Rad AI Expands Partnership With Yale New Haven Health For Radiology AI Deployment
Advertisement
The company’s generative AI tools are designed to streamline radiology workflows, including physician dictation and follow-up care management, by automating parts of the reporting process and reducing dictation time.
California-based Rad AI is expanding its partnership with Yale New Haven Health System to deploy its generative AI radiology reporting technology across the health system’s multi-network imaging infrastructure and jointly develop new clinical tools.
The expansion includes the rollout of Rad AI’s reporting solutions across Yale New Haven Health’s imaging network, which spans more than 16 outpatient imaging centers and five hospital campuses. The company’s generative AI tools are designed to streamline radiology workflows, including physician dictation and follow-up care management, by automating parts of the reporting process and reducing dictation time.
Rad AI’s Omni Impressions tool generates AI-assisted report impressions after a radiologist inputs raw findings. Dr. Elizabeth Bergey, radiologist and chief clinical officer at Rad AI, said the system has evolved significantly through the partnership.
"Yale was our first big academic site," Dr. Elizabeth Bergey, radiologist and chief clinical officer at Rad AI, told MobiHealthNews.
"It's been a partnership where we've grown to trust each other and work with each other very closely to help develop a big part of what Rad AI provides now," Bergey said.
At Yale New Haven Health, imaging informatics leadership highlighted Omni Impressions as a key productivity tool for radiologists. Dr. Melissa Davis, vice chair for imaging informatics, radiology and biomedical imaging and associate professor of radiology and biomedical imaging, said the tool has had a measurable workflow impact.
"Rad AI is at the forefront, especially with its Omni Impressions tool," Davis said. "This is the one tool that if you ask a radiologist broadly, 'What's made my day better?' An impression generator is what it is, and Rad AI was at the forefront of that market."
Beyond deployment, Yale New Haven Health System will also work with Rad AI to co-develop and clinically test new radiology-focused technologies across its network. The organizations said these tools will be designed based on operational needs identified within the health system.
"There are a lot of questions that I think they can help us solve on the ground, and so I'm not really thinking about it from a product standpoint at this point," Davis said.
"Yes, we needed the reporter, like, that was the product for us, but I hope that we can generate an actual partnership that starts to align with our needs and with their roadmap going forward."
Davis also pointed to broader operational challenges, including data management, staffing optimization, and productivity tracking, as areas where future AI-driven tools could play a role, though no specific collaboration areas have been finalized.
"We have a lot of information, and we don't know how to surface the questions that we actually need answered," Davis said.
Rad AI said its approach focuses on building customized models for radiology-specific tasks, with ongoing development shaped by clinical feedback from partner health systems.
Stay tuned for more such updates on Digital Health News
