Listen to the full episode:



COTA’s Vantage Products Give Access to Targeted Oncology Data Sets with Miruna Sasu


The healthcare ecosystem generates approximately a third of all the new data in the world. And it holds untapped potential for developing new therapies and giving people the opportunity to live longer and healthier.

But these data sets are raw and need to be meticulously tabulated into meaningful, targeted information.

In this episode of the Real World Talk podcast, our host Nick Ritter welcomes Miruna Sasu, the president and CEO of COTA. They talk about COTA’s Vantage product and how it can help improve drug development in the oncology space.


  • [01:06]  Introduction — The host Nick Ritter introduces the episode and talks about the amount of data that the healthcare industry generates and the untapped potential for developing new therapies. However, these data sets are often very messy. He says, “To turn these data reserves into truly actionable information, they need to be meticulously curated into meaningful, targeted data sets that are fit for their intended purposes.”
  • [02:04] Differentiating between data abstraction and data curation — Miruna explains the difference between data abstraction and curation. While data abstraction is pulling in data using technology, data curation is more complex.
  • [02:55] Why is COTA’s work important? — Miruna explains how COTA helps identify the most clinically relevant data points in a cancer patient’s journey. She says, “We go into the EHR and the doctor’s notes where you find very pertinent information, for example, stage of disease and progression, and other things that are very important to understand the patient. And we take them out of those nodes, and we structure them in the data.”
  • [04:13] Vantage products are large data sets that are epidemiologically relevant — Miruna explains what makes Vantage products distinct from other data products that COTA has. She says they are proactively curated and done on the indication in oncology.
  • [05:45] What led COTA to develop Vantage products? — There are two main reasons why COTA decided to develop these Vantage products. Miruna says, “We’re always looking for number one, numbers, large data sets, and number two, they didn’t have the time to really wait for curation to occur. […] That led us to developing proactively these larger data sets that we can literally get off of the shelf. And so these Vantage level products are very large data sets that are constantly growing all the time and can be licensed because of that.”
  • [07:44] Vantage data sets help contextualize clinical trial data — When going into a critical trial, we need to understand the population first. That’s where Vantage data sets help.
  • [08:45] Vantage data sets also help identify subpopulations of interest — Miruna explains, “Another area is market analysis to inform the discovery and identification of new drugs for unmet needs.”
  • [11:06] Discussing the post-approval stage of the process — Vantage products can be interrogated across the entirety of the life cycle of drug development, even post-approval. Miruna talks about how these types of data sets can augment and even replace some of those post-approval studies. She says, “These types of data sets can actually augment, if not replace, some of those post-approval studies because we are literally adding different patients to these data sets as they come into the clinics, and so you are seeing these patients very close to real time.”
  • [12:32] You can use Vantage products in the commercialization space — Miruna talks about the potential use of Vantage data sets in the commercialization space. She explains, “For utilizing Vantage level data in the commercial space, you can validate your commercial strategy for product launches in the real world. You can actually support your label expansion, clinical trials, and your life cycle management work, and potentially even look at the safety considerations that you have on not just your label but also your patents.”
  • [14:18] Who’s typically using COTA’s data? — Miruna says that each use case has a different type of user.
  • [17:18] COTA’s Vantage product is currently available for seven types of cancers — Miruna says that COTA’s Vantage product is currently available for AML, DLBCL, CLL, EFL, MCL, multiple myeloma, and MDS.
  • [18:06] COTA has done a great job of utilizing data for research purposes — Miruna talks about the benefits of working with COTA’s Vantage product. She says, “We have an excellent reputation here. The data sets are much more complete and very much regulatory grade. Every single product that we put out there is regulatory grade.”

Key Points

  • We need more deeply curated, targeted oncology data sets. The healthcare space produces a tremendous amount of data that has the potential to change the industry. But these data sets need to be meticulously curated into meaningful information.
  • What is COTA’s Vantage product? COTA offers different data products, one of them being Vantage. Miruna says that these are large and proactively curated data sets that are epidemiologically relevant and done on the indication in oncology. So what makes COTA’s Vantage product different? Miruna explains, “What folks don’t know is that our Vantage data sets — which you can license, and you can get for a researcher for any purpose — are also regulatory grade. So, in fact, if you can find the patients in the Vantage data sets that you need for, for example, an external control arm — you can take them directly from there. And as you’re licensing that data set, you can use it across a realm of different possibilities in the drug development process.”
  • Each use case has its own type of user. Miruna talks about different types of users for each use case. She says, “For post-approval, again, health economics and outcomes research really comes in very deep here. So these folks are constantly getting asked lots and lots of questions by many stakeholders, and so, having the ability to tap into a data set like our Vantage products — these large, proactively curated data sets — at the click of a button is very important for them because many of those questions that they’re getting asked need to be answered immediately.”