The Tech Glow Up - Fabulous conversations with innovative minds.

Turning Wearable Data Into Personal Care; Medical Language AI at Scale – Oren Nissim & Tim O'Connell

• Nathan C Bowser • Season 2 • Episode 7

Share episode

Wearables track thousands of data points daily, but most becomes noise instead of signal. Clinical notes document critical patient information, yet we cannot extract meaning at scale. Two founders solving how we turn data into trusted care.

Oren Nissim is the co-founder and CEO of Brook Health. He has type two diabetes himself, which drove him to build remote care for people with chronic conditions like diabetes, hypertension, CHF, and COPD. 

The company works as part of the health system, extending primary care into the home. His mission is simple: people living with multiple chronic conditions at home need agency. The tools are cheap and covered by insurance. Brook collects thousands of data points daily from every patient. AI compares against baselines and identifies anomalies. 

But here is what matters: a care team analyzes AI-flagged anomalies first, then brings medical decision recommendations to providers instead of raw data summaries.

Tim O'Connell, MD is a practicing radiologist and CEO of emtelligent, a nine-year-old medical language AI company. The company does large-scale data extraction from clinical notes and AI-assisted chart review. 

He started the company in 2016 during the deep learning boom, years before the 2022 LLM explosion. His differentiator is that emtelligent does not use large language models as its core. The company builds custom language models optimized for cost, speed, and accuracy at massive scale. 

His vision for healthcare is better data extraction from unstructured notes so we can use the critical information clinicians spend so much time documenting.

Highlights from Oren Nissim at Brook Health:

  • His glow up is about use cases, not widgets. The industry is being forced to prove ROI rather than just adding more time and cost.
  • The company uses AI to flag anomalies, then care teams validate and present medical decisions to providers. This creates guardrails so providers can trust what they see.
  • His spicy take: watch Medicare Advantage closely over the next few months as some players walk away and others walk in.

Highlights from Tim O'Connell at emtelligent:

  • His six-month glow up is moving pilots to implementations. After years of experimentation, 2025 is the year of execution.
  • When extracting data, the software shows exactly where terms came from in source documents. This builds trust and allows human reviewers to verify accuracy.
  • His industry glow up is better healthcare analytics. We need to extract meaning from the documentation clinicians spend so much time creating.

Healthcare gets better when we turn overwhelming data into trusted insights that providers can act on.

A "glow up" signifies a positive transformation, reflecting the journey of becoming a better, more successful version of oneself.

At The Tech Glow Up, we humanize the startup and innovation landscape by focusing on the essential aspects of the entrepreneurial journey. Groundbreaking ideas are often ahead of their time, making resilience and perseverance vital for founders and product leaders.

In our podcast, we engage with innovators to discuss their transformative ideas, the challenges they face, and how they create value for future success.

If you're a founder or product leader seeking your own glow up, or a seasoned entrepreneur with stories to share, we invite you to join our guest list via this link.

Nathan C:

Hey, it's Nathan. Welcome to another special double episode from the HLTH Conference. Each one of these episodes is launching Monday and Thursday, and we'll feature conversations with two different CEOs so welcome, listen in

Oren Nissim:

this is ultimately about something that is very fundamentally available to everybody. It's cheap, it's covered by insurance. We can all do it these days. There's no reason why anybody living with a chronic condition home has to feel that lonely anymore. That's Glow Up.

Nathan C:

There's no reason that a patient at home should be isolated and lonely. Like we have the tools to provide better care. Fantastic.

Hello and welcome to the HLTH Tech Glow Up. I'm Nathan C, and today I am talking with Oren Nissim of Brooke Health. Oren Thank you so much for joining me today.

Oren Nissim:

Thanks so much for having me.

Nathan C:

Oh my goodness. So Oren could you, introduce yourself and a little bit of what you do at Brook Health? Sure. We're Brook Health and, we do, remote care for people with chronic conditions. We work as part of the, health system, so we primarily work with providers. Mostly primary care, taking care of people with, diabetes, hypertension, CHF, COPD, multi chronics, at home, and extending, primary care to the home, essentially. Amazing. tell me a little bit about your role at, Brook Health as well.

Oren Nissim:

Sure. So I'm the co-founder and CEO. Grew a life as a patient. so I have a complicated version of, type two diabetes myself, which I guess got me to be more intertwined in it, and at some point decided to, stop complaining and do something about it instead.

Nathan C:

Oh my gosh. That is like the classic founder story, right? Noticed a problem and just had to go fix it for yourself. could you actually dive in, to that origin story? I'm curious, how did you make the decision to take this entrepreneurial step?

