Episode 7

Meet the Hosts: Suchi Saria, Ph.D.

with Suchi Saria, Ph.D.

December 10, 2021

Share Episode
Share on email
Share on twitter
Share on linkedin
Share on facebook




Suchi Saria, Ph.D.
Member, Day Zero Advisory Council; Founder and CEO, Bayesian Health

Suchi Saria, Ph.D., is the Founder and CEO of Bayesian Health, the John C. Malone Associate Professor of computer science, statistics, and health policy, and the Director of the Machine Learning and Healthcare Lab at Johns Hopkins University. She has published over 50 peer-reviewed articles with over 3000 citations and was recently described as “the future of 21st century medicine” by The Sloan Foundation. Her research has pioneered the development of next-generation diagnostic and treatment planning tools that use statistical machine learning methods to individualize care.

At Bayesian Health, Dr. Saria is leading the charge to unleash the full power of data to improve healthcare, unburdening caregivers and empowering them to save lives. Backed by 21 patents and peer-reviewed publications in leading technical and clinical journals, Bayesian leverages best-in-class machine learning and behavior change management expertise to help health organizations unlock improved patient care outcomes at scale by providing real-time precise, patient-specific, and actionable insights in the EMR.

Dr. Saria earned her M.Sc. and Ph.D. from Stanford University working with Professor Daphne Koller. She visited Harvard University as an NSF Computing Innovation Fellow and joined the Johns Hopkins faculty in 2012. Currently, Dr. Saria is serving as an advisor to the FDA on AI/machine learning.


Frontline clinicians have had a few years to work with IT, and they're eager to adapt. More and more people are becoming passionate about the intersection of healthcare and technology.



Don Trigg 0:16
Hello, I’m Donald Trigg with Suchi Saria and we’re incredibly excited to join you as part of this new podcast from Think Medium to look at the entrepreneurial changes playing out at the intersection of healthcare and IT. And today, I’m going to spend a few minutes talking with Suchi a little bit about how she got into healthcare and some of the impacts and potentials that she’s likely to take advantage of in the quarters and years ahead. Suchi, t’s so great to be with you.

Suchi Saria, Ph.D. 0:43
Likewise, Don. It’s always fun to talk to you.

Don Trigg 0:45
Well, let’s start by maybe just talking for a few seconds about how you got into healthcare. I think you have an interesting kind of journey story relative to healthcare. And let’s just spend a few minutes talking about that with the group.

Suchi Saria, Ph.D. 0:57
Yeah, I actually grew up being very scared of medicine and biology as a field and kind of was a tech nerd, like stats, physics, computer science. I grew up in India, I got into very, very early, was primarily working in robotics and AI, much before it was exciting as a field broadly. And actually, it was during my time at Stanford, that a clinician colleague, who was a neonatologist, this is around 2007, pre-HITECH Act, Stanford was starting to implement the electronic health record. In fact, Cerner at the children’s hospital. And literally the question was, could we be looking at all this data from the EHR and all the monitor data to be able to monitor babies at risk for complications and bring a machine learning AI point of view to it where we could identify babies at risk for complications early? That was the first time ever I had encountered a problem in medicine. And then before I knew I was sitting at the basement of Stanford during Christmas, reading this big thick book on unitology, and trying to learn CCL, which is a language to pull data out of Cerner. And I didn’t know what I was getting myself into. Since then, it’s just been a downhill journey. But let’s just say I love it. It’s been the most exciting set of problems I’ve ever worked with. And it’s very easy to work 20 hours a day and not feel like you’re working very hard.

Don Trigg 2:17
Yeah, yeah, well, healthcare is sort of a parade of acronyms. And then within companies like Cerner, you have vernacular, like CCL, so, someplace, there’s several old friends and retired engineers who are smiling that you have a command of that vernacular. You mentioned the HITECH Act, big seismic policy driven change that played out in 2009. And then the regulations in 2010. And obviously, data is this kind of great passion area for you. Talk to us a little bit about IT and data specific to healthcare, and some of the learning that you’ve encountered around that over the course of your entrepreneurial journey.

