How COTA and Komodo Health Combine Real-World Datasets for Better Patient Insights

Every day, real-world datasets help Life Sciences companies answer important questions about how patients are treated and how payers cover medications. And while siloed types of real-world data (RWD) — including electronic medical records (EMRs) and claims — can be useful in this effort, linking these types of datasets together can generate even more powerful and complete evidence about patient journeys and outcomes. 

Recently, Komodo Health and COTA teamed up to link COTA’s high-quality oncology data with Komodo’s vast Healthcare Map™ — making it easier than ever to combine COTA’s deep clinical cancer information with data products from Komodo or its curated network of partners. This type of collaboration taps into deeper layers of intelligence about patient communities and gives a more robust view of cancer patient journeys and outcomes for Life Sciences researchers. 

Komodo CEO Arif Nathoo, MD, and COTA CEO Miruna Sasu recently sat down to discuss the emerging era of accelerated evidence generation, better decision-making, and improved patient outcomes made possible by combining high-quality sources of RWD. 

Responses have been edited for clarity and length. 

Q: What is the value of RWD for Life Sciences companies? 
Miruna: Life Sciences organizations use different types of RWD in different ways across the company and the drug development cycle. Compared to searching for answers in published literature — the traditional way many teams search for the answers they need — asking a question in a specialized database with the right analytic tools reduces research timelines to just two days, down from six to nine months. 

In the discovery space, deep clinical, genomic, genetic, and demographic data help researchers understand patient populations as they test molecules against different targets. 

For example, once a molecule moves into clinical trials, RWD can help identify the patient populations to include in a trial based on their biology and likelihood to benefit from a treatment. Rather than “throwing spaghetti against the wall” and enrolling based on broad characteristics, RWD can guide trial design and increase the probability of success by focusing efforts on the right patient populations. Also, during phase 1 safety studies, RWD can reveal safety signals in the data that show whether a real-world patient has a better outcome with one treatment versus another.

After a drug is on the market, Commercial teams use large claims datasets to observe how a drug is prescribed, used, and paid for and its impact on patients in the real world — analyses that can fulfill post-marketing regulatory requirements. Some are starting to use EMRs and genomics datasets to better understand trends in patient outcomes. Where Phase 4 studies or chart reviews once took two to three years, the right data can power evidence generation in just one week. 

Q: What challenges do Life Sciences companies face when working with RWD, and how can we address them?
Arif: A patient’s journey through cancer care creates a tremendous amount of data. Through our work, we’ve observed that many Life Sciences teams may not know what datasets to use for what purpose. Many also lack awareness of what data is even available to them or what they can achieve by combining different datasets for analyses. 

Each dataset allows a user to answer a specific set of questions, but combined datasets can reveal so much more nuance. For example, by combining deep genomics data with EMR and claims data, you can generate real-world evidence that answers questions across a product’s life cycle, from a phase 1 study to post-marketing commitments. 

Five years ago, this intersectionality of datasets wasn’t possible. Today, it’s becoming the norm, and it’s driven forward by partnerships like the one between Komodo and COTA. 

Miruna: Especially in large pharma organizations, people in different functions often rely on a subset of RWD sources. In the clinical trial realm, trialists often use EMRs to inform trial design, but they’re less comfortable working with claims. But by combining information from the EMR, claims, and genomics, researchers can learn more than ever before.  

In the drug discovery space, for example, our data partnerships have enabled us to curate the biomarker data that discovery teams are used to while adding deep genomics data like whole-exome sequencing. When different types of de-identified datasets are linked, we can see an end-to-end picture of a patient’s health journey. 

Q: Could you share an example of a study that helped move the needle on cancer treatment and care by using a longitudinal joined dataset? 
Miruna: During my time in large pharma organizations, I held a central function that involved acquiring datasets for teams across the company. Most often, drug development leads came to me needing data to address two questions: how a physician treats a patient, and how much it will cost. 

These are important questions to answer, as they indicate whether your drug will be useful to patients and have a place in the market — key things to know before investing an average of $1.7 billion to develop a new drug. Teams can answer questions about treatment patterns and costs in a piecemeal way using various datasets, but it’ll take time. If they have all the necessary information captured in linked datasets, it’s much easier and faster to answer the question. 

How has the evolution of healthcare data and technology impacted the industry’s ability to accelerate new breakthroughs for patients? 
Arif: For too long, the process of collecting data and extracting meaningful information from it has been incredibly complex and costly. Many healthcare companies are massively underutilizing the full potential of RWD and still rely on piecemeal or manual analytics. It’s not an effective or scalable way to make decisions or accelerate progress for patients. 

But with the volume and quality of data available today, technology is finally primed to play a stronger role to drive fast, reliable insights. Our MapEnhance™ model is a great example of the technology-enabled systems that can now bring specialized datasets together with far greater speed and agility than was possible even two years ago. This next-gen approach to data and technology is already ushering in a new era of innovation and discovery, empowering the industry to deliver more personalized, efficient, and impactful care to patients.

To see more articles like this, follow Komodo Health on X, LinkedIn, or YouTube, and visit Insights on our website.