Autonomous Medical Coding with Ilyana Rosenberg, Principal Product Manager at Nym Health was automatically transcribed by Sonix with the latest audio-to-text algorithms. This transcript may contain errors. Sonix is the best audio automated transcription service in 2021. Our automated transcription algorithms works with many of the popular audio file formats.
Saul Marquez:
Hey, Outcomes Rocket listeners, Saul Marquez here. I get what a phenomenal asset a podcast could be for your business and also how frustrating it is to navigate editing and production, monetization, and achieving the ROI you’re looking for. Technical busywork shouldn’t stop you from getting your genius into the world, though. You should be able to build your brand easily with the professional podcast that gets attention. A patched-up podcast could ruin your business. Let us do the technical busy work behind the scenes while you share your genius on the mic and take the industry stage. Visit SmoothPodcasting.com to learn more. That SmoothPodcasting.com to learn more.
Saul Marquez:
Welcome back to the Outcomes Rocket, Saul Marquez is here and today I have the privilege of hosting Ilyana Rosenberg. She is the Principal Product Manager at NYM Health, a startup focused on automating medical coding. She has over 10 years of experience in the health care industry, with the majority of her time focused on the revenue cycle, specifically in coding collections and revenue cycle optimization. Prior to NYM Health, Ilyana worked as a product manager at the Broad Institute, partnering with Verily Life Sciences to build Terro, a cloud-based genomic analysis platform that houses some of the largest genomic datasets in the world and aims to change the world of scientific research and discovery. Ilyana also leads the geo map at Global Oncology, a nonprofit organization founded by Dr. Egbert and Dr. Franklin Wang, with the mission of bringing the best cancer care to underserved patients around the world. She grew up in Portland, Oregon, and now splits her time between the US and Israel. So, Ilyana, excited to have you on the podcast today to talk about medical coding. Thanks for being with us.
Ilyana Rosenberg:
Thank you for having me today.
Saul Marquez:
Absolutely. So this coding thing, it’s always changing and it’s such a pain for so many people. So today is going to be a good chat about how you guys are doing that differently. And before we do get into that, Elliana, I love to hear more about you and what inspires your work in health care.
Ilyana Rosenberg:
Absolutely. So I think about what inspires me in health care. I want to share three memories. The first one is about two years ago, I was sitting with my 91-year-old grandmother in her living room looking out at Lake Michigan. She was catching up on news. I was catching up on emails, and all of a sudden the Internet stopped working. So without hesitation, she gets on her hands and knees as a stubborn 90-year-old woman would do and restarts the Internet using a flashlight, looking behind the TV to back up about 30 seconds later, as I was still standing on that couch and I had it moved. And she said I’d like to thank my personal trainer who helps me stay healthy and fit so I can easily fix the Internet. That’s one that I love. The second one is also kind of related to the health care space. Around that same time, I was working at the Brown Institute, my colleague comes running into the open desk area and excitedly told us all that he had just run a complex analysis workflow against hundreds of thousands of genomic data sets. And he’s done all of that within minutes. That used to take a few days, if not a few weeks to process previously.
Ilyana Rosenberg:
So we are changing the speed and method of scientific research and discovery. And the third one comes from the work at Global Oncology, a nonprofit organization that’s bringing the best cancer care to underserved patients. So we put this online map that mapped all cancer research and control projects around the world. I was at a board meeting on one of the top floors of the Dana Farber Cancer Institute building in Boston, and one of the board members was telling us about a conversation she had with an oncologist in Malawi about looking at this Globemaster oncologist and with a bit of surprise and said, I’m not alone. So the map had shown and other researchers and physicians around his vision and around the world were also treating the same patients with the same cancer type. I started a global collaboration to improve patient care. So I just got off to three different memories that really impacted me. And they all representing different components of the diverse and exciting health care ecosystem. And really, no matter what part of the ecosystem you’re working in, whether it’s going to technology, medical care, public health, global health, science, business interests, every aspect is impacting someone’s life. And this impact inspires me every day.
Saul Marquez:
Love it. Love your memories. And thank you for sharing. Those stories struck out to me as going to that each represents a different component of the health care system. And really you can’t live day in a day without having some interaction with that whole ecosystem.
Ilyana Rosenberg:
Yeah, I agree.
Saul Marquez:
My favorite one was one of your grandma still doing that today. Are that’s awesome. That is so great. And so, you know, it is kind of the connective tissue between all of us health and staying healthy, taking care of sickness when it arises behind the scenes of all that is the economics and the coding and all that. So walk us through NYM Health. What exactly are you guys up to and how are you improving and adding value to the health care ecosystem?