Suchi Saria, Ph.D. 2:53
I’ve had the chance to be part of very exciting projects in machine learning AI, do a lot of seminal work in the field in tech outside of healthcare. And when I came into healthcare, the fundamental questions we started asking is, healthcare data are far more messy than the typical data we see in other fields. How are we going to take AI, adapt AI, push the technology to be able to work in fields like healthcare to be able to produce results that are trustworthy, that physicians will adopt, right, like clinicians will adopt. That’s really where the bulk of my focus has been. And what’s been really exciting to me is watching in a mere period of 10 years, how we’ve gone from what I would consider no data, in the sense of paper records, to be able to have the EMR data, an infrastructure layer. Don, you were very instrumental in making this happen. But literally, now we have one of the most exciting infrastructure layers, but the data now exists as digital. And we can really leverage this infrastructure layer to solve the core problems in healthcare. There are just so many transformative possibilities from you on the clinical front administrative front, cutting unnecessary waste, improving efficiency, improving outcomes. So I think the next 10 years is going to be the most exciting, exciting time in healthcare from an innovation standpoint. And the coolest part of it all I see is moving from the past 10 years where there was a little bit of, like, anxiety around technology not being necessarily helpful, but maybe sometimes being painful. But that’s almost always true when you try to do something new. There’s a period of settling in, understanding, and getting used to the infrastructure. I think the next 10 years, hopefully, we’re going to move towards the place where we’re going to be able to add gains, very visible gains, on top of this infrastructure that’s going to help cut burnout, improve outcomes, move to being perceived as very helpful nd, you know, something we can’t live without.

Don Trigg 4:46
For sure. And I’m just kind of old enough to remember the productivity paradox and sort of how we thought about the disruptive impacts of technology when it first came about broadly. And you’re exactly right. We have to play through people in process related changes associated with the technology to begin to see the benefits of role based shifts, task automations, and the other things that I think we’re right on the cusp of beginning to see play out in healthcare. I’m super excited about it too. I’ve done a very early start up NLP company for computer assisted coding. I’ve also been in a larger company environment like Cerner. I often say that ideation is the easy part. It’s the thousands of tough decisions you have to make after the great idea that are determining. But for all that I tried to do in a large company environment to create those same incentive structures and those entrepreneurial dynamics, there’s something really unique and different about having the courage to jump into an early company startup. And you’ve done that. And so, just talk to us for a few seconds about what it took, kind of the courage to jump and to start an early stage company, which I know you’re super excited about.

Suchi Saria, Ph.D. 5:57
I’ve been pushing on the front of, you know, making AI clinical ready for almost the last 10, 12 years, right? I think from a technology perspective, what I’m seeing is, you know, there’s a massive chasm in terms of, you know, the opportunities exist. Clinicians are eager and ready. There’s more and more excitement. But unfortunately, there’s been a little bit of, like, marketing ahead of the results in the last five-ish years. And I think, to me, I’m a faculty at Hopkins, I hold an endowed chair there to do work in the inspection of machine learning healthcare. I direct a large lab on this inspection as well. And wearing that hat, I’ve got a chance to see front and center how quickly we’re moving to a place where the technology now exists and really high quality research now exists that can be moved to the bedside to actually solve some of these hard problems like, you know, improving outcomes in areas like sepsis, and pressure injury, and readmissions, like all problems all of us are struggling with. But right now, our only solution is task forces and education. Unfortunately, those solutions are not sustainable. But going beyond that, for me, it was also very personal. I unfortunately lost my nephew to sepsis. And I remember when I got a call from Mum, when she called me about it, and I had written one of the early papers, it was a cover article in Science Translational Medicine on early detection of sepsis, with a lot of fanfare. It got a lot of academic recognition. But when she called me, my biggest realization was we have a lot of high quality work that’s sitting now in research that isn’t making it to the bedside. And my work wasn’t really getting out there to help people, and I couldn’t really be of help other than to say that I knew something about it, but couldn’t do anything about it. And, you know, my nephew’s story is only one. As I give talks, I’ve gotten letters from people who are, you know, hearing about this research and kind of would write to me telling me their own story. So, you know, Bayesian, to me, was a real calling, realizing, you know, as researchers, we can really do service to the field in bringing together amazing people who really understand the core of health, the core of tech, bringing it together to deliver it in a way that we can deliver a great experience for our clinicians. And I think now’s the time.

Don Trigg 8:11
As you know, sepsis is such a great example. It was an area of personal passion for my mentor and the late CEO of Cerner, Neil Patterson, who lost his sister in law to sepsis. And it’s such a great opportunity area, not just for impact and truly saving lives, but also, I think, to prove out the promise of clinical decision support and data because of that golden hour and that critical need to get engaged with patients at the right moment to avoid really unnecessary complications that we see far too frequently, particularly in exurban and rural areas where there’s just significant issues around how we think about access and transfer contextual for managing it. So it’s so cool that you’ve jumped in and look to have an impact there. So one of the things that you and I talked about the other day is so many new entrepreneurs flooding into healthcare IT and it’s one of the things, I call it the forest floor, these small, early stage startup companies that are going to grow up to be, you know, large parts of the landscape in the years to come. Tell me just observationally, in some ways you’re really a veteran of the space. You’ve been around it now for more than a decade. just observationally, as you think about it, what gets you excited in terms of new insight and approach? And then what are some of the ways in which maybe you have some trepidation around some of the hard lessons learned that maybe new entrants may miss?