Oren Nissim:

I was very involved in the worlds of, wearable and, the ideas behind the fact that we today are wearing and carrying with us a lot of devices at all. Translate a lot of information, very ambiently. And the idea is that we don't need to actually ask a lot of questions in order to just understand what's going on. So we could very easily come into a, if this, then that. and so that has been the beginning of the idea and from that on it evolved.

Nathan C:

a amazing, I find, a lot of times, especially as the general public is coming up against ideas about artificial intelligence, right? What do I even do with it, right? You see the videos of Sora AI making quirky, I'm riding a rhinoceros video", and it's if that's what AI does, like how does it affect me? I'm a nurse, right? Like I don't make rhino videos. can you talk a little bit, a lot of tools are, using ai. talking about predictive, talking about ways that we can, get ahead of health outcomes before there's a problem. How do you, approach this and the use of AI in your work at Brook?

Oren Nissim:

Sure. So we track a lot of information and we analyze a lot of data in the background that allows us to understand anomaly. Understand if a person has these particular conditions, what are we actually looking for? What is the behavior that we would like to see? And then what are those gaps? I think the biggest problem that comes up, and I think you see it in the show a lot. There's lots of technology available, lots of technology, and there is lots of people that will sell all sorts of things. And the key question is really what I like to describe is the accountability gap. At the end of the day, you are a consumer who bought X, Y, Z, and you have it, and now you're feeling empowered and all of a sudden you got these signals, but you don't wanna be your own doctor and you don't necessarily wanna be Google your doctor either or check GPT. Now the the new thing. How do you actually close that gap, which is where a lot of this now needs to be brought back in somehow into the care system, but not as noise because it's just a huge amount of noise, but actually a signal. And what is the signal that we can actually work on? So I think, AI first use case is in order to decipher noise for signal. And then be able to bring it into, as long as we're not willing to give up the job of trusting a provider, which I don't think we're that close to doing, be able to do it in such a way that is meaningful to a provider and actually cut away on their time as opposed to adding one more thing on a time We as a company needs a lot of work into how to do that better, because I think that's the main failure point with all this technology available.

Nathan C:

And I'm super curious about that. What is your primary way that you like to give time back to doctors? How do you achieve that?

Oren Nissim:

You know you're gonna be, we collect probably thousands of data points a day from every single one of our patients, and the reality is that just sifting through that is a huge amount of pain. AI is then able to ultimately compare this with what is the baseline, what are we actually looking for, and where are those anomalies? On those anomalies, we have essentially a care team that will do the first level of analysis to ultimately bring it to the provider on the, Hey, here's the next. Medical decision for you to actually make, as opposed to, here's just a huge amount of data, go read it and here's a few summary notes, we want to get very quickly into the, given this, here is the recommendation on that, what would you like to decide on as the medical professional?

Nathan C:

And is that, it sounds like there's the AI layer and then there's also that human layer that's doing that additional validation and research, presenting those opportunities. So that's happening in the background as the provider might be doing other tasks, reviewing the records and so can, isn't just taking things off of their plate, but potentially working in the background working when they're not necessarily so that the care is always on. Yeah. Regardless of the practitioner.

Oren Nissim:

Yeah, and I think that ultimately it's about how do you actually create guardrails? For this approach. Because the reality is that we all feel like we're not willing to hand the keys just yet, maybe over a period of time, and then who can be in the middle and the same time, how do you make that efficient? You can train health teams to do more, but that means you're essentially, again, adding up more time. As opposed to taking time away. So how to create it in a supervised fashion a very safe environment so that people can really trust what they're seeing. And that I think is a lot of that inner work that we have to do these days.

Nathan C:

Amazing. Awesome. so moving on to some of the more branded questions. The show is the HTLH Tech Glow Up, and let's start at the industry level. I'm curious, what is the health glow up that you wanna see for this industry?

Oren Nissim:

what I wanna see is people not buying the tech for the tech. And I'm saying it as a tech entrepreneur. this is not about the widget, it's about the what are you actually gonna do with it. So it's about the use case. And I think glow up here is about the fact that I see a lot of people coming in and saying I get what you can do. How does that actually make it more useful to me? And essentially forcing the industry to come back and say, we worked out the use case to the point that we're not just adding more time and adding more cost. We're actually trying to deliver an ROI. But assuming these new tools are in place, one of the cool examples that you could see right now is in the scribe world whereby, we used to use zoomin. Now you can use machines. Okay, but how does that flow actually integrates well such that we don't need to then re-review this, we can actually trust this and this is where it's the next level. It's not exactly you can't just use AI to summarize. You gotta make sure that it does it well and to the fact that it's actually useful.