Ilyana Rosenberg:
Of course. We’re transitioning a bit away from patient care and the public health and global health, that definitely inspires me and moving to the revenue cycle on the business side of health care, that has its own unique impact to individuals. So I currently work at an Israeli startup company called NYM Health, and it focuses on automating medical coding. I do often get asked, what do you mean by automated coding? Is it software coding? What is medical coding and why is it so important? So I can give some brief context before I dive into the detail of what NYM is doing.
Saul Marquez:
Sure, let’s do it.
Ilyana Rosenberg:
Medical coding, you could think of it as really the backbone for disease reporting and the classification around the world, but it’s also the core for reimbursement of services in the United States. So let’s say a patient comes in to the emergency department complaining of a headache, fever and shortness of breath. The doctor might do a chest X-ray and unfortunately, in today’s world, probably test to see if the patient has COVID. The doctor document everything they do, the examination, as well as the procedures that they performed, as well as the outcomes of the test that was administered. After the patient is discharged the chart is then sent to what we call the hospital’s billing office, and that’s where all the work is done for the actual services and the physician to get paid for what they did. In that billing office are certified medical coders that review the documentation of the chart the physician wrote down. And they assign relevant diagnosis and procedure codes to the chart. Headache could have a code R51. Shortness of breath has a code – RO6.02. And then you have procedure codes for x ray and COVID tests also have codes. These codes are then sent to the insurance companies to use for reimbursement and to reimburse that health care facility for those services performed. So you can begin to think about really the importance of this, not only for reporting of disease but also to make sure that the hospital and physician get the most reimbursement for those services. If the documentation is insufficient of the codes and incorrect, that health care facility would not receive any payment for those services. That’s what we would call a denial. That’s kind of the background on kind of medical coding. NYM offers a platform that automates this process. So we use what’s called a clinical language understanding technology, what we call the ACLU engine, and we capture the full clinical picture of the patient visit. So what that means is that we can actually break down the senses of the chart, use computational linguistics to understand the meaning of each of those sentences, be able to put the meaning of those sentences together across the whole chart to figure out what happened at that visit. What does the patient say? What happened? What did the physician do? And then what was the ultimate outcome? So we use that understanding from that engine to automatically assign those relevant medical codes to the patient chart. And while it sounds like a complex and it is a very complex system, we do this within seconds. It’s fully transparent and there’s no human intervention involved.
Saul Marquez:
I think that’s awesome. I mean, it sounds too good to be true.
Ilyana Rosenberg:
That’s all we’ve definitely heard. And it’s very much one of those conversations we have with health care facilities when we discuss what the technology they can do, they usually say, well, sign me up for a pilot. Let’s see how it works. It’s definitely one of the newer technologies in the space that’s a small part of the revenue cycle, but definitely impactful.
Saul Marquez:
Yeah, I know it sounds interesting. And so much of physicians work in the EMR is how do I code this thing. And so what you’re saying is through the process, you guys layer in some sort of recognition software to the EMR that then spits out potential options on what the best coding could be?
Ilyana Rosenberg:
Yes, and it’s a slight variation. So we think about the way the physicians write documents today might be right into a patient chart. That patient chart has kind of extracted like a PDF form that certainly a medical coder looks at that form. And so what our technology does is we look at that form automatically, though, with our linguistic eye you could call and assign the codes. There is a technology that exists today called computer-assisted coding technology. And you mentioned presenting coding options. That’s what that technology does. It’s been around for about ten years. And so what CLU is leveraging that technology. It kind of supplies that I’ve looked at the chart, I’ve kind of hear so recommended codes that I’ve used based on my kind of natural language processing and MLP technology, and then that coder would say, OK, use the recommendations. Let me take a look at them. Let me take a look at the chart and I’ll see which ones if it’s accurate. And B, what it which ones I should actually assign to that chart. That’s kind of what’s called computer-assisted coding or technology. The NYM products actually result in kind of fully accurate codes that high quality that doesn’t need that individual, that medical code to do that review. So as opposed to just suggestive codes, it’s actually the final assigned codes that are then sent to the payers for approval of that reimbursement.
Saul Marquez:
Makes a lot of sense and sounds really, really convenient. So as folks begin to use this, what would you say makes it different or better than what’s available today?
