This Week Health

Don't forget to subscribe!

February 7: Today on Town Hall, This Week Health’s very own Bill Russell speaks with Billy Oglesby, Dean of the Jefferson College of Population Health about synthetic data and why it is preferred over de-identified data. What data are researchers looking for to do their jobs effectively? What are the challenges of getting data together from outside the EMR for a more whole person profile? What are some of the approaches and methods for protecting patient data?

Healthcare needs innovative ways to address staffing shortages from clinical to IT employees. Are you curious about how technology can help support your Healthcare staff? Join us on our March 9 webinar, “Leaders Series: The Changing Nature of Work,” to explore how Health IT can be used to supplement Healthcare professionals.

Subscribe: This Week Health

Twitter: This Week Health

LinkedIn: Week Health

Donate: Alex’s Lemonade Stand: Foundation for Childhood Cancer


This transcription is provided by artificial intelligence. We believe in technology but understand that even the smartest robots can sometimes get speech recognition wrong.

Today on This Week Health.

It's a process that starts first with protecting patient privacy, but then after you jump that hurdle, it opens up the doors to a whole lot more powerful research.

Welcome to TownHall. A show hosted by leaders on the front lines with interviews of people making things happen in healthcare with technology. My name is Bill Russell, the creator of This Week Health, a set of channels dedicated to keeping health IT staff and engaged. For five years we've been making podcasts that amplify great thinking to propel healthcare forward. We want to thank our show partners, MEDITECH and Transcarent, for investing in our mission to develop the next generation of health leaders now onto our show.

today we are joined by Billy Osby, the Dean of the Jefferson College of Population Health. Billy, welcome to the show.

It's great to be with you. Thanks for having me.

I'm looking forward to the conversation. We're gonna talk about data and really the quest to leverage data in he.

In new, better uh, ways that deliver outcomes for the clinicians and for the patients and the researchers for that matter. So, I'm looking forward to this conversation. Let's start here. What, What data are researchers looking for to do their jobs effectively?

Well, I think, well, they're looking for a lot of things.

I think, two of the things they're looking for the most, I, I would say, is accurate and comprehensive data to really fuel a lot of the advanced analytics that are needed to help inform decisions around improving healthcare outcomes. So they're looking for data that is very specific, very comprehensive.

And certainly over the last few years, they're looking for data that live outside of the clinical medical records. So traditionally, a lot of research that was done. In health systems or in health provider organizations, was based on really solely the data that lived in the electronic medical record. But the more we know about social determinants and all the factors then influence, health and healthcare outside of the delivery system.

There's a growing need to add more data to those research data sets that live outside of the electronic medical record. And Jefferson is no.

Man, I could go in a lot of different directions because we've talked a lot on the show about the whole person profile and how important that is, because only 20% of health outcomes are really derived from the clinical side.

and then all the other factors, education and where you live. all those, all those things add up to, health. But what's the challenge of getting to that data and bringing all that data together?

Yeah. Well, I, you know, the first thing is that all lives in different places. So there are different organizations, government agencies research firms that have all of that data.

So being able to share it is difficult. And the biggest challenge with data within healthcare organizations, payers, providers. Is patient confidentiality. So it's finding a way to enable more researchers to have access to the data that they need, but making sure that we put all the privacy protections in place so that.

The data really speaks to what are the population level issues without getting into and potentially running into issues of data, breaches of information that's at the individual level.

So what are some of the approaches, some of the methods for protecting the patient data?

Yeah. Historically it's been de-identification where you take some information and maybe strip out the name, address, maybe the zip code, you know, information that at least at the individual level you could say, okay, well I know potentially who that person could be, living in a particular area.

So historically it's been. Basically de-identification, which in and of itself was certainly it's a tool but is not as effective as more sophisticated tools that actually are now using AI and machine learning. To create what's called synthetic patients to basically recreate the database of individual real life people and their health information.

But then applying AI and machine learning to basically recreate a data set that has all the same statistical properties at the group and population level. But is not attributable. You can't reverse engineer it. You can't go back and figure out who the original person is. So that's a significant leap in being able to, what used to be called anonymizing data, where really all you did was just strip out some of the identifiers.

We're now moving into synthesizing data, which is a much more powerful tool to be able to protect patient privacy.

Yeah, we, we've had several data scientists on the show who have essentially said that there's no such thing as de-identifying a patient data. they feel like you could, with enough data points, you could rebuild the original record.

But synthetic data, you're essentially creating data. Based on, so you're looking at this record and then you essentially create all sorts of new variables in, in fact, not variables. You're not changing the variables. Mm-hmm. But new factors that would make it almost impossible to re-identify that patient.

That's right. In fact, there are a lot of validity studies that have attempted to go back and try to trace looking , when researchers actually have the original information and the synthetic information. And try to go back and see if they can match it up and it hasn't been done. So it's a very powerful tool to be able to protect privacy, which then you could imagine what are the benefits that come with that, because it makes it easier to share the data with other researchers.

Makes it easier to merge data maybe with other providers in a region merging that data together so you have even a larger data set to do even more powerful analysis. It's a process that starts first with protecting patient privacy, but then after you jump that hurdle, it opens up the doors to a whole lot more powerful research.

📍   📍

If you haven't heard yet, we're doing webinars a little differently this year. We got your feedback. You wanted community generated topics, not vendor generated topics. You wanted great contributing panelists. Definitely not product focused, more focused on the challenges and the problems that we are facing in healthcare.

We are only making these available live. So we are making them more dynamic in nature and we're doing them on a fairly consistent time, as much as we possibly can. The first Thursday of every month. The next webinar is going to be on March 9th. Which technically is not the first Thursday of every month, and I apologize for that, but I'm actually on vacation that day.

