Skip to main content
Loading Explore guides…
Connecting Providers to Patient Data · Acedra
Home
Explore
Medicine
Connecting Providers to Patient Data
Sign in to save
Chat
If YouTube asks you to sign in, open the video on YouTube.
Watch on YouTube
Reload player
Transcript
167 segments
Copy
Hide video
0:00
Andy Choens: So yeah the the topic that i'm going to speak to today is connecting providers to their patient data and as i'm, Andy Choens: watching people i've got the chat pulled up and i'm watching people saying i'm someone just said that they were from France, I saw Nigeria Canada, Andy Choens: my hometown of Atlanta Georgia i'm up here in upstate New York, but yes, I am a rambling wreck from Georgia tech,
0:25
Andy Choens: Thank you for joining us today, given the fact that you know, obviously healthcare is a highly that we all have, Andy Choens: Healthcare is the same everywhere in that we're always treating people we are trying to make people healthy, yet the business of healthcare is highly localized, Andy Choens: And I was very much when I was putting the slides together, I will confess I was sort of thinking of the concept of of US national level thing so,
0:51
Andy Choens: i'm going to try to be very conscientious as i'm going through some of these topics and I started throwing out terminology because epidemiology healthcare, etc, Andy Choens: is just rife with terminology so i'm going to try to not drown everyone in lingo also when I just have to because you know it's health care, and we need more acronyms I will try to make sure that I am backing up, and you know kind of trying to least give where that acronym comes from,
1:16
Andy Choens: I want to also start with connecting providers to their patient data, so what am I talking about there and who rather, Andy Choens: Specifically i'm talking about in today's discussion ambulatory providers, a lot of times when we start talking about health care, a lot of the, Andy Choens: papers you'll read etc that are about how hospitals providers a doctor and a hospital doing a surgery providing us a care providing an intervention,
1:42
Andy Choens: Well, the world that I live in is actually the other side of the coin it's when the patients go home, Andy Choens: I work with providers all over upstate New York that are providing care in the ambulatory setting it's a it's a mix of both primary care specialist care,
1:58
Andy Choens: But the point of it is that all the providers that I work with our annual what we call ambulatory providers, which means you can emulate in you talk to the doctor and you emulate out, this is not in patient, this is not, Andy Choens: Emergency department care of this is going in for your annual physical make trying to maintain and deal with chronic diseases like chronic heart failure, what have you,
2:22
Andy Choens: This is not that the stuff that we always see on the news in the evening or your watch your local news is out of the emergency department is reporting this or that but that's a little bit different than what we're talking about here today, Andy Choens: Alright, so with that what is it cute as hell, we are we, the terminology, we like to use is that we are a population health services company,
2:47
Andy Choens: We help providers make that transition to in America, we are making the transition from transition from a world of fee for service, so you patient walks in patient has given some care and has charged health insurance pays for, Andy Choens: The American healthcare system is moving away from this fee for service model into this value based payment model which is more about trying to codify and,
3:14
Andy Choens: document the conditions that people are dealing with and provide a mechanism to empower providers to, Andy Choens: really treat people holistically and to try to make sure that we're actually dealing with all of the needs that patients have, Andy Choens: This is a sea change and how health care is provided, because most medical office models are based around the idea of,
3:35
Andy Choens: Patients come in, we will do something for them, we give them an x Ray we do whatever the patient walks out we get paid, Andy Choens: Value based payment is a completely different world, and so what acuteness does and i've got a picture up on the screen of prior to the 19 the office that we occupied Hello river street in Troy New York,
3:53
Andy Choens: That is the rise building in Troy New York it's a lovely build building that goes back to the 19th century, which I have not been inside of for more than a few minutes at a time in longer than I care to admit, Andy Choens: Oh so cross the bottom there so who are we, more broadly, we are this independent, Andy Choens: Population health services company we work with and are owned by CD php, which is a regional health care provider here in upstate New York,
4:21
Andy Choens: And one of our service vendors that we work with very closely, that I need to make sure I acknowledged, our role and what we do is health catalyst So those are the three logos that you see across the bottom, Andy Choens: Because what we are doing the the position that acuteness sort of occupies is trying to get everyone to work together and i'll talk about that more in just a moment, but before I do,
4:44
Andy Choens: Okay, so who am I, I like to joke, that I am the pirate Captain I lead the data science team here at the cutest health, I personally have a background and program evaluation and program improvement, Andy Choens: i've worked in areas such as ambulatory care, child welfare eldercare and other human services domains, Andy Choens: rumor has it, although this is just a rumor and remains to be seen, but rumor has it, I am a fan of the 18th letter of the English alphabet,
5:11
Andy Choens: And yes, I did actually choose this picture very, very, very consciously so, Andy Choens: On slack and zoom I use a picture of the pirate captain, if you are things of British humor you know this show you if you don't know the show you need to know the show go watch it it's hysterical, Andy Choens: Charles Darwin has never been so much fun, but the pirate Captain only succeeds, he only survives literally to the end of the show because of his crew,
5:41
Andy Choens: So, the reason I chose this picture is because sure i'm the one here talking, today, but this isn't really my work, Andy Choens: The thing that I want to make sure that i'm really transparent about is that this is the work of a large group of professionals, that I have the pleasure of working with, and they have come together to help us all create these really interesting ways,
6:01
Andy Choens: of trying to connect propriety providers to their data across ehr claims HR systems, all of these different data sources that tend to live in their own silos and their own bubbles, Andy Choens: It is this team not me that created this and it is this team that is going to be able to make this carry forward into the future,
6:22
Andy Choens: All right, so technologies like I said I did want to make sure I throw their logo in here a couple times that we do work with a company called health catalyst that helps provide some of our backend services, Andy Choens: In terms of technologies used we use a lot of our we use a lot of Python use a little bit of javascript and, Andy Choens: We still have some, Andy Choens: But all jokes aside, we also do we our customers with RStudio we use RStudio connect and we also use a if,
6:55
Andy Choens: anybody really wants to know all the dirty laundry in the back end we use Microsoft sequel server for our backend database driver So those are in sort of the the suite of technologies that we use, Andy Choens: Oh, I didn't put the logo up here, but we also have her what we call the report server which runs docker instances So those are sort of our suite of technologies,
7:16
Andy Choens: When we started acuity as we were very purposeful about trying to not have a single technology or not have a single, Andy Choens: Language that we would try to implement everything we wanted to recognize that data science is a rapidly growing and changing field and that the reality is is that we should be trying to use the best tool for the job, Andy Choens: And while people are certainly welcome to argue about whether or not we have done that in all instances,
7:44
Andy Choens: These were the best choices for us at the time, and we have been trying to make sure that we are empowering the people on our team, remember, I said it's really about that team, Andy Choens: So we were trying to make sure that we were empowering the people on that team to use the technologies that fast, Andy Choens: That situation and their needs, at that moment,
8:01