Ilyana Rosenberg:
There are a few areas where this product sort of stands out in the marketplace today and specifically in the medical coding space today. The primary method of coding is, like I said, with the certified, highly specialized medical coders. But the challenge is there’s a large number of codes and it’s very complex coding guidelines that exist. So we mentioned that kind of headache has a code, x rays have a code. So there’s a diagnosis and procedure code. Today, there are over seventy thousand diagnosis codes as options that could be assigned to a patient. There are also over ten thousand procedure codes. And it’s not just the number that’s so overwhelming sometimes, but there’s also a large number of guidelines for when to code which code, which should be applied together, some separate and these are frequently changing. So it’s very challenging to keep up with the training of these medical coders with the most up to date guidelines. And there’s just so many of them. It’s hard to always get it accurate.
Saul Marquez:
It makes sense. Yeah, you get an example. Great, great.
Ilyana Rosenberg:
Yeah, it’s quite challenging. And one example actually from recently is we’re all talking about, say, especially in the health care spaces with COVID-19. When that came in in the spring, obviously updating guidelines for how do you code for patients that come in with COVID, what’s the right way to codes so we get reimbursed for those services. And those guidelines change daily, sometimes hourly, for the first few weeks of when COVID was really present and beginning to think how do we how do we deal with this? So for that, you had if those guidelines changed so frequently, it’s hard to always update your hundreds of medical coders with guidelines of the most up to date today or this hour that they should use on those charts because our technology is automatically updated the engine within hours and we were all set. So we didn’t need all that training that was required.
Saul Marquez:
Yeah, I think that that’s awesome. And so it’s simplifying it. And while it’s always changing, there’s a great opportunity to not have to do a bunch of training. And really it’s automation here, right? We’re talking about automation.
Ilyana Rosenberg:
Exactly. Because the other challenge that exists today and the way that medical coders code is, first of all, is there’s a shortage of coders and that has happened for the last few years. It’s not just with covid that’s causing that shortage. And typically, if you think about the way that medical care is going to code a chart. It takes about 12 minutes to review that record. With the automation, we can actually code a chart in seconds. And so that really enables health care facilities to cut down on operational costs and efficiency, improve improving efficiency to really able to kind of support that that challenge of that shortage of coders that exists.
Saul Marquez:
Yeah, and it’s a great opportunity. And so how would you say the platform is making business better?
Ilyana Rosenberg:
In a few different areas. One is definitely on operational efficiency. So as I mentioned, it takes about 12 minutes to code a chart for a manual code. Today, and these are highly specialized, highly trained individuals. And also we take seconds. So it’s very easy to say, for example, if we get back to that, COVID, a lot of hospitals and especially in the emergency department space, they offshore their coding services. So when those offshore companies or countries went into lockdown for a few weeks, not a month or two at the beginning of COVID, none of those companies could actually work. There weren’t able to go into the office to access those charts from that hospital in the US, not to code those visits. You started this backlog of charge that required coding. If you do the automated automation way or need to catch up, some of our clients have been able to use us to catch up on that backlog that they have experienced. So it definitely improves that operational efficiency side.
Ilyana Rosenberg:
Another area is on the business of improving it relates to a compliance perspective. What doesn’t exist today is the transparency of coding. You have these medical coders, they call the chart. But if I want to know why the chart was coded in a certain way, I have to go back to that medical code desk or the resume and ask them why. What was your rationale for it? Because of the way that we can understand each sentence and kind of building blocks in that patient visit and have that clinical picture. We actually immediately upon coding can provide a multipage PDF is kind of what it looks like today, explanation of how we actually got to that code. So it enables the business side to really always be compliant-ready and enable to improve denial management if anyone does get denials on those tax from payers.
Saul Marquez:
Yeah, some great applications there, Ilyana, and very useful. What would you say has been one of the key setbacks in kicking things off and what you guys have learned thus far?
Ilyana Rosenberg:
So one of the biggest setbacks is like at the beginning, we were looking at, well, how do we automate how do we capture the clinical picture? Luckily, we actually were able to get that pretty quickly of figuring out working with physicians that we have on staff who are actual software engineers as well. So you have a couple of skills of expertise – definitely beneficial. As well as the linguistic component. We actually pretty quickly get past that challenge if we can capture that full clinical picture and have that accurate coding.