Nathan C:

Thank you for that. so the next question takes the Glow Up a little bit more personal, a little bit closer to home. What's the glow up Oren, that you're looking to make and that you're looking to make for Brook Health?

Oren Nissim:

Thanks. We've been on a mission for a long period of time. I started this with a mission, which is that people living life with multiple chronic conditions at home, we need some level of agency. ultimately this is about how do we use these tools that are at our. Disposal to basically, get better agency in what we do and how can we bridge that gap with a provider that we trust, but have something in the middle that can help us. for me, this is ultimately about something that is very fundamentally available to everybody. It's cheap, it's covered by insurance. We can all do it these days. There's no reason why anybody living with a chronic condition home has to feel that lonely anymore. That's Glow Up.

Nathan C:

There's no reason that a patient at home should be isolated and lonely. Like we have the tools to provide better care. Fantastic. no pressure on this one, but social media loves a good hot take. Do you have a healthcare hot take, a spicy opinion, that you wanna share about the industry?

Oren Nissim:

I will pay close attention to what's happening with Medicare Advantage and people walking, some people walking away from it, some people walking into it, and I think that's gonna be an interesting next few months.

Nathan C:

Interesting. I love it. Oren it's been such a pleasure to chat with you today. Thank you for sharing, about your AI powered Insights and a tool that is clearing all of the information away so you don't just have signal, but you actually have data. thank you so much for visiting with us on the HLTH Tech Glow Up. Yeah, thanks so much. Appreciate it. Amazing. 1, 2, 3. See I'm the worst. Hello and welcome to the HLTH Tech Glow Up. I am Nathan C and today I'm talking with Tim O'Connell of emtelligent Tim, thank you so much for joining me today on the Health Tech Glow Up. Thanks,

Tim O'Connol:

Nathan.

Nathan C:

You have a pretty fantastic smile for this late in the HLTH event. Thanks for joining me early on day three. how's your HLTH been?

Tim O'Connol:

HLTh has been great. I love HLTh It's one of my favorite healthcare conferences. I think it's just got a great vibe and. I spend a lot of time in dark rooms and hospitals and, and I appreciate, you know, we need more unicorns in hospitals. Yes. I love it.

Nathan C:

Sure. And the work that you do at emtelligent?.

Tim O'Connol:

I'm a practicing radiologist. I work clinically one to two days a week. I'm also a CEO of a 9-year-old startup called emtelligent we're a medical language AI company, so we do a couple things, primarily large scale data extraction from clinical notes, and we also do AI assisted chart review.

Nathan C:

I stopped by your booth a little bit earlier today, and I was looking at some of the materials, and it seems like your approach to AI isn't maybe the same approach that you might see, with, a lot of other folks who are talking about AI and health records. Can you kind of explain, your differentiator there?

Tim O'Connol:

Sure. So as a company that does large scale data extraction, we work with a lot of people across the healthcare spectrum. So it can be producers of notes like health systems or it can be consumers and users of that data, like payers and life sciences companies. And what they often have a problem is they'll often be like, we have several billion clinical documents that we need processed. And there's obviously a lot of data there. So we've been spending years making our software so we can really extract the meaning and coded data from very large volumes of data and do it. Very quickly and efficiently and at a cost that works for our customers. So, yeah, I think a lot of people are now using the ultimate software development kit. They're using a large language model. Mm-hmm. Right? And, there's all kinds of problems with that from like a cost and scaling and accuracy perspective when you really start dealing with large volumes of data. Got it. So we love LLMs, we use them for all kinds of things. Mm-hmm. but for the core of what we do, we make our own language models to be able to do large scale data extraction.

Nathan C:

Okay. And you've been doing it for quite a while, right? Yeah. Like it's not just a 2022.

Tim O'Connol:

We started the company back in 2016, really during the sort of the deep learning, machine learning boom and not knowing what was coming next. but you know what? It's been great. the market has changed and everyone wants AI now and recognizes the value it can bring. So, yeah. it's been a great year for us.

Nathan C:

I've, one of the big themes that I've heard this year was like, very specifically ai, but assisted with a human, right? Like there's, there's some kind of co-pilot, there's some kind of ride along, there's some kind of, so it. I'm glad to hear it. I think it, it's that level of, user experience that people are and trust, right? That people are ready for. One of the questions I am, always interested to ask in this sort of age of AI applications, it's like trust and identity start to get really messy. You know, we, some of the first stuff we're seeing is like deep fakes and Sora. you know, there's even like social media networks dedicated to content that's imagined. and so what's real, what's truth? Are these actually experts? Do you have a perspective on, on trust and safety?