Andy Choens: So that's why we have tried to make sure that we don't do i've worked in other places where everything has to be done in spss for everything has to be done in SAS or, Andy Choens: Everything has to be done in our and we have taken the opposite approach, where we say let's just try to figure out what the best tool for the job is and then use that tool so,
8:20
Andy Choens: You know there's some limits on that I don't think we have anything implemented in erling yet, but give us time it was time, Andy Choens: Alright, so some fun facts about acuity, Andy Choens: acuity, this is the logo, we live in this sometimes uncomfortable space between insurance companies aka payers and your doctor or the provider I tend to use the terminology of payer and provider, but when I say pair I mean,
8:45
Andy Choens: medical insurance company, and when I say provider, I mean you're a doctor or the the practice sort of more generally, Andy Choens: It is our job to help both succeed, we are currently importing just for some context in terms of what we're dealing with we import ehr data from 14 different vendors and we do so by a variety of means, including OTC,
9:08
Andy Choens: If you are familiar, how ehr are implemented here in the US, the consolidated clinical document or ccta and just good old fashioned csv, Andy Choens: We are actually supporting over 200 practices and the capital district in upstate New York region and we work with 11 different payer groups, Andy Choens: And we do all that as a company that is going to turn five next year, so we are a very young company we move very fast,
9:37
Andy Choens: We break things from time to time, but we, what we are doing is trying to provide a highly fluid group of services to a very diverse group of providers to help them like I said succeed and thrive in this value based payment regime, and so we live in the middle, which is, Andy Choens: Sometimes uncomfortable because it's difficult living in the middle of between two different groups that actually have a lot of the same common interest,
10:05
Andy Choens: They don't always see themselves as having all of the same common interest, so we live in the middle, helping everyone understand how actually providers and payers really do have a lot more overlap than they have in terms of differences of interest, Andy Choens: Some context around the provider tools that we're going to talk about but let's think about so I started this saying that we are going to connect providers to their data, and that is what we do,
10:31
Andy Choens: So let's think about what those those data sources really are you have ehr which are these marvelously complex relational data, Andy Choens: sources that have all of the patient history, the amount of data that is and, by the way these screenshots know I pulled these down from the vendors websites, so if there's pH is, Andy Choens: These are not screenshots from our clients,
10:56
Andy Choens: But any HR is this incredibly complex thing that is it's basically a filing cabinet for everybody's healthcare data, Andy Choens: And then you have the practice management system, Andy Choens: which deals with things like billing and upcoming appointments helping you know you call them up and say hi i'd like to see my doctor, they say Okay, so we have an appointment available next Tuesday at two o'clock can you do that,
11:18
Andy Choens: that's what that practice management system that's in most practices, these two systems live independently of one another they're connected there's obviously the practice management system can tell the ehr there's an appointment to has to be connectivity, Andy Choens: Yet at the same time, they are actually separate systems and then other groups of data that exist,
11:39
Andy Choens: In here in the United States, we have what we call health information exchanges health information exchange, I work with most often is called fix me, Andy Choens: and health information exchange sends out what we call it tell seven I know so much lingo I hit home, Andy Choens: Health care sometimes so in atl seven message is just a fancy way of saying xml, it is an xml message that has some information about an event or a patient that gets sent out over yield enter webs,
12:05
Andy Choens: And so that information goes out and usually gets dumped into the ehr and notifies the provider of some adventure some something, Andy Choens: Again, all that's going into the ehr and then of course the other sorts of data providers are having to deal with increasingly or claims, Andy Choens: So a patient, you know the practice management system, the HR know what's going on here,
12:26
Andy Choens: But there's this bigger picture of when you start trying to talk about a holistic picture of what someone is medically, Andy Choens: there's this larger picture of of what are other providers doing when they're you know da sign, and all this legal stuff gets taken care of, Andy Choens: How can we leverage the incredible power of claims data, the incredible power of these health information exchange systems,
12:48
Andy Choens: And all the data providers have historically collected in their ehr and practice management system and the reality, Andy Choens: Is that that big holistic picture is what i'm referring today to as population health and there isn't really a stock tool you can't go buy a system for this, Andy Choens: And in fact i'm not even sure at this point, you can because the needs are so regional that are so dependent upon what that practice is doing at that time,
13:13
Andy Choens: Here in the United States that health department of health and human services comes out with a new medical model, Andy Choens: Roughly every three minutes or so that providers may or may not decide to get involved with, so the the complexity of healthcare, Andy Choens: Just within the United States, let alone the rest of the world, but just within the United States is mind boggling complex so that's why companies like oculus have been starting,
13:37
Andy Choens: starting up is to help support providers and all of us, so now, of course, the obvious question is okay, so you say that you're supporting people with us So what does that mean, Andy Choens: So i'm going to take you through what i'm going to refer to us and population health tools, these are some tools that we have provided for our clients,
13:57
Andy Choens: out i've already said that this is obviously very tricky because there's all these different data sources, they don't necessarily want to talk to one another, so, Andy Choens: Effectively, what i've introduced you to as the authority and not modern medicine medicine so we're going to be a little bit Alexander the Great here and we're going to cut that Gordian knot,
14:15
Andy Choens: And there's only one way that I know of to do this and that's by getting everybody at the table and involved, Andy Choens: So when I show you these tools, these are not things that were like made in in the back office somewhere and some people, the data science team got together like Oh, this is a cool idea,
14:35
Andy Choens: that's not how we do things we are not providing a product like Microsoft, where we work on it for a couple of years and then shove, it out, we put it in the store and we asked you just people to buy it, Andy Choens: We have contracts with providers, they need services from us what happens in terms of how we actually get to these tools is the providers or the payers come to us and say hey,
14:58
Andy Choens: there's this need, we need to be able to communicate around this, we need to be able to help people navigate this, Andy Choens: Specific space, maybe we need to help with transitions of care so when people leave Inpatient setting, how do we make sure that that works, how do we make sure that the primary care providers following up with that patient, Andy Choens: And just if you think about that that transition of care, you have a patient leaving the hospital,
15:23
Andy Choens: And they're going to go home and it would be ideal for their primary care provider to follow up and provide contact you know check in with them, Andy Choens: Do we need to talk about your medications how are you feeling do you need to come in and see me back, let me go ahead and schedule that for you, Andy Choens: that's what we're talking around around transition of care and it's really hard because what's happened traditionally is ehr,
15:46
Andy Choens: get this message and it gets dumped into the ehr and it may or may not generate an alert for the provider, Andy Choens: And there's more people at an actual practice, and just the doctors to work they have a support team around them, so I want to introduce you to the first tool that's going to help us cutting the Gordian knot is to help hospital activity monitor or ham,
