Epic’s Post

View organization page for Epic, graphic

726,522 followers

Our friends at Stanford Health Care released a study finding that AI-generated drafts for responses to patient messages led to a reduction in clinicians’ feelings of clerical burden and burnout.   “This is an early demonstration of how integrating generative AI into health care workflows with a ‘human in the loop’ can assist providers, said Michael Pfeffer, MD, CIO at Stanford. “We’re always trying to find ways to have the electronic health record work with clinicians through automation. Already, clinicians are noting a reduction in cognitive burden—and the AI is only going to improve from here.”   Importantly, Stanford’s study reflected the experiences of the kind of multi-role care team that manages patient messages in daily practice—including physicians, nurses, advanced practice clinicians, and pharmacists. All drafts are reviewed and edited as necessary before they’re sent to patients.    “We know that in-basket messaging and responding to patients is a team sport,” said Patricia Garcia, MD, clinical associate professor of medicine and the associate CMIO at Stanford. “I think what makes this study particularly impactful is that it’s capturing what it’s like to deploy this tool in a way that would be practical and reflective of a real care environment.”   Congrats, folks!   Read more: https://lnkd.in/eJZYicyU #healthcare #healthIT #generativeAI

AI assists clinicians in responding to patient messages at Stanford Medicine

AI assists clinicians in responding to patient messages at Stanford Medicine

med.stanford.edu

Lauren Quiniff LMSW

Supporting social workers and their patients in the goal of improved mental and physical health.

3mo

Really interesting idea as I know that working on everything in your in basket can take a lot of time and lead to additional stress for providers. Glad to see that a human still reviews it before sending.

Dr. Panchali Ganguly M.D.

Physician Leader @ Carbon Health | Urgent Care, Care Management

3mo

Yes AI will definitely reduce the clerical burden n medicolegal liabilities by taking care of routine protocols etc but never replace all the higher cognitive skill sets required to manage a patient .

Bradd Busick

Senior Vice President, Chief Information Officer: I build amazing teams, emphasize the importance of culture and deliver transformational outcomes. 🚀

3mo

Remove pebbles in shoes for our providers! Love it!

Love this, great way to use AI.

Amber Webb, MSN-HI, RN, CRNI

Dynamic Nurse Leader inspired by teams to: Motivate, Innovate, and Evolve Nursing Practice through both human experience and Informatics.

3mo

This would be extremely helpful in building algorithms for advice lines as well- it could reduce the burden on urgent cares, telephone time and additional communications that are required when patients call. Building in triggers for high alerts and funneling calls through that require critical thinking could really streamline advice lines and help those answering to practice at the tops of their licensing.

Like
Reply
Yogesh S.

Business and Tech Strategy Leader I Physician | Digital Transformation | PMP | Lean Six Sigma| IIT Bombay Alumnus

3mo

Human in the loop approach could reduce cognitive burden. It's interesting to see how it translates into time and cost savings.

Like
Reply
Erika Sidney MD

I Help Healthcare Professionals Rediscover Their True Selves

3mo

I am very interested in how AI can help our administrative burden. This is interesting.

Teddy T Mpoyi

Cloud & DevOps Engineer | 2XAWS Certified | Network Engineering | ⎈ Kubernetes (KCNA)| Certified in Cybersecurity by ISC2 | Currently Studying For The CCNA Exam |

3mo

A pretty good use case for utilizing both AI and human beings to streamline processes!

Nate Danner

Director @ TytoCare | Revolutionizing Telehealth Exams

3mo

Awesome work Stanford Health Care! Michael Pfeffer I remember talking about this at ViVE in 2022, and sounds like you found a solution!

Like
Reply

I'm very passionate about this! Thanks for sharing.

Like
Reply
See more comments

To view or add a comment, sign in

Explore topics