Optimizing Constrained Resources with LeanTaaS CEO Mohan Giridharadas
Episode 19512th March 2020 • This Week Health: Conference • This Week Health
00:00:00 00:32:18

Share Episode


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

 Welcome to this week, health events where we amplify great thinking with interviews from the floor. You keep listening, so we'll keep producing Hyn shows for this year. Special thanks to our channel sponsors, Starbridge Advisors Health lyrics, Galen Healthcare, VMware pro talented advisors for choosing to invest in our show.

My name is Bill Russell Healthcare, CIO, coach, creator of this week in health. It a set of podcast videos and collaboration events dedicated to developing the next generation. Of health leaders, you know, it, it's crazy. But the with, uh, with all the news this week, um, we haven't looked at the steady and even accelerated progress of things like machine learning, predictive analytics, and ai.

Among the great advancements that are going on today, though, we're gonna do that. I'm joined by, uh, Mohan, the founder of, uh, and CEO of Lean Toss and Mohan, I apologize for not saying your last name, uh, because I, I don't wanna do a disservice to you by doing that. But we're gonna address some of these really cool tools for, uh, optimizing the utilization of expensive and constrained hospital resources.

So, uh, good, good afternoon, Mohan, and welcome to the show. Thank you both. It's nice to be here. Yeah. I, I appreciate you coming on. You know, one of the things I miss about not doing this show this year is walking through the booths and having conversations with people like you, uh, who are showcasing, you know, real solutions that, uh, are really gonna change the way we approach age old ways of doing things.

So, let's just start there. I mean, give us an idea of what it would've been like if I had come up to your booth. What, what would you guys be talking about and what, what would you be showcasing? Great. Lean tasks helps patients get improved access to the health systems by opening up access while simultaneously allowing healthcare systems to reduce the cost of healthcare delivery.

We do this by sophisticated algorithms that help match the demand for care with the available capacity for providing that care. It turns out this is a very complicated problem mathematically because. On the demand side, it's almost impossible to predict how many patients will need care for what type of treatment many days into the future, how long it'll take, and all of the other variables around it.

So on the demand side, it's highly unpredictable and highly volatile. On the supply side, it's highly constrained and highly interconnected. So for, for example, to deliver an infusion treatment. You need the chair, the nurse, the pump, and the drugs to all be available at the same time in the same place.

Those are hard to predict. Therefore, getting the supply demand curve to match is a very hard match problem. And we've spent four years and tens of millions of dollars solving it, and we now have a 200% company dedicated to doing just that. Wow. You know, and uh, usually with these shows, I have a bunch of notes, but we're literally doing this as if I just walk up to your.

To your booth, and so, uh, you know, give so expensive, highly constrained, uh, spaces or equipment. So what, what are we talking about? What are, what are the areas that you guys are focused in on? So, our three commercially available products are iq, we call the entire product family iq. Um, and our first product was IQ for infusion centers.

We optimized the delivery of infusion treatments largely for chemotherapy, but non-oncology, chemo, uh, infusions as well. We currently are contracted with 300 infusion centers controlling about 7,000 shares, which is well over 10 or 15% of the infusion capacity in the United States. Our second product is IQ for operating rooms.

That product runs:

On the drawing board. We've got IQ for inpatient beds, which we expect to launch by the end of this year. Uh, in fact, we are in alpha trials with minimum viable products being launched even as we speak. Uh, and we've got other plans on the table for things like, uh, radiation oncology imaging and phlebotomy labs.

You know, this is a really, this is really pragmatic solution. When I think about it, I, off the record, I had a conversation with a, with ACEO. And, uh, I was saying to him, if I could do one thing for you, what, what, what would it be? And he goes, fill my, or for every minute of the day, , she said, that would, that would help me immensely because it, it alleviates my, my cost problem.

It alleviates, it generates a lot of revenue and we're able to do a lot of the things that, quite frankly, create constraints. And so that, that, or those infusion centers, those clinics, I mean, keeping the throughput. Uh, is so critical for these health systems. Are you finding a, a pretty good, uh, response from health systems as you have conversations around these challenges?

