A recent study conducted by the University of California San Diego School of Medicine has found that the use of artificial intelligence (AI) has improved communication between physicians and patients. UC San Diego Health is one of the first health systems in the United States to test the use of generative artificial intelligence (GenAI) to draft responses to patient messages within the Epic Systems electronic health record. While the study revealed that AI-generated responses did not decrease physician response time, they did help alleviate cognitive burden by initiating an empathetic dialogue.The research, which was published in the online edition of the Journal of the American Medical Association’s Network Open on April 15, 2024, is the initial randomized prospective assessment of AI-generated physician communication. According to Christopher Longhurst, MD, the senior author of the study and the executive director of the Joan and Irwin Jacobs Center for Health Innovation, as well as the chief medical officer and chief digital officer at UC San Diego, the use of AI to assist with health system challenges, such as the growing number of patient messages that are contributing to physician burnout, is of great interest.Ego Health. “The evidence that the messages are longer suggests that they are of higher quality, and the data clearly shows that physicians appreciated the assistance, which decreased cognitive burden.”
This study on quality improvement assesses patient-physician communication and indicates that incorporating generative AI into digital healthcare interactions could potentially have a positive impact on patient care by enhancing communication quality, efficiency, and engagement. Furthermore, by relieving some of the physician’s workload, the aim is for generative AI to help lower burnout by enabling doctors to concentrate on more complex aspects of patient care.The study lead author, Ming Tai-Seale, PhD, MPH, who is a professor of family medicine at UC San Diego School of Medicine, stated that this research demonstrates the potential for generative AI to be a collaborative tool. He also mentioned that physicians often receive around 200 messages per week and that AI could assist in overcoming “writer’s block” by providing them with a draft message infused with empathy, allowing them to respond thoughtfully to patients. The COVID-19 pandemic has led to a significant increase in digital communication between patients and doctors, and there is a continuing high demand for such interactions. Tools like MyUCSDChart, used by UC San Diego Health, have made it easy for patients to directly email their doctors.have been overwhelmed with patient messages are finding relief through this AI-generated response system, allowing them to focus on more critical tasks while still providing timely and accurate information to patients. The program aims to streamline communication, reduce physician burnout, and improve patient satisfaction by ensuring that messages are addressed in a timely manner. The use of AI in this capacity demonstrates the potential for technology to alleviate some of the burdens facing healthcare professionals in today’s fast-paced and demanding environment.A recent study has discovered that generative AI is useful for composing longer, more empathetic responses that are well-received and understood by patients, especially when doctors are short on time. According to the co-author of the study, Marlene Millen, MD, who serves as the chief medical information officer for ambulatory care at UC San Diego Health, AI can assist in crafting compassionate messages at the end of a busy day without experiencing fatigue. Although the study revealed that AI messaging did not necessarily save doctors time, it may still play a role in preventing burnout by offering a thorough response to patient inquiries.The study’s results indicate the potential for a shift in health care communication using AI. Further evaluation is required to determine how beneficial patients find the increased empathy and response length. UC San Diego Health and the Jacobs Center for Health Innovation have been conducting extensive testing on GenAI models since May 2023. These projects aim to explore the safe, effective, and innovative use of GenAI in health care. The study’s co-authors are Sally L. Baxter, Florin Vaida, Amanda Walker, Amy M. Sitapati, Chad Osborne, Joseph Diaz, and Ni.Authors from UC San Diego and Stanford, including Ming Tai-Seale, Sally L. Baxter, Florin Vaida, Amanda Walker, Amy M. Sitapati, Chad Osborne, Joseph Diaz, Nimit Desai, Sophie Webb, Gregory Polston, Teresa Helsten, Erin Gross, Jessica Thackaberry, Ammar Mandvi, Dustin Lillie, Steve Li, Geneen Gin, Suraj Achar, Heather Hofflick, and Marlene Millen, have been referenced in the journal.ristopher A. Longhurst wrote an article about AI-generated draft replies being integrated into health records and physicians’ electronic communication. The article was published in JAMA Network Open in 2024. The DOI for the article is 10.1001/jamanetworkopen.2024.6565.