Modernizing Medical Coding with AI (Michael McLaughlin of Synaptec Health)
Michael shared his experiences and insights in healthcare and medical coding and his start-up building journey.
About
Welcome to the 35th installment of Foothill Ventures’ Lessons from Founders series. From time-to-time, we publish an in-depth founder interview, ranging from early-stage entrepreneurs to established businesses. Our conversations cover their personal journeys, the lessons that shaped them, their visions for the future, and their failures. We also learn more about their companies and about the challenges they try to solve. These insights and lessons are applicable to any entrepreneur — current or future.
Synaptec Health, established in 2020, is an artificial intelligence (AI) — powered medical coding platform that increases efficiency, reduces costs, and improves patient care. Trained on data generated over thousands of hours with highly experienced medical coders, their technology implements NLP and machine-learned algorithms to review patient charts, assign codes for insurance reimbursement, and then layer on value-added services such as insurance company billing and analytics to transform the industry.
Michael, CEO and Co-founder of Synaptec Health, is a board-certified emergency medicine physician who completed his medical degree from the Rosalind Franklin University of Medicine and Science and residency at Rutgers University. During his experience as a resident and physician, Michael discovered the negative impact of administration backlogs on healthcare and its future advancement. Now, he aims to make an impact, starting with medical coding.
Why we invested in Synaptec Health: Medical coding is an enormous market ($16B), and it is well-suited for AI. It is very difficult for humans to stay completely up to date with medical coding rules, and sift through medical records quickly and efficiently. The company has built machine learning models that can read and code each chart in seconds, more accurately and consistently than any human, while reliably identifying down codes and missing documentation. Additionally, the founding team is strong: Michael’s experience and insights from being a practicing physician paired with Chris’ technical chops are a strong combination (in addition, both our partners Xuhui Shao and John Matheny knew Chris from their Yahoo days, and could confirm that he’s a superstar).
What inspired you to found Synaptec Health?
When I was in clinical practice, and even throughout residency, I realized that the clinical side of medicine was making a lot of progress, but the administrative back end of medicine was just significantly lagging behind other areas of tech. If we did not start to make significant improvements in terms of the technology on the administrative side of medicine, the clinical side of medicine would dramatically get held back and not be able to advance forward, similar to other industries. That was something I did not want to have happen. So medical coding was an excellent entry point to make that change.
The Unique Perspective of a Healthcare Startup
The major thing is that healthcare is not like other industries. If you are outside of healthcare, it’s going to be extraordinarily difficult for you to figure out the complexities of how it works. One of the benefits of working clinically is that you understand some of the nuances in terms of how workflows work and how physicians can be very resistant to change, resistant to technology. With technology, when patients are at risk in terms of privacy, you have to be concerned about what you actually start engaging with. So, understanding what is important to physicians needs to be taken into consideration. Is it actually going to make their days more complex? Is it actually going to make it easier?
Addressing the Challenges of Medical Coding
Overall coder quality and consistency are a real issue. There is a lot of turnover with there being a lot of variability. If you have teams of hundreds of thousands of people, how do you know that they’re actually consistently coding? Then, as a company submitting codes, you don’t know what the individual coder is actually submitting. You’ve done your audits, and you can look, but you don’t, at the end of the day, know each chart. Therefore, that puts you at risk and leads to denials. You don’t have that nuance of control over what’s been submitted and potentially what the denials are. And then, on the coder side of it, you aren’t able to see globally the high risk that you are faced with when you’re looking at that particular chart. If you have a technology that is able to look at all of the encounters for a particular customer and see who the payer is, you can start to build models around detecting if this chart is at high risk of being denied and prevent that from being denied.
So one of our early decisions was on how we wanted to go about solving medical coding. We picked emergency medicine as the place to start, and there are a couple of reasons for that. One is it’s my specialty and my background. But, also, if you can solve emergency medicine, then you can solve just about any specialty because of the complexity and the breadth of pathology that comes to the door. There’s a wide variety of ICD 10 codes; there are a lot of procedures that have to be coded. So there’s significant flexibility. However, at the same time, it’s still narrow enough to where you’re solving one particular problem rather than trying to solve all of the coding at once. There have been some approaches by companies that tried to take too broad of an approach by coding all as one, or just coding in general. I think that is a mistake. So we picked one particular area to start with, and then we are bringing on additional specialties for our customers’ needs. And then we just tailor our models for that particular specialty. And even off of that, we will tailor them even further for community hospitals, outpatient settings, rural residency programs, major university hospitals, and build individual models that are tailored for that specific patient population.
Impact of COVID-19 on the Synaptec Health
Before the pandemic, new technology may have taken 5–10 years for the healthcare industry to get on board. However, the pandemic fast-tracked that in terms of people getting more comfortable with it, partly because they may “have not have had a choice.” If you have teams of your coders who can’t go to the office or are sick, you still have those patient charts that need to be coded. The data start piling up. So it really forced the healthcare industry to look at our technologies and become a little bit more comfortable with them sooner rather than they would have otherwise.
The Integral Value of Customer Feedback
The biggest thing is to make sure that you get in front of customers early enough. You can sit at home all day long and try to perfect your product. However, until you actually get it out there and have people start using it, you won’t know what is working and what is not. So we were able to take a bit more time because of COVID to improve our product. That allowed us to go out to the market and be able to code 100% of the charts for our customers, which was a big deal. It is a big difference between doing only 50% and even 90% of coding. Being able to get your product out in front of customers early enough to start getting that feedback from them is the most important thing that you can do as a startup. That was one of the biggest things that improved and expanded the product quicker and reached customers faster.
Looking Ahead for Michael: The Next 12 Months
At this point, it’s continuing to get out there and expand as rapidly as possible into the market. There is a lot of competition. You want to make sure that you are getting to as many customers as possible, show them that you have the technology and can actually solve their problem first before somebody else gets in there. I am confident about our product and happy to put it in front of anybody. But if you’ve taken on some other technology, regardless, even if it is not quite as superior, it takes a bit for people to make the decision to make a transition. So we want to get our product in front of customers before the door opens for somebody else to move in. So we’ve been putting a lot of time into customer outreach and getting them a trial and getting them on board at the start of the product.
Interviewed by Anchal Ahuja. Videographed by Hannah Wu and Heidi Lu.
To get updates on this series, please follow our publication on Medium.
Follow us on LinkedIn: https://www.linkedin.com/company/foothillventures
Follow us on Twitter: @FoothillVenture
Foothill Ventures is a $150M seed-stage technology firm. We back technical founders across software, life sciences, and frontier technologies.
Questions, thoughts, reflections? Let us know in the comments below. We’re always looking for great entrepreneurs and early-stage ideas, and we’re always interested in having a discussion about venture, technology, and anything related. To see more about Foothill Ventures, please visit our website: foothill.ventures.
