How an AI-powered messaging tool puts patient safety to the top of the inbox

As patient portals and secure messaging have become more popular, clinicians are spending more time managing their inboxes, with the number of messages sent rising sharply since the pandemic. To better manage this volume, the Southern California Permanente Medical Group (SCPMG) custom built an AI-powered tool that is not only helping clinicians more efficiently handle incoming messages, but also enabling faster review of messages involving high-acuity cases, like a patient experiencing chest pain.

Speaking with Becker’s Health IT, Khang Nguyen, MD, chief medical officer for Care Navigation at The Permanente Federation and chief healthcare information officer at SCPMG, shared more about this health care innovation driven by a team of Permanente physicians and other experts. The Smart Messaging Tool uses natural language processing to categorize messages by topic and flag high-acuity cases as top priorities, enhancing the patient experience by addressing safety concerns associated with online interactions.

“I’ll give you a good example: A patient who says, ‘I’m having weakness and I can’t move my arm.’ They may not know that they have a very short window to get to the ER,” Dr. Nguyen told Becker’s. “So, this system pulls that to the top. We get to them quick.”

Related AI story: Transforming the patient navigation experience starts at the digital front door

A study published in JAMA Network Open showed that the Smart Messaging Tool achieved 81% classification accuracy compared to 44% for the legacy system.

The findings also showed that the tool reduced the time it took clinicians to receive and read high-acuity messages by 17 hours — from 22 hours to just 5.

“If we’re looking for financial ROI, I would actually say we haven’t found one,” said Dr. Nguyen. “But the long-term ROI is basically patient quality of life, salvaging that clinical situation, saving someone from having a major stroke.”

Dr. Nguyen has also emphasized that the interoperability of new AI tools with existing technologies is key to support their long-term success. For example, integrating the Smart Messaging Tool with the existing Centralized Messaging Hub platform and with an automated routing solution now in development could produce a scalable, centralized communication network to manage a broader range of messages, freeing personnel to focus on other work.

Read the full article in Becker’s Health IT here.