16:08
Andy Choens: Now you will note that the picture that I have on the screen at this point is have a lump of ham and not the tool which gets us into this really funny thing about healthcare, Andy Choens: can't share with you about what we do directly because it's literally talk for ta ta,
16:25
Andy Choens: And I don't really want to violate those federal laws, so I have to be a little bit careful here i'm going to do have some other screenshots, but I just want to acknowledge the pink elephant in the room, of, Andy Choens: we're doing things that we can't directly show, so what is the hospital activity monitor ham, as we call it and you'll see that a lot of our,
16:45
Andy Choens: there's a joke, with everything we have to have our fun the ham report is a daily email that goes out, it is actually provided to the sites as a as an excel file, Andy Choens: And in that excel file is are going to be a whole bunch of tabs and those tabs had things like here's the list doctor, you know, whoever, Andy Choens: Here is a list of your patients who is in the last 24 hours were admitted to the hospital so here they are and what the admin reason, yes, these are all,
17:14
Andy Choens: Patients that have consented to having their information exchange over the HIV that health information exchange, they have consented to that this doesn't just happen by magic, they have to consent, Andy Choens: If they do consent and they allow their information to be sent out over hicks me to the provider we pick it up and we give the doctors reports a hey,
17:35
Andy Choens: These are your patients that have been admitted in patient for the last 24 hours, we also have a list of your the patients who are discharged from the hospital and the last 24 hours so they've gone home, Andy Choens: Somebody should probably follow up with them and again there's context, so you can see, in terms of you know what type of stuff we're providing,
17:53
Andy Choens: Some of its really boring the Mr in the name of the date of birth, just helps people know that we're talking about, Andy Choens: But if you go in and you look at some of the event information, where where are they going Where do they were they admitted to or discharge from so, Andy Choens: You know, hospitals, that we have appear in the capital district places like Albany MED or St peter's this is, you know what I mean by an admin,
18:15
Andy Choens: facility that were discharged location Why were the invitation, in the first place, what was that primary reason, Andy Choens: What was the discharge date, if there is one that's obviously only discharges and for context for the provider again driven by the HIV,
18:31
Andy Choens: How many recent in your visits have they have how many recent Inpatient visits have they have because you're someone who has an impatience day and you can look around the last year they've had seven visits and now they're impatient, Andy Choens: that's a very different patient and some of you just went in you know overnight, now we have to try to gauge what is the severity of the patient's needs so we try to provide a snapshot picture of what's going on,
18:58
Andy Choens: The providers still has the ehr if they have further questions they can go, Andy Choens: diving through the incredibly rich data set, that is, the ehr, this is a snapshot that allows, Andy Choens: The provider a nurse or care manager to make rapid decisions about which patients really need to be prioritized for follow up on that transition of care which,
19:20
Andy Choens: Patients need to be followed up, while they're actually in the hospital, what have you and all of this thing is about really providing patient connectivity between the the ambulatory primary care provider and the patient when they're going in and out of the hospital, so that is, Andy Choens: A whole lot of him, Andy Choens: Another tool that we have, which we call the chronic conditions report or ccr, and this is another excel file that is generated and sent out and both of these,
19:48
Andy Choens: So the actually backup hospital activity monitor is actually a Python script and ccr is our scripts, Andy Choens: And these run on what we refer to as our report server, which is our docker power system for emailing out large numbers of excel files what we developed internally, Andy Choens: The This is again an excel file like I said, and this is something that we send out every other week to a site,
20:12
Andy Choens: And so, if you are familiar with an ehr one of the things that you would know is that eh ours are, Andy Choens: I kind of compare you can see, this because it's a part of me, but I have a filing cabinet in front of me, they are a patient filing capital, Andy Choens: All of the information gets put into the right little you know folder inside the ehr for that patient and it's a marvelously rich data source,
20:35
Andy Choens: But the HR are not good at providing the 30,000 foot view of what's going on, so if you take off in a plane and you're flying over you know, wherever and you look down, you have a completely different view, Andy Choens: Of the countryside than you do if you are driving down the road, and I would say the ehr is like driving down the road using you know, Google to get you from point A to Point B,
21:00
Andy Choens: And this chronic conditions report, this is what you see when you get the plane, because this is full panel data ehr, Andy Choens: have obviously full panel data when I say full panel data What I mean is, all the patients at the site, Andy Choens: So ehr is have that, but when you use an ehr you're looking at just my data or just your data you're not looking at that 30,000 foot view,
21:24
Andy Choens: The ccr is that 30,000 foot view so we break it down and we say Okay, so how many patients have diabetes at your practice and those who do what was our last day once the value, Andy Choens: Because providers need a way of saying hey you know i'd like to be able to do this new intervention i've got this this new technology or i've got this new care manager is joining my practice, and we want to really be able to target people who have an agency overnight,
21:51
Andy Choens: Well, this ccr what we like to say is this democratizes that data, because without having to come to us, or to come to anyone else the provider now has the ability to say all right, Andy Choens: Who are all my patients who have diabetes, with an agency overnight, Andy Choens: They have the ability, using this excel file to literally make that list, and then they can hand that off to their care manager in the office a please let's go provide some services for these patients,
22:16
Andy Choens: If it makes it rapid it makes us they have full transparency into what's going on, Andy Choens: And you can see, the entire list of things, you know that we are providing terms of the types of conditions and labs that we targeted on this and we're adding you know more slowly, it also provides, Andy Choens: A high level view of what are those conditions, you can see, you a risk assessment at this particular,
22:42
Andy Choens: provider at this particular 10 they do what we call provider risk assessment provider puts patient patients into risk levels of 123 and four, based on the criteria, Andy Choens: Patients who are in level four referred for care management, Andy Choens: And that cm active is are they active and care management hits me consenting so we you know, can we share their data over hicks need do they have diabetes, this is how many,
23:06
Andy Choens: And an ehr isn't really good at those because that's not really what it was designed to do and see I can finally show a screenshot that says a phr, Andy Choens: But this is the kind of data that an ehr is not well equipped to provide to provider, Andy Choens: The next one here and i've just got one or two more slides here before I wrap up, but this is what we call our pre visit planning document so Jane doe is not a real patient she is not a real person so,
23:34
Andy Choens: This is a dummy document, but it is emblematic of what our pre visit planning tool is again like I was saying, an ehr is super complicated and the ehr provides all the detail, Andy Choens: All other agencies about values all of their history, so we developed this pre visit planning tool to help providers get ready to see you,
23:59
Andy Choens: So hopefully in the day or two the week, what have you before your appointment, when you go into cedar provider they sit down and they do a chart review, Andy Choens: They go through, and they think about who you are medically they prepare themselves, and because of our role kind of help providers succeed and value based payment contracts,
24:17
