Real World Evidence is here
Historically, decisions about drug efficacy and safety prior to launch have been driven strictly by the results of randomized controlled trials (RCTs). Today, however, evidence from real-world settings (outside of clinical trials) is more widely available, partly as a result of Healthcare’s move to a “pay for performance” model. Real World Evidence includes insurance reimbursement data, pharmacy data, Electronic Health Record (EHR) data, and patient-powered data.
And yet…
According to Dr. Jennifer Graff, Director of Comparative Effectiveness Research at the National Pharmaceutical Council, only 1 in 3 Managed Care organizations consistently use real-world evidence to inform their decisions.
Managed Care Organizations are not the only ones struggling to make sense of Real World Evidence. Pharmaceutical companies, government agencies, payers and providers are faced with the challenges of understanding the evidence, analyzing it, and, more importantly, driving decisions based on it.
The question is why. What are the barriers to using Real World Evidence?
The Network for Excellence in Health Innovation (NEHI), in its September 2015 Issue Brief titled Real World Evidence: a New Era for Health Care Innovation, outlined a few barriers to using RWE. Of these, data quality is at the top. According to the NEHI, “many researchers become ‘data janitors’, forced to ‘clean’ gaps and inconsistencies in data through methods that may not yet have wide acceptance for statistical validity.”
Challenge 1: Data quality
In this new world of Real World Evidence there is a large variety of data that needs to be collected and analyzed. In particular, semi-structured and unstructured data, some of it coming from the patients and their social networks, create a formidable challenge for Data Scientists. Complex data types (i.e. video and images) yield large volumes of data to be analyzed. But it’s not the amount of data per se that creates the challenge. The true challenge is analyzing unstructured and semi-structured data, and doing it in a way that yields scientifically relevant insights.
Challenge 2: A new way of thinking
Big Data analysis is increasingly owned by Data Scientists. This new breed of data analysts is in ever-increasing demand around the world. According to McKinsey & Company, there will be 140,000-190,000 data scientist jobs that go unfulfilled by 2018.
A Data Scientist often has a background in Statistics, Mathematics or Computer Science. Her job is not simply to uncover previously hidden patterns and correlations. A Data Scientist has to put the results of her analysis into context, and to identify trends. To do this, she needs to understand human behavior. And this requires a new way of thinking. It requires a new, whole-brain approach.
What does this mean for Real World Evidence?
With the right analytical brainpower and technology, a number of previously untenable results can be made available in a matter of weeks. Applications of Real World Evidence analysis:
- Recruiting the right cohorts of patients for clinical research
- Identifying drug and medical device safety risks quicker and with more accuracy
- Determining the effectiveness of pharmaceuticals when used among co-morbid patients
- Identifying long-term adverse drug effects, which leads to better decisions about future clinical trials.
Despite the technical and cultural challenges of extracting insights from such disparate data sources, Real World Evidence promises to transform the healthcare ecosystem. Not because Data Science is a fancy term, and not because there’s lots of data involved. The real promise of Real World Evidence is in creating better healthcare for us all.
See how Saama is accelerating Real World Evidence initiatives with analytics.