WellSpan Health uses AI for mass data migration between multiple EHRs.

To harmonize information across disparate EHRs and build trust in post-acquisition system technology, the healthcare system aligned human process improvement and advanced technology combining DrFirst’s AI assistance to streamline the data migration, manual entry and user adoption.


Artificial intelligence has played a significant role in helping WellSpan Health ease the transition between the different electronic health record systems its facilities were using, bringing efficiencies and improving patient and clinician experiences.

In a presentation for the KLAS HDM roomWellSpan Health’s Chief Medical Information Officer, Robert M. Lackey, MD, and Donald “Chip” Gerhart, System Pharmacy Clinical Informatics Manager, discussed how AI helped ensure a smooth transition to the EHR for clinicians.

Post-merger perceptions

After a big merger, WellSpan Health had many facilities, five EHRs and a patient satisfaction issue, Lackey and Gerhart said. Patients disliked having to repeat information across different settings, and issues such as non-standardized medication histories posed challenges for providers. WellSpan needed a single source of information that all stakeholders could trust to be up to date.

WellSpan executives chose to move to a single EHR, but they didn’t want to start from scratch and create a huge burden on clinicians. The IS team has begun a massive data migration, determined to provide vendors with clean data.

“We actually did our migrations and go-lives in three phases,” Lackey said. “The first two, we did without the benefit of any AI. We used humans, and I tried to help with snippets of CCDs that were presented for humans to interact with. That helped, but it took a lot of human investment to reconcile this information in the new chart.

However, when they saw an opportunity to harness AI in their process, WellSpan became an innovative case study, using support from Dr. Premiera technology solutions and consulting services provider based in Rockville, Maryland.

“We were working with a vendor that provided us with our medication history data, and they had a really great engine that was already optimizing medication history. We wondered if we could use this same optimization technology for our CCD extracts of our drugs,” Lackey said. “They ended up doing it for us, and it worked out really, really well.”

Overcoming AI Skepticism

WellSpan executives understood that many clinicians were skeptical of AI and would need some human reassurance.

“We had to do our best to deliver as perfect a process and product as possible, knowing that if we delivered something full of errors, our users would lose trust in it, and that can be catastrophic for a project,” says Lackey. “In this project, we did a whole series of validations to make sure that we could catch some errors that the process was not able to catch initially. And we fixed those to make sure what was presented to our users was as solid as reasonably possible.

In the end, 270,000 patent files, including 5.5 million drug files, were processed by the AI ​​engine. “Nearly 90% of the work was optimized, and it saved up to 13 clicks per drug with all the drop-down menus we didn’t have to worry about,” Lackey said.

As a result, WellSpan reduced five to seven minutes of work per chart, achieved a savings of 60% over what was budgeted for the project, and kept their project online during the COVID pandemic. “Our care teams had much better data on day one — the whole process worked like a charm,” Lackey said.

Having patient records populated with clean data from go-live has led to a better clinician experience and high clinician confidence in the new system. “Being able to instill that confidence early on was helpful,” Gerhart said. “It certainly spawned skills and a more successful transition, as clinicians became an integral part of the organization from the start. I think we had much better buy-in from clinicians, who knew they could be successful with the new solution.

This experience reinforced WellSpan’s belief in the ability of AI to improve the lives of clinicians. It also validated the instinct of leaders to chase innovation.

“We could have easily agreed that we were going to do our data migration the same way we always had. I think that’s one of the things I would say to other organizations: never be satisfied,” Gerhart said. “Look at the relationships you have with your suppliers, value them, and look for opportunities, when you have them, to leverage something your suppliers are already doing for you in a new and different way.”

Watch the WellSpan Health Session Video or explore all HDM KLASroom on demand video series.


Sean N. Ayres