Using Data Analytics to Speed Up Clinical Drug Trials

Share this post:


Lars-Olof Eriksson, EVP, ICON plc

By Lars-Olof Eriksson

I have been involved in clinical drug development for over 35 years and it’s gratifying for me to see the progress that has been made to help people who are stricken with various diseases to live longer and healthier lives.

For me, this is personal. Two of my children have Type I diabetes, and I feel immensely fortunate that they have benefitted from advances that transformed diabetes from a debilitating and too-often fatal disease into a manageable condition.

Now, I believe, medical science is on the cusp of another major step forward. Using advanced data analytics–including IBM Watson–we have the potential to cut in half the time it takes to bring amazing new drugs to market.

ICON, based in Dublin, Ireland, is a global provider of outsourced development services for the pharmaceutical, biotech and medical device industries. Our focus is on clinical development and implementation of trials. On behalf of our industry clients, we create protocols and operational plans for trials, identify and select investigators and support recruitment of patients in multiple countries, manage the trials and prepare reports detailing the results.

We have long prided ourselves in using the most sophisticated medical informatics technologies available to our industry. Today, we’re entering into a partnership with IBM Watson Health to pilot a new system for managing clinical trials.  Hosted in the IBM Watson Health Cloud, the system is something like an online dating service. It helps improve the speed and accuracy with which we identify the most appropriate patients and investigators for each trial we manage.

Watson Health Cloud contains records from nearly 100 million patients coming from multiple healthcare providers. It draws on a wide variety of data about each patient, including symptoms, genomic data, test results, diagnoses, treatments and outcomes.

Until now, the process of selecting investigators and recruiting patients was slow and expensive. Organizations like ours throw a wide net and manually review the cases of a large number of patients before focusing in on the several hundred that we include in a trial. Typically, 50-60 percent of the initial patients we select for screening don’t qualify for the trial in the end. Using cognitive technologies to more accurately screen candidates, we hope to push that down to 20-30 percent.

We’re going to use IBM Watson Health Cloud in combination with our protocol optimization service, where our professionals write and implement scientifically and operationally sound protocols. Because of the wealth of detail in the Watson Health Cloud patient records and the sophisticated analytics tools, we’ll be able to select the best study design and to make protocols easier to implement, shortening the time it takes to conduct the trials by up to 50%.

Today, it typically takes around 6-12 months  to prepare  and start up  a global phase III drug trial and at least another 12 months to enroll  perhaps 600-800 required patients. If we can reduce that to half the time, it would have a huge impact on the industry’s ability to provide new promising  drugs to  healthcare and patients in need.

I want to return to the idea of the clinical trials “dating service.” The most amazing feature of the Watson technology is that it enables us to match patients against dozens of protocols at a time, rather than being limited to one-off comparisons. So, using a very smart computer, we’re augmenting the intelligence and extending the reach of our top analysts and clinicians–the human matchmakers. This kind of technology advance represents a huge breakthrough for my children, and for yours, and for generations to come.

More stories

Watson Anywhere: The Future

(Part 3 in a Series) There’s a paradox in the world of AI: While it’s the largest economic opportunity of our lifetime (estimated to contribute $16 trillion to GDP by 2030), enterprise adoption of AI was less than 4% in 2018. A recent Gartner survey said that the 4% in 2018 has now grown to […]

Continue reading

The 3 Beachheads of AI

(Part 2 in a Series) We have been partnering with and assisting clients on their data needs and strategies for years. It’s clear that data and AI are two-sides of the same coin; in fact, this understanding spawned the AI Ladder concept. We’ve developed skills training in the areas of data science and machine learning; […]

Continue reading

IBM Watson: Reflections and Projections

(Part 1 in a Series) AI has gone through many cycles since we first coined the term “machine learning” in 1959. Our latest resurgence began in 2011 when we put Watson on national television to play Jeopardy! against humans. This became a cornerstone event, demonstrating that we had something unique. And we saw early success, […]

Continue reading