Dr. Maulik Purohit, Associate Chief Medical Information Officer at University Hospitals joins us to discuss precision medicine and how it has the potential to really drive patient care in a much more personalized and individual way. Hope you enjoy.
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 we have another interview in action from the conferences that just happened down here in Miami and Orlando. My name is bill Russell. I'm a former CIO for a 16 hospital system and creator of this week health instead 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 leaders, Gordian dynamics, Quill health tau site nuance, Canaan, medical, and current health.
Check them out at this week. health.com/today. Here we go. All right, today we have another one of our post hymns hymns interviews. Essentially, we couldn't get to everybody. We wanted to speak to at the conference. So we have some zoom calls set up afterwards. And today we're talking to Dr. Maulik Purohit with university hospitals, he's the associate CMIO.
And we're going to talk precision medicine. Maulik. Welcome to the show.
Yeah, absolutely. Thanks for having this is, , this is quite an honor to be.
Well you did a presentation at hymns. I think that really hits on a lot of different intersections of things and people are very interested in, and that is around precision medicine give us a little background on what the, what the conversation was about and, some of the, some of the key topics that you addressed in your presentation.
Absolutely. Thank you for having me and for all of us on this. Yeah, it's a topic that's near and dear to me, for many reasons. One, and the main reason is because it offers the potential to really drive patient care in a much more personalized and individual way.
We often, you know, healthcare in a generic ways and we kind of sometimes lose the individual in the forest. And we w this is the opportunity to really use, , technology to drive better patient care. And precision medicine is really about understanding the individual patient, their reactions to medications or treatments or analysis or diagnosis, and then translating that to a better customized level of care for the patients.
Yeah. So where, where are we at on this? Cause we've talked about this, a bunch on the show and it's, it's one of those where we say, okay, now we're going to be able to really get precise with the medications that we're in. And, you know, there's a, in most medications, there's a population that it works really well in and a population that it doesn't work well in a, have we gotten to the point where we can identify which patients and, and how are we operationalizing this one?
Yeah. Great. Great question. so the insert it, as you can imagine is not an easy black or white, it's a yes and no. , and for some things that we have, and I'll take, let me take you through a little bit of the reasoning background as to why, , it's so complex and we talk about it, but haven't had the success yet that we hope to achieve.
You know, I'll compare it to another industry with the electrical vehicle injured, electric vehicle and your which, you know, it took some time. Right. And we used internal combustion engines for over a hundred years. That's an understatement. It took some time for the electrical. It's still evolving, but now we're seeing, you know, Volkswagen saying we're taking our whole fleet that direction.
So it's hit that tipping point. Yeah.
That's exactly, I think where we are with precision medicine. And then what I would say is this concept of. Clinical decision support, which includes to me AI and machine learning and precision medicine, all in all in one but you know, it took over a hundred years to get us to a battery powered vehicle.'s a lot of doubts, right. In:
You know, so with precision medicine specifically, you know, and I'll get to one use case that you mentioned is a medication. Can we identify one Medicaid? That's going to work for one population patients, but not others. And then from that standpoint, give better personalized care. And so it starts with someone's genetic code and what they have in their DNA, literally in their DNA.
and then how that translates to who they are as a person. And there's a long path, but from, , from the genetic code to who we all are as people, because there's that genetic code, but there's the environment that we all live in. And so I'll give you a simple example is you may have a, again, this is just for, , concept, but let's say you have a gene for being seven foot tall and, that's great.
But then you may have grown up in an environment where we didn't get proper nutrition or whatever it may be. And so you may not achieve what the genetic code dictates because. The environment also influences the genetic code and what is expressed into the phenotype and the same way. , we're learning a tremendous amount about the genetic code and what we can do and how that translates to disease, how that translates to our metabolism, medications, or processing of medications, , bioavailability, bio availability of medicine medicines, and, , our reaction to treatments and so on.
And so. And so one area that you identified, which is fantastic is medication response. So in one area we do have some success and knowledge, which is, , with, , depression treatment. And there's a medication class called SSRS. Selective serotonin re-uptake inhibitors. These are the Selectsa Lexapro Prozacs that people talk about.
And one of the struggles in the past was how do you identify the right medication for the right patient? Because I might prescribe, let's say just hypothetically, I am prescribed to use Alexa for you, , are prescribed as lots for patient. And each of you may have a very different reaction. One might have an allergic reaction that, , makes it unusable.
Another person might have a fantastic response that, , that's all they need and they are back to conducting their lives normally. And we don't know that out priori meaning when somebody walks into the clinic space and I see them, there is no way for me to know how they're going to read it. Right now, now with precision medicine and with the partnership, but to be precise, what we've been able to do is take that and say, okay, we can analyze that as United code.
So if they've had the lab test to get the genetic code, we can put that into our pharmacogenomics area, analyze that genetic code. See what matches with the best SSRI and then have a much better educated guests as to what's going to affect them in a positive way, rather than the trial and error way that we often are used to in medicine.
Well, I wish I could ask better questions on that. I'm not a, I'm not a trained clinician. And even if I was, I'm definitely not somebody who's a geneticists. So to ask the questions to go in that direction, what I want to ask though is for the clinicians who are hearing this going, that's really interesting.
How, you know, what does that look like day to day with the EHR, with the, , the integration? I mean, are we adding steps? Are we adding screens or is this one of those things where you, you put in the medication, it's looking at the data and it's popping up something that says, Hey, consider this.
Yeah. Great question. So that brings us to the infrastructure side of it. Okay. You may have the knowledge, but if you can't bring it infrastructure wise into that technology space and the workflow, then it's not going to be used. And so that's where a lot of my focus is and I'll, and I'll be up front. I'm not the expert in genetics.
