Tamr Achieves Premier Technology Partner Status With SnowflakeLearn More

Boosting R&D Outcomes with Historical Clinical Trials Data

life sciences research and development

Today it can take up to $2.6bn and 14 years to move a drug from “bench-to-bedside.” While over the past decades, our medical knowledge and research and development capabilities have advanced exponentially—drug development remains incredibly hard and costly. One of the most costly areas for pharmaceutical companies is clinical trials where sourcing participants and site selection dramatically add to costs and R&D timelines.

Like other industries, pharmaceutical companies are looking at data–specifically their historical clinical trials data–to help drive greater efficiencies, improve performance and reliability, and crucially accelerate time to trial.

We recently spoke with Mark Ramsey, former Chief Data and Analytics Officer at GSK about how companies can reuse their historic clinical trial data to accelerate modern day trials.

We also created a related ebook that outlines the seven steps for boosting R&D outcomes by using clinical trials data that Mark covers in his presentation.

You can read the entire ebook here, but here’s a snapshot of what you can learn:

Step #4: Take an Agile, DataOps Approach to Clinical Trials Mastering

Rationalizing clinical trial data is not a one-off project. Once you have access to the trial data you need to make sure that data stays current. In the case of clinical trials that means it is in CDISC format. The issue is standards like CDISC are always changing. In order to maintain a portfolio of clinical trial data (with potentially thousands of trials and billions of unique data points) you need an operational framework that ensures data accuracy and availability at scale. Enter DataOps.

DataOps is an agile framework for managing people, process, and technology in order to help data teams accelerate the analytic outcomes of data for the enterprise. Using DataOps helps mitigate problems like schema drift, better leverage technologies that allow for a high degree of automation (AI and machine learning (ML)) to keep data clean and current, and ultimately ensure that the best data is available to people who need it across the organization.