Tim O'Connol:

The way we've built our software and it's always been like this has been, if we're extracting something from a clinical note, let's say it's a report and it says that you've got appendicitis. We're really big on going, this was the term we found in the report. Here's where it started and ended in the report. Mm-hmm. When we're doing like, you know, review for humans to look at our output, we're always like, here's the sentence it came from. Here's the part of the, this section of the report it came from to really be very sort of deterministic and reliable. And be able to give people all the data they need. And then in, in our, our AI assisted, chart, review package, it really has like a multi-pay view where, because you can always have problems with, for example, like optical character recognition of a fax or a table or colored background. So we're always like, here's the text we extracted and here's the source document side by side. Yeah. So that the, the person doing the adjudication can really always get back to the source.

Nathan C:

Do you track those click-throughs into those additional sources?

Tim O'Connol:

Not, not yet. That, that's not really something our customers have sort of required and, yeah.

Nathan C:

I find it, it's an interesting data point to follow on to that. Like, we have the resources. Are they actually being used? An interesting point is like, helps, just document. I like it that on a user side. sorry to be pushing on your product. It's

Tim O'Connol:

all

Nathan C:

It's all good. it's something I ask everyone, just'cause I'm, very curious. I always like to ask about the origin story, and you definitely started with a little bit of your professional practice, but I'm curious, like not all radiologists start a business startup, tech startup, start working in ai. can you talk a little bit about what inspired that bridge?

Tim O'Connol:

Yeah, absolutely. So I did a fellowship in emergency and trauma radiology and in imaging informatics back in 20 12, 20 13. And I met, A team of an open source medical, natural language processing software package. called CTAs. It's a great piece of software. And I was back at work at the hospital I worked at and in radiology, particularly in emergency radiology, we don't get great histories from our Emerge docs. We might get a history that just says, rule out trauma. And we're sort of like, well that's, you know, I'll look at the x-ray, but that doesn't give me a whole lot to go on. Or I'll read the CT scan and I can assume it's trauma. So what I needed was I needed a decent patient history. And so I used this open source medical NLP software. We processed some radiology. Ports. I wrote an app, I integrated it with our radiology package, so you could just click on a button and see the patient history. Mm-hmm. But the problem was that the medical NLP software really wasn't accurate enough that we could trust the output. And so around that time I met one of my co-founders, Dr. Sarkar, a lifetime machine learning researcher, and he was like, oh yeah, that's a huge problem. Like accuracy's really hard. And so we really hit it off personally and professionally and, and with a couple other guys. we ended up starting emtelligent So really the goal was just if we can get at what's in those clinical notes, we can solve so many problems in healthcare.

Nathan C:

The, frustrated Doctor as a founder Is like very much, a theme from this year's interviews. there's a very interesting connection between, those who are working with data and informatics. And I was literally digging in this morning. I'm like, what is the informatics to founder pipeline?'cause there's like a. There's something about when you can, when your work is based in data mm-hmm. It can feel like a tool in all kinds of ways. Yeah. so, awesome. Let's, let's get, back to some of the theme of the, reason why we're here. Sure. At Health. as one of the larger, events for healthcare technology, it's a great place to kind of connect with the pulse, and share, ideas back, to the community. A glow up is a notable transformation like a rebirth. I'm curious, is there a glow up or a, a notable goal that you have for the healthcare and the health tech industry, at large? Where'd you like to see us go?

Tim O'Connol:

I would love to see, years ago I watched a documentary and was talking about someone who worked at Ford Motor Company after World War ii, and he was saying that they used to pay their invoices by weighing them. Right. So we've gotta put a pound of paper here from US Steel. Let's cut them a check for a million dollars and see if that covers it. I feel like in healthcare today, we're sort of at that level of healthcare analytics. We need better data and so that's what I'm really passionate about, is getting people the data they need. No matter what their role is in healthcare from those unstructured notes, right? Yeah. We have clinicians, doctors, nurses, so much ultra to valid health professionals who spend so much time documenting important stuff about our patients, and yet we can't use that data. So that's the transformation I want to see.

Nathan C:

Yeah. just thinking back to like recent times when family was in the hospital, the frequency. That like, you'd have to give kind of a whole history of like, why we're here. Like basically every professional needed to do the same interview so that they felt they had the notes they needed. Right. And like, which made it great if they were on shift for a few days in a row. Right. But it was hard if they were only there for a few hours at a time.

Tim O'Connol:

So very, very hard. Right. that's a great way We could help improve the patient experience. Right.

Nathan C:

Amazing. So, thank you for that. and for, for emtelligent mm-hmm. Let's take it in a little bit. what are the, what are the goals?