Andy Choens: Some of the space here is occupied by information that will help that provider know what things they should be doing so, for example, down here, Andy Choens: We have some list of cervical cancer screenings and the studio in that case, or something for them to do, Andy Choens: And, but we have a list of things that these are coming these measures or ECG one measures for those of you in the United States,
24:38
Andy Choens: These are measures that the doctor should be considering about how am I going to fill in this patient this particular patient apparently very complicated, Andy Choens: This is a little over the top in terms of an example, but it gives you an idea of what type of information is on how we're trying to help providers identify opportunities to close gaps in care,
24:58
Andy Choens: He goes down and has you know, an er an impatient say so again we're integrating data from the HR from kicks need from claims, all this is getting dumped into this one single document, Andy Choens: That your primary care provider can review and try to mentally get ready to provide you with the best possible care at that point of contact in the office they can sit down and they consider the orders, you know they can say Oh, did you follow up on that what have you,
25:24
Andy Choens: Then, if the provider has further questions again they still have that ehr they can still go to that, and they can open that up, Andy Choens: and go looking through Okay, so I see that your last day one seems really high what's a 12 that's it's not good, but they can go into the HR and said Okay, you had 112 everything also pretty good and you had 112 that's different than a patient that's got lots of 12,
25:49
Andy Choens: And 12 is not getting Wednesday, so they still may have to go to the ehr to really kind of put that full picture together but we're providing a snapshot, Andy Choens: of information that really helps the provider get their head in the right space, so that they were they walk in to see you, they are ready, they know what's going on, and they have some context for where you are medical,
26:11
Andy Choens: The last tool i've got I wanted to talk about just because this is an RN epidemiologists, Andy Choens: kind of seems like need a shiny application shown us i'm wearing this thing, Andy Choens: So this is a shiny out that we may and it's also I wanted to use this as an opportunity to highlight something that's not ehr driven a lot of our tools are because we are connecting providers to their data, the HR driven Of course they are,
26:34
Andy Choens: This appointment trends application is not in fact there is almost no he HR data in this thing whatsoever also fun, because that means I can do screenshots but, Andy Choens: What this is really being driven by is by that practice management tool you've got appointments coming up you've got appointment showing up or not, Andy Choens: If you would all recall it,
26:58
Andy Choens: back in March of 2020 the State of New York shut itself down and so with this tool came about was over, about a weekend after, Andy Choens: hit and New York City and the New York state just a day or two later started shutting down provider started calling us as a I know that people are not going to show up for their appointments,
27:21
Andy Choens: I know people patients aren't going to show up for their appointments, I know that my numbers are decreasing of appointments, but I don't have an ability to wrap my head around with that, Andy Choens: I don't know how bad, we were able to very rapidly put together a, Andy Choens: tool It started off as a FLEX dashboard that we email the people and, later, we were able to pull it put it together as a shiny application and I was actually,
27:43
Andy Choens: In our network and that purple line is 2020 and you can see, the fall off the crater there is right there as we go into march of 2021 cubit 19 has New York state to shut down hard to deal with the epidemic, Andy Choens: And the green line of bears what it should look like for 2019 so we're looking at the difference this tool is also was able to be adapted,
28:08
Andy Choens: To help providers understand Okay, I know my in person numbers are crashing that's what that screenshot was, but they were also implementing remote care, all of a sudden, Andy Choens: kind of wild you could go to your doctor on zoom and like have an entire medical visit where you didn't even have to like be in the same room with your provider, Andy Choens: And we all of a sudden, we shoved medicine in the 21st century,
28:31
Andy Choens: And the practice sites we're working really hard to implement these technologies and they will honestly doing a really good job what they didn't know what were they were they plugging the whole, Andy Choens: I said I know my Inpatient number my my in person numbers are down,
28:45
Andy Choens: Am I plugging that whole with these remote visits, and so this tool actually has the ability to let us go in and track, and of course it varies by the site and it varies by the type of care provided, Andy Choens: But we were able to start helping providers understand, yes, your in person visits are way way down,
29:01
Andy Choens: This is to the extent that we are able to make that up using remote technologies remote visits etc doing phone calls what have you to really try to make up that whole makeup that gap plug that hole, Andy Choens: This was a tool that came about, I want to say, the initial version of this we put together literally in one weekend, Andy Choens: And we were able to get this out and by the end of the year, it is now a standing thing that standing application,
29:25
Andy Choens: that the practice, some of our practice sites continue to use here in 2021 to understand what what their numbers are looking like trending over time because simply put, Andy Choens: Appointments mean revenue, so, while you know one blend you know depends, how much rather new depends on what the appointment is your appointments are going up revenue will eventually bought,
29:48
Andy Choens: So just one more application we're able to do to help them see that 30,000 foot view of what their practice look like, Andy Choens: All right, so that was my presentation Thank you so much for everything I put a link up there, I made the slides that I just went through publicly available there, am I get lab page and there you go for everyone who needed it you're obligated tori Arco junk, Rachael Dempsey (she/her): Thank you so much Andy I really appreciate your energy as well,
30:24
Andy Choens: I am the pirate are, Rachael Dempsey (she/her): You definitely, Rachael Dempsey (she/her): Well, I go over to the slide Oh, for some of the questions do you mind copying and pasting the slides into the chat or just that link there,
30:38
Rachael Dempsey (she/her): And just a reminder if anybody joined a little bit later, we do have a slide a link where you can ask questions to are up though other questions but Andy one of the most up voted questions so far is either our packages that helped with HR data wrangling, Andy Choens: hmm good question, Andy Choens: So that is something that I skimmed over when I went through the discussion around technologies,
31:07
Andy Choens: There it is I skimmed over that So what we actually do I did say that the technology provider that we use to help us do what we do is health catalyst, Andy Choens: What we actually wind up doing is health catalyst provides a lot of our backend services in terms of hcl, Andy Choens: And they have a set of tools that they have developed which we use to actually help us manage all of that complexity,
31:30
Andy Choens: And so what we actually do we describe our data warehouse as I, as a layered cake and our that first level of of what we typically do elt, Andy Choens: But we attract load and then later we do the transformations we use to help catalyst tools to actually do that initial,
31:48
Andy Choens: Export out of the hrs into the data warehouse so no, we are not using any our packages for that there are really good our packages to help you with diagnosis for beans and things like that that are useful, but, Andy Choens: If they're very well may be tools, where you're not used at this point, Rachael Dempsey (she/her): Thank you, Nicole, do you want to go back and forth me for the slider questions,
32:14
Nichole Monhait: yeah really um the next one Andy is about large data, how do you deal with large data sets greater than 100 gigabytes using our I tend to use SAS to do data wrangling, since our as limited by Ram size, is there a way to solve this in our, Andy Choens: So I guess, Andy Choens: The first question, That I would, Andy Choens: address with that is so, if you have very, very large data hundred gigabytes is pretty is pretty big,
