My goal was always to be an entrepreneur and or to be in a leadership position, But I can't say that I had an exact path to find, you know, Well, in advance, I feel like I'm where I am today. You know, just do the hard work. Lots of constant learning luck and, most importantly, had a lot of people well, just meant for me and help me along the way. I think that's really been something that I've been very grateful for in terms of how I got into the into this particular startup. Um, when I was in my twenties, I developed a rare medical conditions, and I was living on the West Coast of the time, and I was fortunate enough to have been referred into Johns Hopkins in Cleveland Clinic. And so I started flying from the West Coast for treatment on a regular basis. And, you know, I spent a lot of time around, you know, in a health care setting and really understanding, you know how health care works. Um And then about a decade later, I developed another issue, and, uh, it was really that issue at that point. Time that drove me into looking for other treatment options. And so I started. I have a background in developing algorithms. So I started working on a text mining pub Med in trying to get access to more medical literature and, you know, with that text mining exercise. And I did find what I was looking for from a health perspective. But I was also looking for my next project, and it became really passionate about health care, and it was looking at what was happening in industry. There's a tremendous amount of e char data that was being created, a lot of it, mostly on structure and the the number of medical journals that were being creative was this exploding as well. So that's really what led to pound me going into into the stern up.

So what we do is we build machine learning models using on structure tax to solve various, you know, predictive problems and those air research clinical as well, administrative functions. So you know the way that customers air handling the problem, currently in some cases, is manually. Some problems can be solved with just throwing up bodies at it at the problem. But in other cases, the problems really can't be sold with just throwing resource is onto the problem. So couple examples. So one of the things that will do is we'll go through. Let's say that a researchers looking for a particular cooperative patients, they may have a mad a static type of cancer. And, you know, in some cases the medical codes that are available are even specific enough to identify those patients. So we'll go through all the medical records. Sometimes you're looking at millions of of data points just to even find the co hurt. And then once you find the cohort, then you can work on, you know, identifying some of the other characteristics that the researchers are looking word. So that's one type of use case. Another use case could be taking the instructor text and we convert, say, operative notes to diagnostic and procedure codes. And that's cost savings for the organization as well as helps identify consistency for coding across the organization. Um, still another use cases Real world data for research purposes. So we have a partnership with an academic institution and were able to get access to HR records. You know, there d identified and help pharmaceutical companies and other researchers identify cohorts of patients they may not be able to otherwise find. So but all of this really lead back to you. This is all about data, and this is where what I developed my medical conditioner realized how important it was to find the exact out or the right treatment method because that congrats Lee effect the outcomes that patients can achieve. And not only does it benefit the patient but also benefits, you know, society, General, because it can significantly lower costs of treating that patient, which is something that, you know we all pay foris a a, you know, more of a machine learning tools. So, Google Scholar, just more of a of a application that, uh, uh, you know, has resource is available and searching all that. This is a machine learning based platform. You know, Google Scholar isn't, for example, you know, translated diagnostic codes and all about, and it doesn't have the machine learning miles built into it.

quite honestly, that can't remember the first couple of weeks because it's been quite a while. But I think that's really the point of this question. Is that so? It's It's a good question. But what happens in a start up is that you know, most startups, you're gonna be in its for longer than most people are school, right? And, you know, 67 years. And, uh, you know what? Change? Certainly You get mawr as you for us. The more data we got from various parties of the easier was the build out of solution. So there was a lot going on in the early days of just trying to get data and, you know, working our algorithms. But, um, you know, it's really it wasn't really until later years where we started making the big progress.for research state of the data that we receive its de identified plus everything that we do is in a HIPPA compliant environment. So whether you know, the data is a d identified or not, we still treated as is his hip a data we follow all over internal protocols in terms of access to that data and saw it so forth for some of the other use cases. You know, those are were permitted to have access to that data to provide services to to the hospital. But really, security is something that, you know, is always top of mind for us. We're always working on on additional safeguards that we can put it in a place, but it is really, um, you know, it is it is really important. But one of things I should you know comment on, though, is that, you know, probably at some point time, there's gonna have to be some change on hip on just data regulations in general because, you know, HIPPA is focused on on hospitals and providers. But, you know, your your average credit card company probably knows more about you in some ways than ah in its unrestricted access for example, than then you should probably be permitted just because you think about credit card transactions and everything else so you know, it's it's probably a little bit of an impediment to researching, and it definitely has to be taken seriously, but it's probably a little bit unbalanced right now in terms of where the regulations should be.