Yes, we do. Uh, it takes a while because I think the reality is people have just accepted that this is just the way life is. We all accept that if you drive downtown during rush hour, traffic is a lot and it'll take you longer to there. Similarly, health systems have just come to accept. The infusion centers are crowded in the middle of the day and patients will need to wait.

The ORs will be short and we'll need to run into overtime and have, uh, extra anesthesiology teams and nursing teams late into the night. So people just accept that this is a reality because they understand it's a very hard problem. What is eye-opening to them is realizing how elegantly and, you know, and, and in a sophisticated manner that this can in fact be solved.

If you step back a minute and say, think about how every appointment in a health system is made, two people chat. It could be the provider and the patient, the provider, and the scheduler. Or the scheduler and the patient. Three, two people chat. They look at the calendar and they say, bill, Wednesday, 10 o'clock, whether it's for your procedure or for your infusion, or for your doctor's appointment, they looked at the calendar and they made the appointment.

There was no math involved in that decision. Nobody ran the stochasticity of the demand signal or the constrained optimization availability of the supply elements into it. They just looked at the empty calendar. This makes as much sense as Imagine Bill. If you and I were solving a jigsaw puzzle and we sitting near an empty table, we pick up a puzzle piece and I say, Hey Bill, where do you wanna put this piece?

And you say, that corner of the table looks empty. Let's go put it there. And we do that with each piece as we go through, right? What is the chance that the puzzle is solved when we are done with the pieces? Zero. Why? In this model, each puzzle piece is like a patient, and the empty table that we started out with, which becomes full as the day progresses is the calendar upon which we are making appointments.

So just as we would not be surprised that the puzzle doesn't solve, how can we expect that the bolus of patients that were picked on any given day actually makes sense in terms of who needs to come in what order for what service? So there was no optimization in there. When we challenge health systems with that, they get it and their first reaction is often, well, it's hard to predict the demand and the supply is uncertain, and people don't show up on time, and nurses call in sick and pumps are out of service, and robots go down.

And so things happen. And so our comeback to that is, sure. Let me give you an example where it works. Think about Uber. Uber has no idea how to predict the demand, right? Because in the last month alone, I've taken an Uber in New York, LA, and in South Dakota, and I don't live in any of those places. So the demand is, is hard to predict.

The supply is even harder. The drivers don't even work for them. These are freelance agents who wake up and decide to drive today or not drive today. So what does Uber do? It builds sophisticated math models. It has continuously modeled demand for cars in every zip code, every minute of every day, everywhere in the world, and it factors in whether time of day, political events, sporting events, et cetera, and therefore gets a really accurate demand signal.

Then it looks at the driving pattern of all their drivers and figures out who drives when and where, and it tries to match the demand and signal, uh, supply signals. When they're off kilter, it proactively pings the drivers and tells them to come out for higher incentive or to drive west six blocks, or to drive north six blocks, just to start getting to where the action is.

If the demand is too high, it does search pricing, so it does crazy mathematics with dynamic realtime adjustment and machine learning to get the supply demand signal to match in a world where the demand is volatile and the supply is unpredictable. Healthcare can do that. And that's kinda what we've done.

So that's interesting. So every client you go into, you're gonna have to build that model out. So you come into my health system and I say, yeah, let's, let's definitely do this for or, and infusion centers and we'll get, we'll get going down the road. Uh, this is where machine learning comes in. You're gonna take a whole bunch of historical data and run it through your algorithms and essentially come back with, with models that work for my health system.

Is that how it, is? That how we're gonna stand this up? Yeah, exactly. Uh, and the beauty of what we've done is it's one code base. It's a multi-tenant SaaS product that runs in the Amazon cloud. We sure we configure it for every health system, but this is not a customized solution built for each health system.

So let's take infusion as a starting point. Uh, that's an easier one to explain and then I'll switch to or and explain how that works. So for Infusion, we start out exactly as you said, bill, we take historical data. From the historical data, we build very sophisticated forecasts of the volume of patients.

By day of week, infusion is the day of week, Gabe, because different oncologists practice in different days of the week and they tend to have a different propensity for sending their patients onto infusion depending on the kinds of patients they have at the disease group, they that they cover. And so we predict the volume.