32:42
Andy Choens: What are you trying to do with that, so the solution that I would suggest, if you are doing some kind of a machine learning model would be different than if you are trying to do some sort of summarization, Andy Choens: Because if what you are trying to do is say so practice management data is something that tends to scale up into the om D scale, because just think about how many appointments provider has in a day,
33:09
Andy Choens: You know i'm talking to a provider like one doctor and there's often more than one doctor and the site and we're working with over 200 sites, so our practice management data is large it's deep, Andy Choens: I don't usually need to do a machine learning model off of you know the full cohort of that data, so we actually do what I would recommend if this is a relevant,
33:31
Andy Choens: opportunity for you is to use a database server because yes ours memory down and but, if what I really need, for example, going back to this, Andy Choens: Our appointment trends going up or down that calculation of how many appointments are happening in the day, that is not actually being calculated and, Andy Choens: i'm actually offloading that through DVD player on to the database server and it's calculating the number of appointments per day,
34:00
Andy Choens: Are is only in this in the instance of this particular application it's having to graph a number of you know about 50 K it's it's a it's an integer, and this is the monthly views and there's only you know, Andy Choens: there's two lines there's only 12 months in a year, so at most 2448 you know data points so hundreds and hundreds of thousands of appointments, but I can SLIM it down to,
34:26
Andy Choens: 48 data points and ours, you really you can you can graph that on the pocket calculator So if you can use a database server I would recommend that if you can't, Andy Choens: There are virtually using virtual machines other job that i've done, where I needed to do machine learning models on very, very large data sets I used virtual machines, where I could actually have an arbitrary amount of Ram but there you have to have the budget to pay for it,
34:54
Rachael Dempsey (she/her): Thanks Andy and I am I meant to say this before, but if we're getting to anyone's question and you want to jump in and add any more context or follow up feel free to unmute yourself, it should let you do so, and if anyone has this too, so with that, let me know, Rachael Dempsey (she/her): But i've done, I know you had put your name there, and that was your question, so I just wanted to see if you had any follow up to, Manju Rupani: Something,
35:20
Rachael Dempsey (she/her): With your magic, Manju Rupani: Thank you Andy just wondering about this theater data is that accessible to anybody or you have to go through those capitalist was, Andy Choens: So, so the HR data, Andy Choens: To help me answer your question of what Where are you on the globe, so I can, Andy Choens: tell you what, let me just answer this like outside of Chicago,
35:47
Andy Choens: Okay you're in Chicago okay so so you're in the same healthcare regime, as I am, in terms of federal laws so in order to get access to the HR data, well, we actually wind up doing the very first step that we have to go through and, Andy Choens: Now i'm like gosh with some of the folks on like on the team that are doing this day to day we're we're here to help me with this,
36:08
Andy Choens: But the very first step is what we have what you'd have to do is get a da you actually have to get permission to access that data so obviously in America we have, Andy Choens: What we call pH I laws which very tightly control, who can have access to private health data, Andy Choens: And those laws are very important, and if you violate them there are very significant consequences may I suggest you do not violate those so the very first step is to get a da with the practice,
36:35
Andy Choens: And then, once we had that da with the practice and the doctor has to say acuteness help I am the licensing acuity is help to be a third party vendor and they are going to work with me to manage my ehr data that we reach out to their vendor, Andy Choens: All scripts cerner whoever and we start working with them in the details here it kind of depends on on,
37:00
Andy Choens: Who the vendor is and how that particular site has that tool set up and we start working with them on information exchange, Andy Choens: So that we can access that data so that's where we start getting into you know it might be an OTC connection and might be a flat file, what have you, Andy Choens: And then we were able to pull that down our data is,
37:18
Andy Choens: It is in the cloud but it's in a pH I grade you know the expensive grade of all DNS because no we can't just let people access that data, because obviously it's private we have information that, Andy Choens: People have the right to have quietly and keep private so that is data that hence why I had to be sort of careful and make you know,
37:39
Andy Choens: silly ccr jokes and you know him jokes throughout this presentation, because you know the actual spreadsheet of the hospital activity monitor I, Andy Choens: didn't want if I put it up here, it would have been two thirds, you know you skated out I would have had to have like made it really hard to breed so wouldn't have been much fun to look at,
37:59
Andy Choens: So I felt like it was better to approach this, but no, we have to be very careful around healthcare and data exchange within this world, which is good, but it also makes everything complicated did I answer your question, Manju Rupani: Yes, you did Thank you so much me, Andy Choens: Like I hope it wasn't rambling, Rachael Dempsey (she/her): insanity,
38:23
Rachael Dempsey (she/her): jocelyn I see you had just asked a question in the zoom chat and I wanted to pass the MIC over to you if that's okay to ask that lie, Jocelyn: Yes, thanks Rachel So my question is, how do you track patient's medical history when you look at their, Jocelyn: Service chart, Jocelyn: Because during the years patient could change their plans and have multiple patient ID or insurance plans ID So how do you track their medical history,
38:54
Andy Choens: That is a really good question actually so inside our platform we actually use an mdm tool called multi view and what multi view does and no tool of this nature is perfect, we have tuned ours to a place that we're very comfortable with, but is it perfect no will it ever be,
39:15
Andy Choens: No, but what this does is it allows us to connect so I mentioned that we work with, I believe, if we work with 11 different paragraphs multiple different provider groups, and so you mentioned the complexity of I went from, Andy Choens: Blue Shield to CDP HP insurance, for example, I some point I in the past, I used to have Blue Shield right now, I have to take insurance, so I have a new, Andy Choens: provider, a new pair ID on that some number within with Blue Shield,
39:48
Andy Choens: That was a record number with them, and I have a new record numbers, the php, which is obviously not the same, and yes, we, Andy Choens: Up to a point, are able to track people across those because we use this multi view that will go in and look at first name last name, date of birth, gender and a whole bunch of other criteria to try to gas that Andy and this data set is the same end as this data set, Andy Choens: We also have to be very careful about that, because there are,
40:18
Andy Choens: very complex rules around when we can combine that data and share it, and when we can begin, because we have to be very conscientious around privacy, Andy Choens: So anytime we start doing things that any any process that starts to walk across multiple data sets,
40:32
Andy Choens: We have to stop take a deep breath and really, really, really thinking through from a legal and privacy standpoint, to make sure that we're not doing something inappropriate but yeah we use a tool called multi view, to help us say, Andy Choens: The other part that can be fun that can be complicated, Andy Choens: Is you you as an individual patient over the course of your life will have multiple you know providers, you know just imagine as a simple example a kid,
40:58
Andy Choens: Who goes from having a pediatrician to eventually a family medicine practitioner, and that could be a multiple ehr so we're also able to, on behalf of the payer groups that will work with, Andy Choens: map that you know progression across different ehr systems, so we can say hey you know this is how that particular health care for this patient who has had your interns for all those years has been developing,
41:22
