Ochsner to Pilot Epic EHR Integration for Generative AI Patient Messaging

Ochsner Health is launching an Epic EHR integration that uses generative AI to draft messages to patients.

A small group of Ochsner clinicians will test the new Epic feature, which aims to speed up response time to patients and allow doctors to spend more time with patients. The system drafts responses to routine patient requests, which are then reviewed and edited by clinicians.

"Ochsner has long been a leader in using digital tools to improve the patient experience," Louis Jeansonne, MD, Ochsner's chief medical information officer, said in a press release."Now we are looking at how technology can simplify workflows for our clinical staff, which should significantly reduce the hours they are spending away from patients."

Ochsner is part of an early adopter group to test the tool leveraging Microsoft's Azure OpenAI Service, which integrates with Epic's EHR. About 100 Ochsner clinicians across the system (of 46 hospitals and 370 centers) will participate in the initial phase of the pilot, testing simple messages unrelated to diagnoses or clinical judgments.

A clinician must review the message's accuracy and make any needed adjustments before the system can send a message to a patient.  

Officials noted that Ochsner will educate clinicians on the importance of remaining engaged with patient communication and relying on the drafts only for support.

"The AI will generate a draft for the clinician to review and send," said Amy Trainor, Ochsner's chief application officer. "It's meant to help clinicians respond more quickly to patient messages so patients can get answers to their questions sooner. And it will reduce time our clinicians are spending on computers so that they can spend more time doing what they do best—direct patient care."

Trainor noted that there are three phases of the pilot through fall 2023. Each phase will gather patient feedback to enhance the system.

"At Ochsner, we are constantly looking for ways to improve our patient and provider experience, and we believe this pilot will show that AI can help relieve the messaging burden on our clinicians," she said.