Real world data (RWD) and real world evidence (RWE) are playing an increasing role in health care decisions. There are multiple data providers and institutions as well as various analytic companies that are integrating data and using technology to build platforms. Data sources can include: claims data, electronic medical record data, genomics data, imaging data, sensors, wearables and many others.

This data has the potential to allow us to better design and conduct clinical trials in the health care setting to answer questions that were previously not feasible. In addition, with the development of sophisticated, analytical tools and technology capabilities, we are better able to analyze these data and apply the results of our analyses to medical product development and approval. The first time building a trial using real-world evidence (RWE) analytics can be daunting. Below are four easy steps to make the big data problem a little smaller.

Step 1: Understand the data, attributes and quality of the data

In order to work on a real world analytics project, a team must understand the data sources. Data attributes include size of the data, variables available, time window, unique identifiers etc. They can be anything from large sets of heart-rate data from wearables to information in electronic health records.

For example, a lymphoma study required using patient data from the European Union which required a careful appraisal of each country’s available data sets. A prioritization framework based on access and attributes was created, weeding out the weaker options to arrive at the data sources that were the best fit for the project.

Step 2: Build an interface of different data variables of interest

Once data sources are selected and prioritized, it’s important to begin finding which metrics are of most value and how they relate to other metrics in other sets. That’s how researchers can begin building relevant connections. The process can include de-identification and linkage across data sets like electronic health records and claims data. Encryption, meanwhile, can help protect privacy.

For example, a rare disease real world study required linking claims data sets with EMR and lab data via a patient ID. Patient demographics, number of doctor visits, prior history of medication from claims, doctor’s notes, reasons for discontinuation from EMR and lab values from lab data were linked up to study patient profiles who suffered from the rare disease.

Another example is to use the claims data to map the patients with a particular disease and use it to find patients for a clinical trial.

Step 3: Integrate vertical and horizontal aspects of the big data platform

The objective of this stage is to “understand the unique needs and attributes for the program.” The process involves identifying the range of applications that platform could be useful for, and to whom. There are four specific areas: identifying needs of research partners, understanding the disease state at hand (through things like population size, patient variables, and treatment options), identifying the platform’s key target audience, and other existing data sources on the problem.

Step 4: Apply enterprise-level analytics

Once all the RWE has been contextualized, an interface has been built, and its potential understood, the analytics queries can begin. As an example: A Sankey diagram can fluidly trace more than 5000 major depressive disorder patients through dozens of potential treatment combinations. The work answers a powerful combination of questions, including who the patients are, what the drivers are behind treatment decisions, and how patients have moved across the lines of therapy.

The deft use of the four-step approach can allow researchers to reach a great degree of specificity in their cohorts. For example, a study from previous work began with 70,000 potential eligible patients. After applying every possible inclusion and exclusion criteria, it whittled it down to little more than 200 highly compatible patients, allowing for a well-tailored trial.


Jyotsna Mehta

Principal and Owner

KEVA Health

Boston, MA


About KEVA Health

KEVA stands for Knowledge, Evidence, Value and Access. The company specializes in generating Knowledge that produces Evidence, builds Value of products and allows for Access and reimbursement. This includes strategic consulting services, value and access product strategy plans, data analytics advisory services, real world evidence studies, patient reported outcome studies, economic modeling, dossier, and publication services.