So March 9th is gonna be the webinar and we're gonna continue our leadership series. We're gonna be talking about the changing nature of work and a lot of things have changed. The pandemic drove us to work out of our homes. What does that mean? What does it look like? How are we making decisions?

Are we making data driven decisions on that? How are we maintaining culture? How are we hiring? Are we hiring differently? , and not only that, not only focusing on it and the roles there and the challenges there, but also on the challenges that our health systems are facing. The changing nature of work as we move into working at hospital, at home, , and some of these other care venues.

what does that look like? Addressing the staffing challenges in the clinical side as well as the administrative side. So, we are looking forward to having that conversation. Love to have you join us March 9th. Keep an eye out. We're gonna announce who the panelists are gonna be. I currently have my feelers out for some people, but you can count on the fact that we're gonna have great panelists.

We're gonna have a great discussion. You can sign up on our website this week, Top right hand. The cool thing about that is you could put your question right in there, and I give those questions to the panelists ahead of time and we make sure we integrate that into the discussion. So sign up today, hope to see you there. 📍   📍

Yeah. So, so the Jefferson approach to this is you do bring it together, you bring the data together, but then before you make it available to researchers and others outside of. Medical record and, some of the areas that we have put a lot of protections around you're gonna synthesize that data and then make that data set available to researchers and others.

Is that pretty accurate?

Yes. With a little exception, which is so there is the data synthesis that happens behind the screen, but there's actually, it's not a data set that just lives there that can be, accessed. It's actually a data set that has a front end on it where you can pick and choose what are the.

That you want, the data that you need. And there's a platform that we're using that also provides you an ability to do some analysis of that data all within the same environment. So you actually don't ever need to access all of the data. You have a user interface that allows you to pull the data that you do need, and there's an analysis environment where you can crunch all of the numbers so that all within one ecosystem, it ecosystem, you're able.

Develop a research question. Identify your patient population, enter in the variables, analyze it, and get some insight. Into what you're looking at.

So you could build cohorts right into the right, into the tool. Is that something , you developed internally or is that something you went out and acquired?

We partnered with a company called MD Clone which is based out of Israel, but they have relationships all over the world. And so we've partnered with them. They're a leading provider of these kinds of tools. we, Our. Partnership with them started probably about two and a half years ago where we were engaged in a lot of scoping, figuring out exactly what are the tools that could help inform not only research, but our education mission because we're also a university as well as our healthcare providers and a lot of the population health management goals that we have.

So we actually spend a lot of time talking. With MD Clone to see if the platform that they have not only fits the needs that we have now, but is something that can grow with us over time. So instead of us building this ourselves, We're partnering with MD Clone and together we are building out all of the data assets in the platform that will help us answer some really key research questions, not only globally, but also specifically within our area in Philadelphia.

But to also contribute our data and research. Tube, other researchers that are also a part of this network.

So how much, I mean you obviously you guys are going out for grants and funding , and all that kinda stuff. How much of this is self-service and how much of it is custom solutions for specific grants that are being applied for specific research that's being done?

Yeah, think of it as this, where you, the, the platform that we have can address a wide range of use cases. So it's, a platform where once we provision the credentials, what the user can and cannot look at, cuz we can still provision a lot of permissions around that. But you basically set that up around whatever the use case is.

So if it's a student, for example cuz you can have MD clone be connected to the classroom where, Are learning about kidney disease, then not only they're learning the technical information they can go into md clone, pull actual real data to see, what is happening with patients with kidney disease, what are the disparities, what are the barriers to treatment?

How long does it take for patients to actually come in presenting with a problem versus, you know, other patients within the city. So there's a use case. Built around just education. And then you can take that model and then just replicate it. For other use cases, like researchers who wanna put together a grant application, you're able to log right in, pull some of the preliminary data conduct some preliminary analysis so you can put that in the grant application to let the funders know that you actually do have the data.

You just need some grant funding to be able to work on it and be able to.

I know that you guys focus, not only you focus on global issues, but I wanna focus in on Philadelphia right now. How, how is that solution going to impact population health , in the Philadelphia market?

Yeah, I, think pretty significantly because it's going to allow us.

Better partner with other organizations around the data that we have to work together to identify the disparities and the inequities, and then be able to do something about it collaboratively. Again, going back to what we were talking about earlier, because we have to maintain the privacy of that data , having a way to synthesize it.

Creates a lot of opportunities for collaboration and collaborative discovery. So, I am looking forward to, once we fully implement the system, we're in the, middle of implementing it now and testing it that it will increase our ability to partner with other organizations including providers.

Better address a lot of the significant health disparities here in Philadelphia.

Fantastic. Billy, I wanna thank you for your time. Love the work that you guys are doing at Jefferson and really appreciate that since I do have family that lives in Philadelphia. Love any progress that you guys can make.

Great. I appreciate it. Thanks so much.

Thank you.

gosh, I really love this show. I love hearing what workers and leaders on the front lines are doing, and we wanna thank our hosts who continue to support the community by developing this great content. If you wanna support This Week Health, the best way to do that is to let someone else know about our channels. Let them know you're listening to it and you are getting value. We have two channels This Week Health Conference and This Week Health Newsroom. You can check them out today. You can find them wherever you listen to podcasts. You can find 'em on our website this, and you can subscribe there as well. We also wanna thank our show partners, MEDITECH and Transcarent, for investing in our mission to develop the next generation of health leaders. Thanks for listening. That's all for now.


Thank You to Our Show Sponsors

Our Shows

Newsday - This Week Health
Keynote - This Week Health2 Minute Drill Drex DeFord This Week Health
Solution Showcase This Week HealthToday in Health IT - This Week Health

Related Content

1 2 3 251
Transform Healthcare - One Connection at a Time

© Copyright 2023 Health Lyrics All rights reserved