Suchi Saria, Ph.D. 9:45
I think, really, there are problems everywhere to be solved. And if you can find the right people, partner with them deeply, I think there’s really measurable gains to be made. I spend a lot of time focusing on how we can bring chemical signals to the bedside and real, measurable clinical financial gains to be made. And I think there’s just so much to do. The infrastructure exists. Because of interoperability, the data streams exist. I think people have now had a few years under their belt of being able to work with IT, you know, frontline clinicians, so now they’re eager to adopt. So I see from a timing perspective, that’s kind of really the most exciting thing. And there are more and more people who are passionate about this intersection. Partly because of COVID, people are looking for meaning. People are looking to solve real problems. You know, just participating or being part of a gaming company is not good enough. There are really high quality individuals who are coming into the fore to be able to solve their problems. That’s exciting. Okay. So what are the challenges? One of the biggest challenges I see is healthcare is just sort of like a very complex field. It’s very hard when technologists come in not understanding healthcare. Like, it’s interesting. For me, one of the reasons I moved from Silicon Valley to Hopkins was I felt like it’s just the kind of field that it’s very helpful to have education, 360 education. You really want to know it both as an insider, but in some sense, you need this inside outsider perspective, right? You’re not so jaded that you feel nothing can be done. But at the same time, you have enough of a, you know, view of all the landmines that you can navigate around them. And I think that’s where, I think, you know, technologists who are coming in, it’s very important to honor the complexity of this domain and to partner with people who can be true, true partners. And it’s not in a way that they’re telling you what to do and you do it, but you really are learning why you’re doing what you’re doing. And the manifestation of not having that experience is often people are solving the wrong problems. Problems that are not worth solving are not useful problems. So I think, just focus on making sure you’re solving the right problems and then making sure you’re solving the right way. And part of that is being able to understand the ecosystem to know where the landmines are.

Don Trigg 11:56
No, I think that’s so smart. And I do think there are some things about healthcare, particularly the role of Washington as the largest regulator and payer, that cause the ecosystem to operate differently. And I think it is challenging and complex for entrepreneurs who are coming in to really understand, what do I need to really deeply know about health care, about IT, and about how change happens in the ecosystem in a way that allows me to make smart decisions around capital allocation and how I’m looking to scale and grow a business. And I think, time and time again, I see people struggle with that because they’re making assumptions around approach that maybe are inconsistent with realities of how healthcare operates. You talk about that all the time, I think you’ve been very smart in terms of navigating it. And I would really say, on behalf of Dr. Bisbee and Think Medium, I think that really is the genesis in a lot of ways of Day Zero and the desire to want to use this podcast as a vehicle for helping entrepreneurs understand key issues and topics playing out in healthcare in a way that can make them more successful in terms of scaling the enterprises that they’re looking to build out. And I know certainly they’ll get a ton of benefit from listening to and learning from you, Suchi, in the months ahead.

Suchi Saria, Ph.D. 13:18
Absolutely Don. And I think the insider outsider perspective, right, there’s a little bit of, when you’ve been in healthcare for a long time, reluctance to really take on big bets, and important ideas that we all agree need to happen. But all of us sort of, you know, there’s a question of, like, is now the right time nd do we need to be the ones putting in the energy to make it happen? I think this is where, you know, from a timing perspective, it’s very unique. COVID pretty much gave us a clean slate to start all over again. Everybody’s trying to re-understand priorities. We also all know IT is here to stay, data is here to stay. Infrastructure is here to stay. Incentives that promote high quality delivery that’s cost effective is here to stay. Consumerism, access, is here to stay, which means there’s real opportunity to partner with really high quality people, seasoned, seasoned healthcare executives, to partner with high quality teams, entrepreneurs, bring them along. They need you as much as you need them. And I think it’s, like, I’m hoping the next five years is going to be about very exciting conducive partnerships all across the board to make things happen.

Don Trigg 14:33
I think that’s 100% right and, how do we make it easier for big companies outside of healthcare that see an opportunity to come in? Similarly to your point, Suchi, how can regulators and others think about this entrepreneurial ecosystem and make it easier for companies that are looking to have discernible impact to understand the regulatory framework, take advantage of emerging standards that can be important in terms of how they look for scale attributes around their business. I think this has absolutely got to be multi-stakeholder and orientation approach if it’s going to have scale impact for healthcare.

Suchi Saria, Ph.D. 15:11
I couldn’t agree with you more.

Subscribe for Updates​

For exclusive access to Think Medium content and program updates, subscribe here.