Ilyana Rosenberg:
So once we did that, we realized it was really a further step back that we have to encounter, which was on the integration. There is such a diversity in emergency or electronic medical records and practice management systems and really every system that physicians use to document the visit as well as the billing office uses to document what’s the follow up on that chart. And because of that diversity, it was challenging to figure out how do we integrate into all these different formats and all these different systems so that we can continue conversations. And it’s a large problem that actually exists with many vendors in the health care space today. And we work closely with our clients in order to have that seamless integration into each one of the systems. We are able to accommodate all formats today with something that we worked on to ensure we could be flexible in the formats that we receive, the formats that we send back, the information to that client so that that integration flow can be customized and flexible to the client depending on the system that they’re on.
Saul Marquez:
Very cool. Very cool. And so you guys are making some really exciting steps here. And I want to ask, what would you feel and believe is the most exciting thing that’s going on with NYM.
Ilyana Rosenberg:
Honestly, its with NYM and a lot of other startups and even non-startups today. So health care in that large ecosystem of health care continues to evolve every day. And in the last few months, we’ve covered has really challenged that. I’ve seen every aspect of that system so we can as a startup, as well as even larger, more established companies are pivoting and looking for opportunities to either have vaccines, developed devices, a better medical treatment, or other areas like we’re doing it NYM to optimize the health care system so that resources can then be diverted to focus instead on patient care. So that’s kind of how I’m seeing that health care system evolve today. And I’m really excited to see how that system continues to adapt and really all the innovation that arises from it.
Saul Marquez:
Yeah, definitely is exciting times. COVID has done that and I couldn’t agree with you more. Ilyana, I certainly appreciate all the insights that you guys have shared and that you’re up to at NYM for coding. And so I want to give you an opportunity to give us a closing thought and then the best place where the listeners could reach out to you and find out more you or anybody on your team to find out more about how they could do a demo or explore what NyM has to offer.
Ilyana Rosenberg:
Absolutely. So today we focused on medical coding and NM is working to optimize the revenue cycle of health care, but they really are so many other areas of health care. I want to pose a few questions to the listeners to think about, especially, as I mentioned, the innovation and the opportunities that are rising today. What areas of the health care ecosystem do you as the listener interact with? And what are the problem areas that you see that exists? Listen to individuals who work in that space to understand the need, and then think outside the box for possible solutions. NYM started from an idea between two individuals and a few hours in a coffee shop. So the health care system is complex and the solution may seem small at first, but you never really know the larger impact you might have. So you can reach me on LinkedIn, if you want to know more about the work NYM is doing to automate medical coding, discuss anything health care related, or even if you know what it’s like to read between two countries, they do work between the US and Israel. I’m always happy to connect with new individuals. If you do want a demo or a little more about the name and product, in addition to reaching out to me directly, you can also go to our website at Nym.Health. And there’s more detail there on webinars that we’ve done, as well as white papers and opportunities for a demo.
Saul Marquez:
Love it! Ilyana, thank you so much. Certainly, exciting stuff that you guys are up to. And I appreciate it. And I know the guests and listeners appreciate having you on to share what you’ve shared today. So big. Thanks to you. I really appreciate your time.
Ilyana Rosenberg:
And thank you as well. I appreciate it.
Saul Marquez:
Hey, everyone. Saul Marquez here. Have you launched your podcast already and discovered what a pain it can be to keep up with editing, production, show notes, transcripts, and operations? What if you could turn over the keys to your podcast busywork while you do the fun stuff like expanding your network and taking the industry stage? Let us edit your first episode for free so you can experience the freedom. Visit SmoothPodcasting.com to learn more. That’s SmoothPodcasting.com to learn more.
Sonix uses cutting-edge artificial intelligence to convert your mp3 files to text.
Let powerful computers do the work for you; automated transcription in minutes. Powerful integrations with the most popular software allows Sonix to easily fit within your workflow. Automated algorithms have improved a lot over the past decade. Are you a podcaster looking for automated transcription? Sonix can help you better transcribe your podcast episodes. Sonix has the world’s best audio transcription platform with features focused on collaboration. Lawyers need to transcribe their interviews, phone calls, and video recordings. Most choose Sonix as their speech-to-text technology.
Imagine a world where automated transcription just works. Automated transcription is much more accurate if you upload high quality audio. Here’s how to capture high quality audio. Rapid advancements in speech-to-text technology has made transcription a whole lot easier. Do you have a lot of background noise in your audio files? Here’s how you can remove background audio noise for free.
Sonix is the best online audio transcription software in 2021—it’s fast, easy, and affordable.
If you are looking for a great way to convert your audio to text, try Sonix today.