We then predict the mix. How many patients are gonna need a one hour treatment, a two hour treatment on a Tuesday, on a Wednesday? Having predicted the volume in the mix, we grade the accuracy of that health system in estimating the duration. How do we know we've got the historical data, so we've got a thousand instances where they told us it was a three hour appointment, and so we can construct the bell curve of how accurate they are around the three R prediction.

Based on that, we adjust the expected duration of each appointment. Having done that, we then have constraint based optimization algorithms that factor in hours of operation, shared availability, nurse staffing, nurse roster, nurse coverage, nurse specialization, uh, pharmacy hoods, pharmacy hours, pharmacy distances.

We factor all of that in and come back with a suggested template. So no longer is it, open up the calendar and first come first. Serve free for all. Give them appointments. Dialogues, which is slightly to Mr. Russell, I see you need an appointment on Wednesday. Your treatment calls for a three hour infusion on Wednesdays, I can offer you a three hour infusion at 7 10, 7 40, 8 20, 8 50 or nine 30.

Can we make any of those work? And so by steering very intelligently and very gently, it doesn't damage the patient experience. Patients in every walk of life are used to this concept of, let me ask for the time I want. And the, the, the facility will adjust and give me the closest they can do that, and I'll live with that.

This is true when you go get a haircut or make a dinner reservation, we take that optimization and put it back into the ehr. It's interesting. So how do you, how do you factor it? There's two factors I'm, I'm struggling with here. So, uh, equipment failure and uh, staffing. And again, I guess you're looking at historical data, you know that things fail at a certain rate and you know that people don't show up at a certain rate and patient's not showing up at a certain rate.

So you just, you factor that into the algorithms. Uh, but, but again, it's complex. It's not as simple as just saying, well, X percent of these people aren't gonna show up. You, you really?

Is we run discreet event simulation algorithms because we've got historical data, so we know what they were aiming for and what they got. Now we don't know why people are running late, whether the Starbucks line was backed up or there was no parking in the hospital that day. But we just know their propensity to run late for every minute of every day.

And so we build our templates to be resilient. So our templates have shocks built into them because we expect. Stuff will happen, patients will be late, nurses will call in sick, et cetera. So we expect all of that to happen. Having built the resilience schedule, that's like your best shot. That being said, stuff will still happen, and when that happens, we can guide them.

So for instance, if a nurse calls in sick, you can take one nurse out of the roster for the day and rebalance, uh, your algorithm. So we allow dynamic real time support. What's interesting is we don't need to get dragged down into the. Nuances of each patient. John does go to, got a comorbidity, and so when it's a three hour chemo, it'll probably take five hours for John.

We don't need to do stuff like that, uh, because we built our schedules to be resilient. The easiest way to explain it is the following. If you've gone onto Google Maps right now and said you need to drive from New Jersey to Manhattan on Monday, pick it up April 15th, or whatever that, that date is way into the future at 8:00 AM Google Maps will predict how long that drive will take you.

Now it has no idea who's gonna be driving on that day. So it's not trying to adjust its algorithm saying, oh, Bob's driving. Bob's a slow driver, and he hogs the middle lane, so I better add 10 minutes to the commute. It's not doing any of that. What it is done is it's done probability event distributions for every 0.1 mile of the journey.

It gets some right and gets some long, it gets some short, but because the mathematics is robust, it's able to give you a remarkably accurate forecast, even though that's 20 days out from now. Does that make sense? Yeah, that makes sense. I, so I wanna ask, ask you about, uh, you know what, so let's assume I, I implement this within my health system.

What kind of returns are we looking at? What are, what are health systems finding in terms of those, those constrained resources? So, uh, it varies by product. So for infusion, we are finding the returns are on the order of $20,000 per chair, per year. So we build our products to have anywhere from a five to a 15 times return on investment.

So we want to make sure that it's a complete no brainer from an economic standpoint for the health system. And in fact, we are so confident we do two things that just throws health CIOs, uh, you know, uh, by surprise catches them by surprise. The first is we guarantee the product if 90 days after the go live you're not feeling it, we'll return all the money you've paid up.

They've never seen that from any IT vendor that they've ever dealt to. That's true. The second thing we do is we tell our customers that we do not confuse customers with hostages. You do not need to sign a multi-year contract and be locked into something that's not working for you. So all our contracts are written with a cancel anytime.