Andy Choens: But again that's something that both has both tactical and legal and privacy aspects to it, Jocelyn: Thank you very much, Nichole Monhait: awesome i'll take us back to the slack for the next year i'm sorry the slide over the next one, Nichole Monhait: i'm going to ask one that i'm particularly interested in the answer of Andy and it's are there other quick tools you've had to make and shiny like the appointment trends APP,
41:48
Andy Choens: Oh gosh yes, we were we generate shiny Apps weekly, Andy Choens: So things that we are doing in shining right now, Andy Choens: On a technical side, so I mentioned that we use that health catalyst platform and they have a number of tools that go through and do that html and all those jobs,
42:09
Andy Choens: We actually have been starting to develop our own shiny applications to help us manage the data warehouse so that we can better have better insight into what's running How long do those things right, Andy Choens: We have a series of shiny dashboards that we built that go beyond what the health catalyst platform provides out of box to help us meet our needs I related that not actually shiny but it's kind of fun internally we also use slack,
42:35
Andy Choens: Probably too much, and so, if you happen to work someplace that use slack you know understand the emoji hell that we've all been living in in the last 18 months, Andy Choens: um The other thing that we do is that we have our markdown reports and, for example, some of those are about our atl job so we actually have channels for our Devon prod environments at a one of the Members, Andy Choens: of our team was absolutely phenomenal she wrote in our markdown script,
43:03
Andy Choens: That runs every morning and it puts out a list of these are your jobs that failed last night, you need a human, to go look at them, and that is something that gets in dumped into nobody actually looks at it on, Andy Choens: Our markdown generator is actually ignored what we use is the side effect of it that gets shoved into slack,
43:20
Andy Choens: And we're able to read that it's in our communications platform and it's from an our script that's running in RStudio connect but it gets dumped into slack, which is where we live moment the moment, Andy Choens: And it says hey these ETS jobs failed and a human needs to go figure out why and fix it and every morning the the what we call the iot looks at that and starts figuring out how to make our to spend better,
43:44
Andy Choens: And then, in terms of the providers, we have a number and I couldn't go through them all in part, Andy Choens: I was told to keep it up a half an hour and we have so many shiny Apps we have things that are helping people with financial analytics we have things that are helping folks,
44:01
Andy Choens: With care management, we have a whole bunch of different things that we've been doing that kind of try to walk that gamut of data sources that we deal with so yeah shiny is a a very important part of what we do, as our static our markdown files, Rachael Dempsey (she/her): that's amazing thanks sandy and I know you had a few great questions that you had copied over to the slide Oh, and just wanted to pass the MIC over to you to have you ask those that's okay,
44:33
Toyin Ola: Certainly thanks Rachel yeah one question that came to my mind, and you are speaking about I think it was the ccr and identifying special populations as whether or not you ever incorporate data from like remote patient, Toyin Ola: monitoring devices that's something that any of the sites that you support us, Andy Choens: not yet, but it is something that I have been having multiple conversations with once a couple of the provider sites that we work with that are underneath,
45:06
Andy Choens: A single 10 their CIO and I have been having conversations about that and somewhere here depending I actually got, Andy Choens: I don't remember the plan they're gonna they're talking about implementing but actually bought, some of them devices, so I can start playing with the API because yeah we are trying to figure out how to do that and start actually doing that that is, Andy Choens: that that is something that is in the next,
45:34
Andy Choens: two to five years, I think, is going to be extremely exciting in this ambulatory space, I mean everything i'm you know, this is a garment a lot of people have apple watches just this like, Andy Choens: A The other day I was having a really, really awful day in the watch kept telling me that my blood pressure was up which the end result of that was like through the watch prosper and adulthood shut up but,
45:57
Andy Choens: I didn't need an API to tell me that I was stressed, but but being able to track that like being able to track heart rate and blood pressure, data, Andy Choens: and be able to start integrating that into ehr and via to connect all those pieces, Andy Choens: The The other thing that I was personally very interesting to me is cgm data so continuous glucose monitoring data for diabetes my wife is a type one diabetic,
46:19
Andy Choens: And so, she is a user a patient using a continuous glucose monitor and, Andy Choens: To be able to integrate that more holistically with her providers HR is something that I think is really, really interesting and if I manage to help be part of providing that that'll be very, very cool,
46:37
Andy Choens: But I would love to be able to provide that because you know the doctor is going to run an agency and say oh so this is colin's it looks like blah blah blah but but, to be able to then, and right now he has to go to a completely separate system, he has to log into a,
46:51
Andy Choens: separate system, and he can't put those two pieces together so yeah, I think, to be able to connect those is where ambulatory care has to get to quickly to really take it to the next level with patient care, Andy Choens: Sadly i'm not giving, Rachael Dempsey (she/her): Thanks Andy,
47:12
Rachael Dempsey (she/her): Another anonymous question was are you monitoring for outbreaks like respiratory viruses or micros that could spread easily in a hospital setting and what would be your latency on that, Andy Choens: So we are not doing that because, like, I was saying earlier, are what we are really focused on this ambulatory care so that would really be more of, Andy Choens: An emergency department, they would have that kind of data,
47:36
Andy Choens: Eventually, through the hie we would get that we know that would be something we would tend to just rely on the local emergency departments to use to actually track because, Andy Choens: Our providers aren't really doing that kind of testing, and the only way that we would even get that kind of outbreak data would be via the HIV is ambulatory providers aren't doing just routine testing that kind of stuff,
48:03
Andy Choens: We are doing some stuff to help the providers manage patients with Calvin so patients who have had coven and tested positive, especially in that transition of care, Andy Choens: circumstance, where they're coming they're being discharged from an Inpatient stays doing a coven we are highlighting that for providers,
48:23
Andy Choens: Based on based on the messaging so that they know, and can you know provide appropriate transition of care of follow up care for those patients, but the that type of Community outbreak monitoring is pretty it's out of scope for what we do, Rachael Dempsey (she/her): Thank you, Nicole turn it over to you for some of the other questions, especially because you have the EPI background and will say things much better,
48:49
Nichole Monhait: I don't know about that original but sure i'm Andy there's a little bit of a conversation that's been spanning the chat about practice data sets and how to get your hands on a data set where you can, Nichole Monhait: play around with our and do some EPI related work but not ah, I do you know any data sets or any sources that people could use, Andy Choens: So this weird timing on that one, so in my in another part of my life i'm an adjunct professor at,
49:21
Andy Choens: The Albany college of pharmacy and health sciences and I have been wanting to enter that for my students, because what i've been wanting to do in the spring semester is actually provide them with an ehr that's all fake data, Andy Choens: So the call, I think you guys had said that you were going to put out a slack channel, Andy Choens: Yes, I am blanking on the name of the ehr but I will actually put out a,
49:46
Andy Choens: Something i'll put something into that slack channel because I found an open source ehr that you can spin up, Andy Choens: And one of the cool things that they actually have is they have a sequel script that would in a mysql database would actually allow you to generate, Andy Choens: it's anonymized data so that you can actually have your own your own private ehr to kind of play with and experiment with, and it would be running in a database server that you would control,
