The National Institutes of Health's electronic health record, the Clinical Research Information System, was first purpose-built 20 years ago for the nation's largest research hospital.

It will be soon replaced, said Jon McKeeby, chief information officer at NIH Clinical Center in Bethesda, Maryland.

WHY IT MATTERS

According to Federal News Network, during a panel session at the AFCEA Bethesda Health IT Summit last week, McKeeby told attendees that 40 of 120 IT employees have reached retirement age.

If and when they retire, they'll take their institutional knowledge of the legacy EHR system devoted to clinical research, McKeeby said in the EHR modernization news story.

"It’s made it very complex and very dependent on specific people, specific skills, so it’s very difficult to maintain."

He said the NIH is working with the Mitre Corporation on the requirements and the performance work statement, and so far it has amassed more than 1,000 requirements for a new EHR that could hasten the agency's use of artificial intelligence.

A new EHR should also help NIH accelerate the implementation of AI to make sense of unstructured data and summarize it to support clinical decision-making, he said, noting that regulations require that data models are continuously monitored, said McKeeby. 

"Now we have all the tools to make it so we can be more visual, interact with it, but also have it create summaries, and also predictive models to help us in healthcare." 

THE LARGER TREND

Healthcare is looking to AI innovations that can ease administrative burdens and fundamentally change the clinician experience in the EHR, according to Paul Brient, chief product officer of athenahealth.

"As swiftly moving AI technologies hold vast potential to improve healthcare delivery and outcomes, how we ensure their safe use in clinical care might just be the issue of the year for 2023, if not the decade," Brient told Healthcare IT News in December.

With appropriate guardrails in place for safety, transparency and ethics, Peter Shen, head of the digital and automation business at Siemens Healthineers, said that the creation of algorithms in partnership with clinical partners to validate data before training improves their "ground truth" and therefore, elevates their trustworthiness to make more personalized clinical decisions.

ON THE RECORD

"It’s going to be open to every vendor, even the existing vendor, but we need to move to a more integrated model, so that’s the goal," McKeeby said in the FNN story.

Andrea Fox is senior editor of Healthcare IT News.
Email: afox@himss.org
Healthcare IT News is a HIMSS Media publication.