What does a platform look like in healthcare? Today we hear from the CEO of Mayo Clinic on what it looks like at Mayo Clinic.
Today in health, it. Transforming healthcare through platforms. My name is bill Russell. I'm a former CIO for a 16 hospital system. And creator of this week, health has set of channels dedicated to keeping health it staff current and engaged. We want to thank our show sponsors who are investing in developing the next generation of health
Gordian dynamics, Quill health tau site nuance. Canon medical and current health, check them out at this Dot com slash today. All right. Great article. It's actually out on LinkedIn, transforming healthcare through platforms. G and Rico for Rugea. CEO of Mayo clinic talks about , well worth the read. If you get a chance, just go out there and read it. I'll give you some of the, , highlights that I'm going to talk about. So what, while the pandemic highlighted many problems with our healthcare system, many of these issues are long-standing and indeed go back several decades.
There's a long standing need. For more cures and innovation while also decreasing healthcare inequity in variability of care offered across the United States and across the world. We also need to drive out waste and we need to focus on paying for value. The enduring nature of these challenges and the inability of legacy approaches from across the healthcare sector to solve them, showed the need for an entirely new approach. This is why three years ago, Mayo clinic committed to leading.
A platform transformation of healthcare. All right. What are they talking about from pipeline to platform? Our current healthcare model functions as a pipeline, which is linear, highly transactional and inflexible. The failings of this model were clear during the pandemic where collaboration was limited and stress to individual notes led to points of failure, this in turn hampered. And in some cases paralyzed the entire system.
, platform model of healthcare and ecosystem is fundamentally different. A platform is built around secure collaborative resources, such as a powerful analytic engine and an open ecosystem of trusted collaboration. And as highly dynamic, self-learning inherently accessible and scalable. This approach brings together providers, medical device companies, health tech, startups, patients, and payers among others to design integrated an end to end solutions that are supported by longitudinal clinical data and AI algorithms. The platform is purposely collaborative and fuels innovation and access instead of limiting it.
Okay. But let's be real clear. It does this with security and privacy in mind. And we'll go on and talk about that. Transformation at the Mayo clinic.
To create Mayo clinic platform. We knew we needed a unique architecture designed specifically for the challenge of healthcare for any such platform. To be adopted at scale. There's a need to reconcile two seemingly contradictory responsibilities, safeguarding, patient data, privacy, and security. While enabling innovation through broad access to results in AI models. There you go.
A digital platform in healthcare needs to be highly trustworthy and scalable. At the same time to do this, we developed a platform based on a federated data learning model and created a glass wall so that partners can extract insights, develop and train AI algorithms. And access digital tools without any underlining data being shared that.
Is the magic right there. Now you're going to hear a lot of people. Hey, we're bringing together this, we're building a platform where people can gain insights and whatnot, and just ask yourself, is the data leaving your house system? Is it going somewhere else? Do you now have another point of attack to get to your health systems data?
Are you in control of that? , area where that data is. Imagine if you could create something, this whole glass wall concept of see-through can't get through. Right. You could see through, you could see the results, you could see the things on the other side, but you can't get through it. That is one
, more innovative things that this platform has, and I'll go into my soul and I'll go into the difference between this platform and your platforms. When you talk about platform. And we'll come back This architecture places priority on the patients and the rights to data privacy. This is critical requirement.
To preserve the trust. In the platform enabled healthcare system while. Enabling innovation at scale. All right, so everything's powered by data. They talk about the amount of data. They have 5.5 petabytes of data, 10 million de-identified patient records, 644 million clinical notes, 335 million medication records, 9 billion pathology reports. You get
There's a lot of data. In this. , in the Mayo clinic platform. So there's four domains that they focus on with an architecture and data in place. They're pursuing four domains and here Gathered the data make it comprehensible and safely accessible. So gather, accepts data and diagnostic signals from various sources.
Such as wearables, EHR has clinical systems, diagnostics devices. And integrates harmonizes and stores the data. So it seamlessly. , can be used for advanced innovation solutions. All right. So I think it's important here that the platform isn't any single system. And it's a, , it's a platform that receives and accepts data from a lot of disparate systems and then make sense of that.