50:12
Andy Choens: So that yeah that's actually something that i'm i'm actively pursuing so once I can tell that story i'll try to work on the here in the next couple nights and i'll try to put like out some instructions for how to do that because, yes, that is definitely possible, Nichole Monhait: awesome thanks Andy, Nichole Monhait: um, Rachael Dempsey (she/her): yeah just needed someone but yes ask a question and the audio is going in and out,
50:46
Nichole Monhait: Was there a question that someone wanted to to ask, I can go back to the slide Oh, if not they'll give a second in case that person wants to come back and try again, Rachael Dempsey (she/her): Robert I think there might be an issue with your audio, but if you want to put it into the chat we can ask it to, Rachael Dempsey (she/her): Or we can go to one another, from the slide oh first to,
51:14
Nichole Monhait: yeah i'll ask us a question and we'll see if that question comes through um what kind of features might your team engineer about a single diagnosis, for example, if someone had an icd 10 code associated with diabetes in the last three years, Andy Choens: So someone, Andy Choens: What would we take me what the what would we do part again, Nichole Monhait: What, Andy Choens: I got out of the details, Nichole Monhait: The question went away, but it was,
51:42
Rachael Dempsey (she/her): I was, I was marking it as an answer it as we went through, but it was what kind of features might your team engineer about a single diagnosis, for example, if someone had an icd 10 code associated with diabetes in the last three years, Andy Choens: Okay, Andy Choens: So,
52:05
Andy Choens: that's it what feature if we're by using the word feature i'm assuming that we're talking about machine learning models at this point, which is awesome um the answer to that is going to be really dependent, Andy Choens: On what the question obviously what what is the question that we're, Andy Choens: Trying to answer some things that we have done, for example, and diabetes is a feature in this model is things like,
52:29
Andy Choens: What are the odds are machine learning model trying to predict the risk of reading readmission to an impatience day after discharge, so we have a readmission risk model, Andy Choens: And you know, chronic diseases play a part of that model because people will buy some you know, chronic diseases are more likely to be, Andy Choens: sick and therefore more likely so that would be an example of something where we would use something like a diabetes diagnosis and even more importantly,
52:55
Andy Choens: Things connected to their a one see, because that would help us understand if it was a diabetes related, Andy Choens: In patients day or not so things like that would be using a model to help predict something like a readmission risk other things that we have been starting to work on, Andy Choens: are trying to, for example, understand disease progression, so you, for example, had quite the person has been the question started with a diagnosis of diabetes,
53:21
Andy Choens: If you have diabetes and the question is going to become what it what, Andy Choens: types of neurons these are you likely to develop, so what types of complications, are you likely to develop and when how long is that progression going to look like, Andy Choens: The other side that we're moving more active on is actually diabetes becoming the, Andy Choens: output, the consequence is trying to go so here are our patients pre diabetes, of all those that we know who have pre diabetes,
53:47
Andy Choens: Who are the most at risk of becoming diabetics in the next three to five years so it's I know i'm flipping the question on its head, Andy Choens: But that is this idea of disease progression being going up to diabetes and actually formally diagnosed with diabetes, Andy Choens: Pre diabetes and then, if you have diabetes, you know, initially, you would have if you develop diabetes in that regard your Type two,
54:09
Andy Choens: And so you'd have uncomplicated type two diabetes and, eventually, as the disease progresses that those patients are going to start developing you know, Andy Choens: It can impact your kidneys and can lead to chronic kidney disease things like that so there's opportunities and modeling around who is most at risk for things for consequences of that what diabetes and any chronic disease, the, Andy Choens: Asthma what have you can have no side effects that are our holistic system,
54:41
Rachael Dempsey (she/her): Thanks Andy as we get to the top of the hour, here I know some people might have to jump so I just want to have Nicole give another plug for the slack channel as well, because we can answer some of the unanswered ones there, Andy Choens: yeah that slack channel so i'll happy to continue the conversation, Nichole Monhait: yeah so i'm going to drop the link in the zoom chat here, and I think we'll be able to share it,
55:05
Nichole Monhait: After the fact, as well, somehow, but any questions that didn't get answered or that you think about after the fact, feel free to throw those in the slack channel and Andy has told us that he will tell us more about the practice data set question, there too, so i'm dropping this link oops, Nichole Monhait: Not the zoom link, I have to find the slack link i'm dropping the slack link in the zoom chat now, Nichole Monhait: And we can continue any discussions over there,
55:35
Rachael Dempsey (she/her): awesome and if anybody wants to unmute themselves and ask a question live now, I also want to give everyone the opportunity to to do so, Rachael Dempsey (she/her): I could take unmute yourself as raising your hand, Rachael Dempsey (she/her): hey, David (Boston - LinkedIn/in/DavidGabbe): hey Rachel Andy really interesting presentation, David (Boston - LinkedIn/in/DavidGabbe): So what's so it's a little,
56:02
David (Boston - LinkedIn/in/DavidGabbe): unclear to me is how do you measure how successful, David (Boston - LinkedIn/in/DavidGabbe): Your activities or your your products or shiny dashboards aren't, Andy Choens: Oh good question and that one is ultimately a, Andy Choens: PR I have a really simple you know there's a there's a cop out answer I could say, well, people that asked us for us tell us they like it that's a cop out, Andy Choens: Answer i'm,
56:31
Andy Choens: A better answer is so with as in this is actually connected to why we have been trying to convert more of our tools to shiny, Andy Choens: So if I send out, you know here, it was earlier, apparently, I drew a little my screen I didn't even notice that, Andy Choens: sorry about that um but, but you so we have that idea that ccr report or the ham report, those are email reports,
56:55
Andy Choens: And you're actually right in that I, or I suspect right in the I don't know if someone opens up the ccr I it's it once it goes out as an email, Andy Choens: assuming it doesn't get rejected, and we do track that so that we can follow up with Okay, why is this email address not work anymore,
57:11
Andy Choens: We don't know if someone opens, so we are reliant on so I represent the data science team at acuteness we do have what we call practice intelligence team that has constant communication with our sites, Andy Choens: You know they have regular touch points with them when they talk about the tools we get some feedback that way, but one of the things, Andy Choens: we're in one of the big driving reason for why we've been trying to go, Andrea: More and more in terms of use shiny,
57:35
Andy Choens: Is because there we can better actually say hey, Andy Choens: This is how many, Andy Choens: User people actually use this this is how many, Andy Choens: You know people were able to go in, Andrea: With that, Andy Choens: and other cases with things like, Andy Choens: Following up on transitions of care we've actually been able to do some very some you know starting to look at analyses, where we start saying, can we bend that curve and start,
57:54
Andy Choens: Increasing the number of primary care visits to happen after, Andrea: A discharge but, Andy Choens: But a lot of it is going to, Andy Choens: Be what I would call process measure, Andy Choens: Where we're trying to look at you know people utilizing the tools emotional anyone not and shiny is way way way better for that than me an email itself,
58:13