So even after the refund guarantee period is gone, if you feel that the impact is, you know, uh, flattening out and you could do just as well without it. Cancel, churn as close as it's possible. Every single day, every one of our customers had the right to cancel their contracts and chose not to, and day after day.

ive years, and so they've had:

By the way that sales, uh, uh, the way you're going about selling to health systems, that's, uh, as unique as I've ever heard. Um, and, and really kind of, kind of fascinating. I mean, you've taken all the risk out of me, uh, at moving down this path or introducing you to. To my clinicians to, to see if this is a great solution for, for our system.

I mean, what's the risk? The risk is, uh, the time I guess, spent on doing the pilot if nothing comes of that. But I, I assume you also have a, a fairly good, uh, list of, of ref re referenceable clients that are, are seeing these kinds of returns. So there's almost no, no risk in the sales process. It's no risk, uh, at all because, and we understood that this is a bit of a disruptive technology.

It's going to surprise health systems. Therefore, we needed to, uh, put into place all of these things in terms of the time invested on their side. We've minimized that as well. We've built the scripts to, uh, to drive the data extraction. We don't need integration with the EHR. We, uh, are HIPAA compliant and SOC compliant.

We mostly don't need PHI and so we've eliminated the security risk, the implementation risk, the implementation effort, the financial risk. So we are de-risking it as well as we can. On the referenceability side, we've got the who's who of institutions. So if you start down the academic medical centers and you rattle off the names of the academic medical centers, you respect more starting on the east.

Columbia. Cornell, Johns Hopkins, UPMC, Penn, duke, Emory. Come down to the middle of the country. Northwestern Rush, MD Anderson on the West coast. Uh, Colorado, Utah, Seattle, cancer Care, UCSF. Stanford, U-S-C-U-C-S-D, uh, are all customers, many non-academics as well. Uh, dignity. Prior to the merger with Common Spirit, deployed our OR product across 39 hospitals, 255 ORs, many, many systems.

Have deployed the OR product across their entire, uh, you know, asset base Duke across all 110 ORs, uh, Oregon Health and Sciences across all a hundred plus ORs. Similarly with uc Health. Uh, and so we are getting system-wide deployments of our product, of each of our products, and they usually start with a narrow field.

So Sloan Kettering on Infusion started us with one center. We now run holiday centers similarly with MD Anderson. Duke started us Big Bang across all of their ORs. And so we are open to whichever way we structure it. Wow. So, um, and this is how these conversations usually go with, with me in the room. It's, you know, it starts with, Hey, this is what your product does.

I get it, the sales model makes sense, all that. But then I, I come back and say, does your product help me do some other things? So it's, it's interesting. You're really looking and optimizing that calendar. But can you come back and help me to optimize my maintenance schedules around, uh, specific equipment or scheduling of resources for those, uh, infusion centers and ORs?

Can we do it in reverse and sort of start to, to design better? We could do some of those, and those are natural progressions of what we are talking about because right now we are optimizing the asset by matching the demand and supply signals. Improving the supply by, uh, making greater availability of the pump or the robots, et cetera, is a natural extension.

But at the moment, the reason we aren't doing that is that starts to limit scalability because now suddenly you have to deploy your team at each institution to work your way through. What are exactly the equipment, supply chain issues, what are the exact maintenance regimens in place, et. We are building our product to be scalable SaaS products.

So for instance, our infusion product is now already live in 180 infusion centers in 120 of them. We have never set foot on the property even once, right? We've gone live in 120 centers without set setting foot on the property. So we've sold the product over a WebEx. We've done the setup over a WebEx series of WebExes over a six to eight week period, and we've been live and supporting them every single day for many years now.

For example, we've got a client in Montana, and I've never in my life set foot in Montana, let alone, you know, on, uh, on this particular location. And so, uh, this, this is a, a goal for us to make it scalable and therefore we are very judicious about where exactly we extend the process improvement mindset, because that immediately goes down to.