Tim O'Connol:

So the six month go up, I think right now is, we've got 20 25. If 2024 and 2023 were years of experimentation. with the healthcare industry, 2025 is like the year of implementation. So, we've done a really large number of pilots in the last, six to eight weeks. Even that, pilots always take like a couple months of, legal and this sort of stuff to even start before someone even sends you data.'cause it can always contain PHI and this sort of thing. So we've done a huge number of. Pilots and we have a huge number still to go. And really the glow up I want to see is those pilots moving to implementations.

Nathan C:

Amazing. and congrats. That's like hard earned. if you could be even a gen general answer to this, it's amazing. there's a lot of folks in like the deep tech world that I work in that believe that healthcare, that their solution is a, has a healthcare use case, and often they're looking for those first pilots. And so when you're talking about a lot of work and planning and time and partnerships goes into it, is there. Some broad generalizations. Like is there a sort of a rule that you keep for like, well, a partnership takes four months. Takes seven months, how much does it take to do a partnership in healthcare?

Tim O'Connol:

You know what, it really depends on the customer. Mm-hmm. and when you're dealing with like large mega. Core kind of customers. Mm-hmm. getting through contracting can be six to eight months

Nathan C:

just on the contract,

Tim O'Connol:

contracting.

Nathan C:

That's the paperwork part. After you know what you want to do after you

Tim O'Connol:

Yeah. So it's not me complaining about it. when you're working with, say, startups, they tend to be far more agile, and can work a whole lot faster. we've been really trying to optimize our processes for that. like working with legal counsel to simplify contracts and doing all these things oftentimes as part of the pilot process, customers will come back and go, oh, like, well, you know, you made some assumptions here and they weren't all correct. Right? And we're like, yeah, you're absolutely right. We did.'cause we didn't wanna spend, a week in planning before we got you stuff. We wanted to get you some data and iterate on that. Thank you.

Nathan C:

Oh, that's the way you do it. Yeah. Start small. Yeah, exactly. Start in one building, not four. Amazing. we're still on the thematic questions. Okay. heroes and Legends is the theme of HLTH 2025. I use this as an opportunity to ask people about the heroes, legends and mentors that have guided their journey and entrepreneurism. How have mentors and legends in this space, impacted your journey?

Tim O'Connol:

I've been so lucky to have so many great mentors, in healthcare and engineering if I had to provide a shout out to any, mentor, one of them would be, a wonderful cardiac electrophysiologist I worked with as a medical student. Great guy named Dr. Paul Dorian at St. Michael's Hospital in Toronto. Amazing. he was an incredible mentor to me he was trying to solve complex physiology problems and just allowed me to use curiosity and hard work to try and solve problems with him for a couple different summers, doing research. And so, yeah, I mean, it was just such a positive, overwhelmingly positive experience.

Nathan C:

One of the reasons why I really like that question is because. the power of somebody saying, I believe you. Keep trying, keep going, keep trying is like so powerful. And like to start with someone who's like, be curious. Yeah. Go learn, right? Is like what a gift. Right. Amazing. last question is totally optional, but do you have a spicy healthcare hot take?

Tim O'Connol:

Not so much for healthcare. I'm a little bit worried about ai. Right now we're starting to see something called vendor financing, where people who sell stuff are loaning money to people who want to buy stuff. But during the internet, boom, I worked for a company called Nortel Networks. I was a network engineer. And it was an amazing place to work, but that company got into trouble by doing vendor financing. And that can be a sign that there's a bubble going on, and I'm worried about that. So I don't think it's gonna, you know, bubbles happen. We know that bubbles burst. We know that. For what we do. Nothing has really changed other than a lot of customer interest with the AI ramp up. So, you know, we're gonna keep doing what we're doing, but I'm just worried

Nathan C:

as a leader who's been through a bubble or so. Mm-hmm. do you have a strategy or advice for how to approach it or how do you approach, the possibility of disruption.

Tim O'Connol:

you know, the worst part I saw about that the internet boom, was there were so many wonderful people that I worked with at Nortel and they had their, literally their life savings in stock. Work in that company and I think a lot of people got hurt. And so I would say no matter how good your own hype is, always expect that external externalities can happen.

Nathan C:

Yeah.

Tim O'Connol:

Right.

Nathan C:

Oh my gosh, that's fantastic. Tim, it has been such a great time chatting with you on the HTLH Tech Glow Up. Thank you. Thank you so much, for joining us. We've got one last thing to do. Alright. One second, we're gonna clap it out. Okay. One. Two, three. Awesome. Thank you.