. The solution was deployed on premises, fostering close collaboration between AI researchers and medical practitioners.

According to Etemadi, this combination of NVIDIA GPUs and Dell PowerEdge servers was pivotal in addressing critical healthcare challenges, marking it as an “ideal synergy for advancing patient care.”

“Combining the power of NVIDIA GPUs and the flexibility of Dell PowerEdge servers allows us to solve real problems affecting real patients,” Etemadi said.

The first GenAI tool built on this solution – the Automated Radiology Interpretation and Evaluation System (ARIES) – quickly scans radiology images, highlighting diagnostic findings and anomalies that would normally take hours for radiologists to review. This speeds up how radiologists can interpret images and address patients’ health concerns.

“With many GenAI beta users, we’re seeing an up to 40 percent efficiency gain. When one of our more junior radiologists first worked with ARIES, it took his productivity level to that of someone with 15 or 20 years more experience — without any drop-off in quality,” said Dr. Samir Abboud, chief of emergency radiology at Northwestern Medicine.

Northwestern Medicine has rolled out ARIES to its 11 hospitals and broadened the reach of GenAI to nursing and other caregiver roles. And the project is continuing to drive collaborative innovation.

“We’re democratizing access to the very tools that create AI … I want every hospital system worldwide to have its own AI factory,” said Etemadi. “Powered by GenAI and multimodal large language models, healthcare will soon be able to predict disease states months to years before they happen.”