Flatiron Health, which has built an oncology-focused EHR network and de-identified database with more than 4 million patient records, recently announced a milestone of more than 1,000 research publications using its real-world data derived from EHR. Neal Meropol, MD, vice president of oncology research at the company, recently spoke with Healthcare innovation on the expansion of the types of research done with their data.
Founded in 2012, Flatiron is an independent subsidiary of the Roche Group. Collaborate with partners in academic institutions, policy groups, regulators and biopharmaceutical companies. Some key academic collaborators include Penn Medicine’s Abramson Cancer Center, Yale School of Medicine’s Yale Cancer Center, University of Utah Heath’s Huntsman Cancer Institute, and Temple Health’s Fox Chase Cancer Center.
Meropol, a medical oncologist, clinical investigator and outcomes researcher, oversees Flatiron’s clinical teams that support retrospective and prospective evidence generation.
Health innovation: in health innovation, We focus on writing on the healthcare provider side and not so much on the life sciences companies or drug development. But obviously the two worlds are linked, and Flatiron’s work is one of the places where that happens. He has been in Flatiron for seven years. What are some of the significant changes you’ve seen in terms of the company’s capabilities?
Meropol: In many ways, it has been extraordinary, but all within the context of an ongoing mission, which has been to improve and prolong lives by learning from the experience of each person with cancer. The way we do this has remained largely unchanged over this time, and that is by providing software and services to practicing oncologists, where we are EHR providers, but also by curating data largely derived from electronic medical records that They are collected during routine care to obtain insights that help address quality and policy of care, and that help accelerate drug development and contribute to a learning healthcare system.
HCI: So what has changed in the last five years?
Meropol: When we started, our data was most commonly used for market monitoring: how are new treatments being adopted? So the customers, in a way, were commercial arms of the biopharmaceutical company. But we have evolved to have a much broader scope of research areas to which our data is now applied. That includes academia, government, NCI and regulators, nonprofits like the American Cancer Society and Friends of Cancer Research. Having a broader range of real-world data consumers from Flatiron opens avenues for all types of applications. Additionally, we now no longer rely solely on electronic health record data; We now have links to other external data sources, such as mortality databases, claims data, digital images, and genomic data. That really opened the door to a lot of different types of knowledge that we can gain.
HCI: Does expanding the types of research include things like looking at health equity and how people receive care in many different types of settings?
Meropol: Exactly. Applications of our data today not only include understanding the adoption of new therapies, but also understanding real-world outcomes associated with different patterns of care, the ability to make comparisons of effectiveness, and understanding differences. in approaches that may not be amenable to a prospective clinical trial.
We have worked with what are called natural experiments, looking at the impact of drug shortages on health care delivery and patient outcomes, and also looking at national policies, for example, Medicaid expansion and how that affects cancer care. We measure quality with data from Flatiron, looking at how people use biomarker testing, whether patients receive biomarker-directed care, and how patients are treated at the end of life.
We’ve looked at many different areas of health equity, including how quickly patients initiate care, whether the adoption of new innovations is equitable across different groups, whether the location you receive care, whether it’s an academic setting or community, affects the care you receive. receive. The data is very rich in terms of what is possible.
HCI: Has the number of oncology practices or academic medical centers using Flatiron OncoEMR or other tools continued to grow? And the OncoEMR continues to evolve with new features?
Meropol: Our footprint in community oncology and academia continues to grow. In terms of new features in OncoEMR, something that’s really notable is that over the last few years we’ve been developing decision support tools. We have an app called Flatiron Assist, which helps guide appropriate treatment selection based on patient characteristics, and this has been quickly adopted by our OncoEMR practices in an effort for users to improve the quality of their care and expedite their intake. of decisions.
HCI: We typically hear from academic medical centers that creating and updating clinical decision support rules is a complex governance task. So is this something you have to receive information about from the network?
Meropol: Two things: One thing is that, right out of the box, the Flatiron Assist solution is based on the National Comprehensive Cancer Network clinical practice guidelines. The second feature is that it is highly customizable, so practices can choose to customize Flatiron Assist recommendations based on their own practice preferences.
HCI: How about adding these AI writing tools to the EHR as well? Is that something Flatiron is working on?
Meropol: Yes, we have made ambient AI testing easier for practices that want to go in that direction, absolutely.
Also, one of the new areas that is really critical is that to take advantage of the data from the 4 million cancer patients that we follow, we have to find more efficient ways of sifting through unstructured information, and we are now routinely applying machine learning. and artificial intelligence to help with healing where performance is high quality, so that we can expand the number of patients about whom we can have meaningful information.
HCI: Could the ambient AI tool become smart enough to figure out what to include in the structured data and what to include in the narrative?
Meropol: There is a lot of discussion about what the electronic health record of the future will look like. Historically, electronic medical records were not created for research, but there are tools that allow for better capture of information at the point of care in a structured or usable format or applications that include billing for clinical care, but also applications for research, that would be good for everyone. and very enabling in terms of improving the quality of cancer care. So I think everyone is looking toward a future where that’s more possible, where that becomes a reality, but it’s not going to happen overnight, because EHR vendors like Flatiron are really focused on the workflows and ensuring we help clinicians provide the most efficient information. and high-quality care possible. And there is always the risk that implementing new technology will cause increased computer clicking, cause more burnout, and have unintended consequences.
HCI: Are clients working in community oncology practices different from people working in academic medical centers in the tool sets they want or need?
Meropol: Common drivers in community and academic oncology settings are that they attempt to provide the highest quality care to patients, but an important driver for physicians in an academic setting is career advancement. They may be more interested in participating in research and publishing the results, but I should note that the Flatiron Community Oncology Network has many practices that do clinical trial research and are very motivated to do so. Therefore, the incentives and desires to be able to provide cutting-edge care in the form of clinical trials exist both in the community and in the academic center. And one of the things that we’ve really developed over the last few years is providing software and services to community oncologists to better enable them to participate in clinical trials. That includes helping with patient matching for clinical trial recruitment, but also with transferring data from the electronic medical record to study databases. That’s why we have a tool called Clinical Pipe which is a data transfer tool for clinical trials, which reduces the burden on sites and allows more sites to participate in more studies than they otherwise could have participated in.
HCI: I remember there was an announcement of a Flatiron partnership with the Association of Cancer Care Centers to work on expanding access to that tool.
Meropol: Indeed, community oncologists are often very interested in developing their clinical research capabilities, but investments in clinical research at an academic center and in community practice can be very different. What we’re trying to do is help support the infrastructure to conduct research in routine care settings. That’s why we’re trying to align clinical trials with clinical care and, in doing so, make it a more routine approach to how patients are cared for.
HCI: Do you want to talk a little bit about your clinical trials network?
Meropol: At the highest level, we realize that data collected in routine care (what we consider real-world retrospective data) cannot answer all questions in oncology. There are certain research questions, certain evidence needs that require the collection of what we call intentionally collected information that goes beyond what is routinely collected, whether it’s measuring the dimensions of the tumor or making sure that the functional status of the patient is accurately documented prior to care. it starts. That’s why Flatiron has created a business where we will support the collection of prospective data from clinical trials, ideally for studies that are pragmatically designed and highly aligned with routine care.
Therefore, we are developing the capabilities to conduct clinical studies within the community setting. That includes working with sponsors on study design, using data from Flatiron to help inform study design, supporting patient identification for studies, and then supporting the data collection that we’ve talked about. We believe we have an opportunity to decrease the complexity of clinical trials that exist today through a pragmatic study design, but also a pragmatic operational design that will expand the accessibility of clinical trials for cancer patients.