, data or it makes it so that you can make sense of that data, right? The next is discover, discover enables Mayo clinic researchers and our trusted partners to develop new digital and algorithmic tools. Based on one of the largest longitudinal clinical datasets in the world, right? So they're able to discover new insights from AI and machine learning tools and reach into that dataset. Important to note the data's not coming out, but the results of the algorithms are coming
Validate. Validate is one of the first products. In the industry that provides a bias, specificity and sensitivity report for AI models, creating a nutrition label for AI insurers. It is clear from an objective analytical perspective, how an AI algorithm performs under different constraints, including racial, gender, and socioeconomic demographics. As beautiful, actually, it's just beautiful. , Deliver these tools into an existing workflow is last. So deliver as , is committed to decreasing the clerical burden on providers by making new and existing digital tools more efficient.
And connected and seamlessly actionable. And so that's a, that's a layout of the Mayo clinic platform.
So, what does my soul want on this? My soul. What on this is, this is beautiful. I've said that. A number of times, I love how they're doing this one is they don't rely on . The EHR is the platform itself. Now, if you're a small health system, The EHR might be your platform. I might be, as far as you can go. Maybe you're not an academic medical center. You're not doing that kind of discovery and validation and those kinds of things.
And all you can do is buy bits and pieces and bring them together by all means. That's your platform. That's a good approach. Find the right platform. And the right platform is one that is going to accept data from a lot of disparate sources. It's going to make sense of that data. It's going to enable you to get insights from that data and to share those insights in the workflow.
, as they're happening. So that's why a lot of people consider and utilize their EHR. As a platform consider the nature of that platform. Is it a closed platform on open platform? Are you able to apply tools of your own making to that platform and do the things you want to do or every time you do it, does it cost you money? Are there gates to go through? Are there APIs that are unaccessible to you and those kinds of things?
Is there a walled garden around the things that you're trying to gain access to. , and now they might have a walled garden around some of the things and not all of the things. You have to determine which ones are important to you, which ones aren't. But if you have the wherewithal. To do what Mayo clinic is doing. I would highly suggest you do it. And that is an agnostic platform that brings the data. And that gives accessibility to AI and machine learning models, but protects the privacy of the patient data.
, and, , it gives you the ability to, , provide visibility. Into the algorithms that are accessing the data itself. So . This is a really interesting model that I think a lot of academic medical centers should be following. If not, , partnering with them on the model itself, because that's one of the natures of a platform, right. It invites collaborators into
To work on it to make it better. And the more you have this network effect, right? The more people that connect to the platform, the more powerful it becomes. One of the things I, again, I'm just going to cue it back to be careful of platforms that need your data. And so this was one of the problems we had with Watson.
Watson was a platform. It was AI could do all these things. And they IBM kept coming in and saying, Hey, we need you to feed us more data. Hey, send us more data. Hey, give us your data. And we were constantly sending data outside of our system to another source. Now it was for good purpose. It had all those things, but that's not really what we want in a platform. We do not want to expand the attack surface on our health system and our patient data. We shouldn't have to do that in the process of gaining access to these advanced tools. So be very careful how you build out these platforms. Look at the architecture is so critical. Look at the architecture, , understand the use cases, understand how you're going to deliver this information back into the clinical workflow in a way that is actionable.
So I just want to highlight this story. What a fantastic. , right up by the CEO and you got to love a CEO that can talk at this level. About technology and about the platform. So that's all for today. If you know someone that might benefit from our channel, please forward them a note. They can subscribe on our website this week, health.com or wherever you listen to podcasts, apple, Google, overcast, Spotify, Stitcher, you get the picture. We are everywhere.
We want to thank our channel sponsors who are investing in our mission to develop the next generation of health leaders. Gordian dynamics, Quill health tau site nuance, Canon medical, and 📍 current health. Check them out at this week. health.com/today. Thanks for listening. That's all for now.