Facility by facility deployment, which, uh, uh, which limits scalability in a pretty dramatic way. Yeah. And you've just addressed, you know, the last, uh, challenge, which is, you know, when you talk about somebody like Dignity or, uh, some of these other systems, I mean, you're talking about, I. National deployments so you can, uh, because you've chosen to focus in on that, that one area, which is an acute problem within health systems, and you've decided to just focus in on that problem.

You've created a very scalable solution across the board. Uh, you know, to be honest with you, I mean, if I'm walking through the booths, I see all these things. I'm seeing referenceable accounts, I'm seeing, uh, a solution that, that, uh, is really going to help me from an operational and a cost standpoint. I see very little risk in implementation.

Uh, you know what? What's the problem? I, I, there's, there's part of me that's a pessimist and I'm like, there has to be something here, something wrong, and, and I, and I'm not seeing it. So probably what I would do is just pick up my, pick up the phone, call some of those academic medical centers where I know some of the CIOs and just have a conversation with them.

he OR product was launched in:

It's about building a nationwide scale, you know, sell, uh, Salesforce that can scale and uh, and position it. And that's kind of what we are in the process of doing. We haven't talked about the, OR product, lemme give you the two minute version of what the OR product does, right? Sure. So what has historically happened is every health system, and I'm sure you're well familiar from your CIO days.

Has block schedules in place, and the reason they have block schedules is surgeons and service lines need a guarantee. I'm a surgeon. I get Monday and Thursday blocks, so I know I've got two full day blocks of an or available to me. And so all the patients I see when they need surgery, I steer them into a Monday or a Thursday into the future into one of the blocks I've got.

Okay, so now let's just think of that from a supply demand perspective. What we've just done is create static pre-allocated reserved supply. Think about the demand side. The demand side is crazy volatile. In order for me to fill a particular Monday, eight Mondays out will depend on all the patients I see in my clinic.

What percent of them will need surgery, what percent of them need surgery that fits a following Monday or a Thursday timeframe, and what the lengths of their procedures will be and whether all of them will add up to be exactly the eight hours I've got. There is no chance of all of that falling in place.

And so what happens with blocks is blocks are reserved. Surgeons are still looking for time and they scramble and at the last minute they do add-on cases and emergent cases, which are not really add-on, are not really emergent. And so it throws the whole resourcing of the health system, uh, you know, into a bit of chaos to trying to match supply and demand of an OR or capacity is precious.

It's $300 a minute to, to have an OR. And so to have it allocated in this rough map, sort of a static supply, uh, doesn't make a lot of sense. So all the efforts in improving utilization rely on trying to cut down this minutes of, we call it grains of sand, first case on time, starts, turnover time, et cetera.

Those will save you five minutes here and 10 minutes there and 20 minutes, uh, in another place. That's great, but you can't squeeze in a case in those. So instead of starting 20 minutes later by started on time. Nothing really changes. All that would happen is that end 20 minutes earlier than I otherwise might have.

You've just shifted the entire day forward and back. You haven't effectively raised capacity. What we've come up with is a patented concept called collectible time. We are able to mine the patterns of surgeons and figure out who leaves large blocks of time, either in the mornings or the afternoon. Who releases blocks systematically ahead and above, above and beyond what you should normally recommend.

Who cancels and abandons blocks from that we can reallocate blocks more efficiently to surgeons and service lines, even if when that's done. In the moment, the match won't happen. And so what we've done is we've created a concept like open table for open time, which matches the need for you to get a dinner table with the restaurant's avail, availability, and ability to offer you a table for four.

So we've created exchange, which allows surgeons and service lines with two clicks on their mobile phone to request a block or get a block. University of Colorado Health. When we started with them, said. We are 95% blocked out. We have no room for new surgeons. By deploying exchange, suddenly you created a liquid marketplace where a new surgeon who had been brought onto the faculty could ask, put up their hand and ask for a time in the or and somehow it would arrive.

They recruited 11 new surgeons who built viable practices without having guaranteed block out. So the power of things like that is enormous. The product also helps people, uh, you know, get the analysis on their phone. They can drill down into how they perform, what the causes of delay were, et cetera.

Whereas historically, they just get a bunch of PDFs once a month that nobody looks at. Yeah, it's amazing. So it's IQ I-Q-U-E-U-E. For those of you who are, listen, listening 'cause um, and infusion centers, operating rooms and clinics. What's, what's, what's next? I mean, what, what are people pushing you or asking you for?