I'm not the expert in cancer care, but my role as associate CIO and the innovation lead for transformation is to help put this into the workspace that it can be supported and use and support our clinic. And the work that they're doing. And so, and there's a long process for this. And this is where, you know, an organization like duty precise has been very instrumental for us, which is one is getting the blood test first and foremost, that allows us to get the genetic code from people into the EMR.
But that process is pretty long. So you go by, so you get the lab test, you go to the lab. Now what often happens is the lab may not be interfaced with your EMR other places. And so they send a PDF results of the genetic code. And the problem is that a computer looks at a PDF as an image and it can't decipher the content of that message.
And so you need to have that in what's called structured data or discreet data. And to be precise, I've been really instrumental in health. Take that interface from the lab to our inner, , to our EMR and convert all of that into structured data that we can then analyze in real time with the computer.
Now, once that data is in there with the genetic code to present, it's also helps us curate the data because if I give a length of genetic code to our clinicians, even on a geneticists, they won't be able to use that because it's really raw data that doesn't have much meaning. So we need to convert the raw data into non.
That then supports clinical care. So that's the other part is using the expertise when to be precise, to curate that data, looking at what scientific literature I was there, compare that to genetic code, put all that together, and then convert that to a decision support tool that the clinician can now use.
And then from our side, we then take that and then convert that into the EMR, into the workflow of the EMR and the user interface to make it usable. In real time for the clinician. And so then the clinician has all of this knowledge, not just raw data and knowledge in front of them in their workflow, as they see a patient that allows them to use that knowledge and treat better, treat the patients in a better manner.
So let me, let me ask two different questions. One is a quest lab core. Will they supply that data a in discreet?
Great question. So I don't want to quite like that. I don't know that labs specifically, but what most labs do is they give us the data and then for us, what we're actually working on with to be precise as to take all of that data, put that into a single pipeline that comes to us into the EMR and typically most likely.
Don't have the ability to convert it into discrete data. And so we have to do that on our side. And then that's where we have a partnership with, to be precise, to do that.
So talk about adoption. So adoption is always one of those things. When we talk about these kinds of projects, I mean, the, the, the, the capabilities that you're describing are, , have a lot of promise and, and are very exciting.
The question becomes when you get. That clinical decision support in front of the clinicians. How did you get them to, I don't know, to, to use it, to want to use it, to understand what it meant when it actually did pop up in front of them.
Yeah. Great question. I love this topic and then I'll tell you the key to adoption is a great product, right?
I don't know if you have an iPhone or an Android or whatever, but nobody has to tell me to get an iPhone. I got it. I get what I've resolved and I update it. I love using it. Nobody has to tell me to go use my iPhone. Everyone has to tell me to stop using my iPhone, right. Or whatever smartphone you have.
, and it's the same thing with it. Products and healthcare space is not a traditional we've given physicians and nurses a bad name and said, oh, there's adoption is a struggle, but we haven't said, well, we've given them a bad product. If I'm going to give you a product that is going to increase your work time by two hours.
Not to have much clinical meaning and really not impact anything in a way that's meaningful for the clinician. Well, the adoption is going to be an issue. However, if I give you a product in your space that reduces your critical load, , , in terms of time, but also it gives you better patient care and it's actually decision support and helps what you're doing.
Adoption is very easy. And so to me, the question of adoption is not the question of, well, if someone used a product, the question of adoption is are we giving them the right product in the right way at the right time, that makes it easy to use. And the same thing, like if you want it to get a cab and your Uber app was so painful that you couldn't get a cab and it took you 15 minutes, you would just walk out the airport and get a cab outside.
But because the overlap is so easy, Adoptions on an issue. And it's the same thing I would say here.
Fascinating to me. It's, it's, it's a platform. So I'm going to be able to apply it to, , many addition, ma many different specialties, I would assume across
the board. Yeah. And we have many different, , initiatives in our system.
So the one you described pharmacogenomics that we want into a little more. That's one of our other ones, but we have good for our, , fertility and, and, , OB areas. We're looking at it for pediatrics. We're looking at it for, , oncology. So there's many use cases. And as you said, it's a perfect question because once you create the platform and the process, the use cases, , are plenty.
And in fact, we've had people in some departments actually use it and uptake it without us doing any marketing or any education. They saw the value of. And I started using it and our numbers went up and we're actually surprised because we monitor the data and we had adoption to areas we didn't expect, but they love the information that they're getting and now we're getting more demand for it.
And so, , this is a huge, , consumer it's, it's a huge need from the consumer side, but the consumer isn't just the patient. The consumer is your providers, your nurses, your patients all together, because they want a better way to take care of. And so this is huge and I'll tell you the other, , the other part we haven't hit on yet, but is also a limitation, , is the access to the test to get your genetic code.
, if few years ago it was, , very expensive. It might cost you three, $4,000 out of pocket, which as you can imagine, limits the access tremendously. The cost has come down because we've gotten better at getting the genetic code, but getting insurance reimbursement to cover the cost of the test would be fantastic.
Because that's going to really drive better care and upfront there's a cost, but in the long run, it'll pay for itself because you're providing better care up front to the patient and eliminating some of the downstream effects of poor care up front. And so that's the other area that needs development.
Fantastic, , millennia. I want to thank you for your, , for sharing your experience and, , really appreciate your.
Absolutely. Thank you so much. It's been an honor to have beyond here. Thanks for having.
Another great interview. I want to thank everybody who spent time with us at the conferences. It is phenomenal that you shared your wisdom and your experience with the community, and it is greatly appreciated.
We also 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 Kern health. Check them out at this week. health.com/today. Thanks for listening. That's all for now.