📍 Today in health, it epic releases. Open source AI validation tool for health systems. Today we discuss. My name is bill Russell. I'm a former CIO for a 16 hospital system and create, or this week health. Instead of channels and events dedicated to transform health care. One connection at a time we want to thank our show sponsors who are investing in developing the next generation of health leaders.

Notable service now enterprise health parlance, certify health. And Panda health, check them out at this week. Health. Dot com slash today. All right. Hey, let's this new story by the way. And any new story we covered, you can find on this week health.com/news. You can also subscribe to get that delivered to your inbox every morning. And finally share this podcast with a friend or colleague you said is foundation. For weekly discussions on the topics that are relevant to you in the industry, they can subscribe wherever you listen to podcasts.

This is a form of mentoring. All right. Let's let's take a look at what's going on here. So I'm funding this story from fierce healthcare, Heather Landy epic launched an open source tool on Wednesday to enable healthcare organizations to test and monitor artificial intelligence models. The AI validation software suite is free and available to the public on GitHub Corey Miller, vice president of research and development at epic. Told fierce healthcare health systems can download the code to their electronic health record systems.

He said, health systems. I can use the tool to validate AI models to integrate, or that integrate with HR systems, including models developed by epic. As well as other other models developed by other organizations as AI best practices are developed, the open source framework will enable organizations to bring in those standards and practices alongside the AI validation capabilities.

Epic executives said. Miller said it marks Epic's first open source tool. That is one of the things I was going to highlight here. This is a departure in a welcome departure that we now have this code out there. It was really necessary. It was really needed. And it'll be interesting to see. Where this can be utilized.

I would assume it can be used with other EHR. We'll keep going here by publishing on GitHub. It's truly available to everyone. It's not behind any locking key that we control. We're excited to dive into this world. It's fitting that a tool intended to ensure the, that equity of health AI is going to be publicly available and open. Two contributors from around the globe and it is exciting and interesting. In early April EHR giant announced plans to release AI validation software, which they have.

They are a software suite that epic calls, an AI trust and assurance software suite automates data collection, and mapping to provide near real-time metrics and analysis on AI models. Seth Hayne, epic senior vice president. Of R D said back in April. Wow. Didn't read that correctly. You can tell it was a long weekend.

I'm having trouble reading my text in front of me. The automation creates consistency and eliminates the need for healthcare organizations. Data scientists to do their own data mapping the most time consuming aspect of validation. It goes on to talk about the healthy AI partnership, a collaboration of organizations, including duke health, Mayo clinic, Kaiser Permanente crease

You

disseminates, best practices for AI product using the healthcare two sites, duke and university of Wisconsin health. We'll use epics, AI trust and assurance software suite. To conduct a study to. To generate evidence around use of the tools to locally test and monitor AI models.

And so a lot of exciting things in this article, you can check it out. I did not cover the whole article. Let me give you my, so what on this, my somewhat on this is a open source tool. Fantastic. Good on you. Epic. Appreciate you heading in this direction. The second thing is love the health systems that are putting this to use.

What are they going to be putting it to use for it's that they could look at, provide some visibility into the system and the model. Try to ensure fairness across different patient demographics. One of the things that we've talked about on the show, I remember talking with Stanford, Mike Pfeffer. About this he was talking about the value of their data. He said, because these national models aren't necessarily relevant. To their populations.

And this is the kind of tool that's going to be able to help you to evaluate is this tool. Giving you the right results for your local population. Really like the direction here, if if you are. Looking at equity in your AI tools. If you have an AI governance. Group set up, which I recommended a while back.

With regard to this, I think that's one of the biggest steps going here is having a group of people, a named group of people within your health system. That is looking at all of these things as they emerge. They're looking at. The use cases they're looking at what's required from a literacy and adoption standpoint.

They're looking at policy and governance. They're looking at use cases and evaluating those use cases around AI. And so I think it's important. To have that named group that is looking at all those various things. And then obviously also looking at equity. And this tool is one of those that group would look at and say, Hey look. This gives us ideas for how we are going to measure how we are going to report out on the equity of our models. And they can begin to work with it and others. To to validate the model and test it out and see how it works and get it working in your environment. So a lot of good things here, a lot of exciting things here.

And take a look, give me a, give me some feedback. Let me know how it's working in the real world. Love to hear from you on that. All right. That's all for today. Don't forget to share this podcast with a friend or colleague. And use it as foundation for metrics. See how hard it is to come back from a from a holiday week, but it was a great holiday week and need it.

So I will get back into the flow of things. It's all good. We want to thank our channel sponsors who are investing in our mission to develop the next generation of health leaders. Notable service now, enterprise health parlance, certify health and 📍 Panda health. Check them out at this week. health.com. Slash today. Thanks for listening.

That's all for now.