From Digital to Data Science

Srinivas Karri
Director of Product Strategy

Despite repeated reminders from those in good authority, it appears there is still significant room to improve my health. Whenever I see my physician, I'm reminded that I perhaps should eat a little bit better, exercise more regularly, and get my full allowance of rest. To help me on this journey, I've invested in technology and daily habits to keep me on the path.

It is, of course, the cumulative effects of these individual habits that ultimately should put me on a trajectory heading to long and productive life. As my physician politely suggests in terms of a clinical pathway, the outcome is not optimal. This, of course, is great in theory and, having some idea of my future trajectory, should help me stay on track.

In the broader context of healthcare, as medical practitioners increasingly seek to provide proactive management for their patients' health, new digitally enabled therapies are being developed that consider disease progression and early preventative measures. As an example, the progression from a pre-diabetic, to a diabetic, and then to a diabetic with associated medical conditions is well understood and generally predictable. As the disease progresses, perhaps as a result of inadequate insulin control, complications, such as foot ulcers, retinal damage, and cardiovascular events can create life changing circumstances dramatically reducing the quality-of-life.

Treating these types of diseases before they progress to more costly and complex states offers significant benefits as early intervention can have a disproportionate benefit over time. It is with this hypothesis that clinical R&D is now developing therapies that not only treat the condition, but also support proactive and predictive disease management to reduce the likelihood of downstream complications. Taking a digital approach by identifying, measuring, and quantifying multiple real-world data streams, it is possible to demonstrate drug efficacy with potentially small populations over a shorter period of time. And, in the context of managing the overall condition, this should provide significant cost-benefits.

Under these winds of change, the role of the clinical data manager is evolving. As clinical R&D is connecting new data streams into the clinical data funnel, it is becoming necessary for the custodian of clinical data to develop new capabilities to manage, distribute, and interpret this information. As the new role of the clinical data scientist emerges, it requires a whole new set of capabilities to support the analytics and the interpretation of highly variable data, at scale and obtained through real-world conditions.

Be the first to comment

Comments ( 0 )
Please enter your name.Please provide a valid email address.Please enter a comment.CAPTCHA challenge response provided was incorrect. Please try again.