Customer Logins

Obtain the data you need to make the most informed decisions by accessing our extensive portfolio of information, analytics, and expertise. Sign in to the product or service center of your choice.

Customer Logins

How to train your data – integrating comparative effectiveness research (CER) into Big Data: Insights from ISPOR

23 June 2014 Tericke Blanchard

The role of big data in healthcare decision making was the central theme at ISPOR's annual meeting in Montreal earlier this month. The greater amount and availability of electronic healthcare data is creating new opportunities for partnerships to evaluate the comparative effectiveness of healthcare interventions. However, this also raises important issues, e.g. priority setting, data ownership, and when/how to communicate results, which could hinder stakeholder collaboration.

Overcoming these challenges was the subject of an ISPOR session I attended. Each presenter offered his or her own perspective (industry, academic, payer) for overcoming obstacles to generate evidence that has the potential to improve patient care. The first issue from the industry perspective: ensure that robust clinical information is a part of big data.

What is the role of RCTs? Randomized controlled trials (RCT) are the "gold standard" and must be a part of healthcare big data, Leona Markson (Merck), who took the industry perspective, said. She noted that CER in big data is relatively new and that RCT methods are usually more interpretable than CER methods. Inclusion of RCTs, although expensive to conduct, in big data could work in parallel with continued efforts to improve standards for CER and generate data that is useful for decision makers. A key element of this will be transparency, so the data can be evaluated.

Research motivations should be transparent To facilitate this, it will be important that the research agenda is well-defined and transparent. Robert Epstein (Epstein Health), who took the payer perspective, said the provider community has limited resources and is primarily interested in delivery of healthcare services. To improve collaboration with the health system, he explained, provide full transparency and support input on study questions, design, and interpretation of CER. One way to address this is to focus the research on health delivery issues rather than product-specific issues.

Sebastian Schneeweiss (Harvard Medical School), who provided the academic view, added that the issue of transparency is important to allow researches and/or patients to validate or refute the data, and also for bias reduction.

Data ownership: Payers vs. industry If cross-functional collaboration is essential to develop the CER agenda, data access must also be considered. Once a drug receives regulatory approval, the majority of the new information around its use will no longer be held by the product manufacturer, but by other stakeholders.

Manufacturers would likely expect greater access to the data collected in the healthcare system in exchange for research funding. This could be a way forward on academic/payer-industry collaborations in order to evaluate medical products within the same healthcare system where the data was generated.

It is clear there are a number of obstacles to overcome to improve cross-functional collaboration on the use of CER in big data. ISPOR showed there is great interest in evidence-based decision making and collecting data from more sources and developing shared policies and procedures to foster the development and interpretation of big data is a move in the right direction. As this area evolves, we will continue to look at the opportunities and challenges.



Follow Us

{"items" : [ {"name":"share","enabled":true,"desc":"<strong>Share</strong>","mobdesc":"Share","options":[ {"name":"facebook","url":"","enabled":true},{"name":"twitter","url":"","enabled":true},{"name":"linkedin","url":"","enabled":true},{"name":"email","url":"?subject=How to train your data – integrating comparative effectiveness research (CER) into Big Data: Insights from ISPOR&","enabled":true},{"name":"whatsapp","url":"","enabled":true}]}, {"name":"rtt","enabled":true,"mobdesc":"Top"} ]}
Filter Sort