David (Boston - LinkedIn/in/DavidGabbe): that's that's really interesting because as as somebody somebody who goes to a doctor, I would have thought the answer might have been, David (Boston - LinkedIn/in/DavidGabbe): there's like an improvement, Andrea: or at least not a degradation in, David (Boston - LinkedIn/in/DavidGabbe): You know, Andrea: Some key lab tests, David (Boston - LinkedIn/in/DavidGabbe): You know, for for patients who have specific kinds of, Andrea: Conditions,
58:35
Andy Choens: mm hmm and, Andy Choens: depending upon what the intervention is that might be I guess we're doing a number of different things, but, Andy Choens: If, Andy Choens: You are, for example, I know there are a couple of providers who are targeting diabetes, Andy Choens: So there we would be able to use a Wednesday as as a, Andrea: As a proxy, Andy Choens: For any kind of an impact, but in other cases, Andrea: You know, because, Andy Choens: And this is sort of the funky part about this,
59:08
Andy Choens: That ccr or the, Andy Choens: One of the terms that I use is at the, Andy Choens: point of it is to is to democratize the data, Andy Choens: And one of the honestly in a way, Andy Choens: Unfortunate side effects of that is I don't always know or have transparency into how providers are using it, so I don't know necessarily to lock, so a doctor can get that chronic conditions report you go out I got this thing i'm going to target diabetes,
59:36
Andy Choens: I don't care about that that I don't even know to, Andy Choens: follow that up because, Andy Choens: In order to get that list, Andy Choens: of patients, they want to go, do you know work with they don't have to ask me anymore, Andy Choens: i'm almost at a way we've cut ourselves out of the loop, and so they can go do that thing and we don't even know to look so, Andy Choens: Like monitoring,
59:54
Andy Choens: lab values across all lab values across all sites looking for signals is guaranteed to be you know lead you down the path of of false signals so yeah in a way, they would have to come to us and say hey you know we'd like to, Andy Choens: work with you on a program, Andrea: and Andrea: You know,
1:00:11
Andy Choens: Improvement Plan and evaluation to see if this is effective and then, absolutely what you're saying is true if someone comes to us and says i'd like to do this, can you help me track the outcome, then we will start looking at appropriate lab, Andy Choens: values that might be proxies for a chanel, Andy Choens: But they could also do something, Andrea: Without even telling us, David (Boston - LinkedIn/in/DavidGabbe): Okay amen,
1:00:36
Rachael Dempsey (she/her): Andrea or Andrea guys, I see that you're unmuted as well, and he wanted to give you a chance to ask your question, Andrea: Oh, Rachael Dempsey (she/her): I can't hear you, Rachael Dempsey (she/her): Yet, Rachael Dempsey (she/her): But if you have an issue with the audio you feel free to use the chat to, Rachael Dempsey (she/her): Nicole, do you see any other questions that we haven't really touched, eugene: Upon yet,
1:01:08
eugene: Can I ask a follow up to the diabetes modeling, Question buyer, eugene: So the there were two sort of, Andrea: potential applications you, eugene: said, like, for example, readmission risk, or, eugene: The likelihood of complications, given the fact that they, eugene: Have diabetes, or some other icd 10 code fill in the Blank or, eugene: If you know that one of the most important predictors, for that is some kind of metric that let's say comes from a blood panel or,
1:01:38
eugene: White blood cell counts, or something along those lines is there an implementation of this model and sort of like an iterative loop where the physician who sees this patient will know or have an action item to get the blood panel to, eugene: Best predict whether readmission is highly likely for a patient at a later date, you know, is there a feedback loop sort of to make sure patient outcomes improve, Andy Choens: yeah that could be that is something that we could implement um,
1:02:07
Andy Choens: That would most likely already be driven unless we came up with some sort of a novel lab you know correlation that's probably already going to be driven natively by the ehr, in which case we would just, Andy Choens: offload that to the HR to driving them getting that lab completion and all of that getting those results into the ehr um,
1:02:31
Andy Choens: But no you're what you're saying absolutely makes sense, one of the things though you use the word that is worth highlighting, which is feedback loop, Andy Choens: And one of the things that we are very conscientious about doing anytime if if it's a tool, or a model or anything else is involving the provider so so not only would they know,
1:02:52
Andy Choens: provider ask us for some sort of a model or something like readmission risk, but we would also have those people involved in the development of the model because, Andy Choens: What we have found is not only does that increase the trust in the model, it also gets people to really start using it, because anytime you have a model it's a model it's not reality it's not perfect,
1:03:13
Andy Choens: And having them having those providers involved, from the very beginning in terms of that feedback loop of talking about what this model is, Andy Choens: help them get the understanding of what is the model right one is the model likely a little bit off, you know what are the weaknesses of that model,
1:03:28
Andy Choens: So, having a feedback loop on any data science project back and forth between those domain experts and the people doing you know the data science and the technical side is critical, Rachael Dempsey (she/her): Thanks Andy I know we're about 10 minutes over so I just want to be respectful of your time, especially you have to if you have to run to another meeting to, Andy Choens: Go do you have a one that I need to get to hear that oh boy, Okay,
1:03:56
Rachael Dempsey (she/her): So thank you so much, I know there's a few other unanswered questions is okay if we just ask you one last one, which was had it, I see this one i've been uploaded, how do you suggest, our users normalize our use when so many people are using SAS or spss, Andy Choens: fun washing I have been accused of doing this, a, Andy Choens: Our advocacy is something I have been accused up before,
1:04:25
Andy Choens: So what I would actually say is um so previously, I worked at the New York State Department of Health and we had an organization within that it was called ED calm, Andy Choens: which was epidemiology and biostatistics community of practice, you know because there needed to be another acronym in healthcare,
1:04:42
Andy Choens: And within the bounds of E commerce, but I was able to start doing we're starting a conversation around both are and ultimately also version control but but trying to like start talking about how it could be used, Andy Choens: Ultimately, having a new language is a little bit different than, say SAS if you're in a SAS shop or an SPS shop or what have you,
1:05:04
Andy Choens: Having ultimately a champion, who is in some form of a leadership role, you know start identify, I would say, if you are in a leadership position, and you have the opportunity to start pushing that conversation, Andy Choens: Otherwise, it helps to have someone who's in a leadership position is open to the idea, you know, maybe we can do some things that are different, maybe we can do some things that are,
1:05:25
Andy Choens: You know, can broaden our horizons here in terms of the technologies that we're using and get that champion and we were able to use this idea of ED calm, Andy Choens: As sort of that proxy for that champion and we started getting people to talk about it, we started holding workshops on doing are and how to get people up to that those skill levels and working with,
1:05:44
Andy Choens: The Department of Health it to get our installed on people's workstations so that they can actually start using our, which is how we were able to make some headway there in a place that is has a lot of sass users, Andy Choens: But yeah I think having a process where you have both a champion and a process to start enabling people is are both going to be the two critical steps for that that's awesome,
1:06:07
Rachael Dempsey (she/her): Thank you so much, any I know you have to run to your next meeting, but really appreciate you sharing your insights with us and answering everyone's questions i'm excited to see that slack channel grow too, and we can answer some of the unanswered, Rachael Dempsey (she/her): To, Rachael Dempsey (she/her): Thank you for the good, Andy Choens: really good questions, Rachael Dempsey (she/her): Thank you all for joining as well, have a great rest of the day,
Here to help you learn
Sign in to keep a private conversation with your course tutor.
Ask me anything about the material…
Sign in to chat