Oakland, Calif.-based Kaiser Permanente tested an artificial intelligence-powered system and found that it resolved one-third of patient messages, helping clear clinicians' inboxes.
Kaiser's desktop team conducted a study that used an AI-powered system to analyze 4.7 million patient messages sent to Kaiser Permanente Northern California's adult and family medicine, according to an April 4 news release from Kaiser. This system categorizes messages by topic and forwards them for regional team management.
The system resulted in 31.9% of messages being resolved without reaching a physician's inbox.
"The system was effective in identifying about 1.5 million messages that would have otherwise gone on to physician inboxes," Vincent Liu, MD, research scientist with the Kaiser Permanente Division of Research and study lead author, said in the release.
Kaiser also said the system could be helpful in identifying health trends.
The study was published April 4 in JAMA Network Open.