Uh, because I would imagine there's, there's other areas that health systems would like for you to, to do. Health systems are really concerned about beds, inpatient beds, uh, virtually every urban hospital is running flat out 9% bed utilization, and for periods of the day, 110% bed utilization, which means 10% of the people don't really have beds.

So they're in hallways, they're backed up in the PACU or, or somewhere in the system. If you compare what happens to an inpatient bed versus what happens in a, in a hotel, so. Guests check out in the morning. There's time to clean the room, and then guests check in in the afternoon. It happens the other way around.

In a, in a hospital, patients try and check into a bed in the morning because surgical procedures happen in the morning, and by the time someone gets discharged from the hospital with rounds and imaging and CT scans and blood work, it becomes late afternoon. And so you've got this inversion period where the incoming is more than the outgoing, late morning, early afternoon, and that causes a chronic backup every day.

So hospitals have built sophisticated mechanisms to manage this. There's patient placement, people who are trying to play the chess game of which patient gets which bed and which unit at which time. There are people who can stand up surge units when you suddenly need 20 more patient beds and they can open up a temporary unit and staff it to the right kind of nurses.

It's a really complicated chess game to play. We are using our algorithms. To predict the likelihood of a discharge on time by each unit for each hospital in a fingerprinted, customized sort of a way. And based on the prediction of discharge, be able to make more intelligent decisions on bed placement to get more patients into the right unit with the right service at the right time, with a minimal amount of weight, right?

So it requires playing the chess game. Two and three moves ahead. So, uh, I, I'd be remiss. I, and we're, we're over time, so I appreciate you answering my last questions here, but I, I'd be remiss if as A-C-I-O-I wasn't asking you. So you said earlier, you know, you are grabbing data from the EHR, you're moving into the cloud, you're, you're, uh, running your algorithms out, out there in the cloud and then providing that, uh, information, I assume potentially back to, uh, an interface of some kind, or are you actually delivering data back into the EHR itself?

We are not writing to the EHR. So what we do is we provide information that helps the health system make more intelligent decisions. So it varies by product. So for the infusion product, we are providing a template and we will teach them how to modify their Epic or Cadence template or, or Cerner templates from the current methods to an intelligent thing.

They've got a block schedule in their EHR already. We replace it with our more intelligent block schedule. So there's a little bit of a, uh, of an assist at that point in time just so that from a workflow standpoint, the frontline continues to work, uh, entirely within their existing systems rather than seeking to replace anything.

So from time, I, I make a decision to the time I am up and running. But, uh, I've taken contract out of it. 'cause some health systems take 60 days for a contract. Yeah. But let's assume contract's done is, is that a contract? 30, 60, 90 day window? What is that contract signed to? Go live is typically eight to 10 weeks.

Give it plus or minus a week or two here or there. Uh, and that involves getting the data clean, getting it loaded, getting the models configured, run metric, alignment, scheduler, training, uh, et cetera, et cetera. We've raised a whole lot of money over the last several years, and therefore are quite well funded to, uh, to grow and expand.

And that's, that's kind of the mode we are in. That's exciting. Well, you know, thanks, thanks for taking the time, Mohan. I appreciate it. Where can people go if they want to get more information on, uh, your solution, the company, or even investing? I. Uh, lean tasks.com. L-E-A-N-T-A-A-S two As and one s lean tasks.com.

All our products are laid out. Uh, each product has got a three or four minute video attached to it so you can get a sense for how the product works. It lists the names of, uh, several of our reference clients, uh, and so on. So that would be the, the place to start. Fantastic. Awesome. I, um, alright, let me close out the show then.

I'll, I'll end the recording and then, and we can, uh, have probably a follow on conversation. Uh, so don't forget to check back multiple times this week. We're gonna be dropping multiple shows from, uh, from Hims and I appreciate everybody who's, uh, sent me notes and, uh, have, have really appreciated the . The interview's in the coverage, so that is, uh, greatly appreciated.

This shows a production of this week in Health It. For more great content, check out the website this week, health.com or the YouTube channel. Thanks for listening. That's all for now.



More from YouTube