Skip to main content Skip to footer
Case study

The challenge

The stakes are high in oncology drug development: The mission—saving lives—is critical, but the process is costly and the competition is fierce. A major pharmaceutical research company focused on a full range of cancer treatments, including one for acute myeloid leukemia (AML), needed a quick and accurate method to process the massive amounts of data emerging from its own trials, from available research and from the Cancer Cell Line Encyclopedia. It engaged Cognizant, its long-time trusted partner, to consider ways to make the process of reviewing critical information on drug performance and patient outcomes more efficient.

Our approach

Cognizant’s Artificial Intelligence team applied its expertise in data science and analytics, alongside its experience in the life sciences industry, and built an automated process to analyze data in clinical trials research and during clinical trials, specifically for one AML treatment. Our solution uses text mining to automatically review more than 10,000 online resources, such as medical journals and scientific research publications. We leveraged an Agile development model to design and build an automated pipeline that intakes this vast range of disparate data, normalizes it, performs analytical processing and delivers easily understood reports on outcomes. The automated solution makes identifying optimal doses of drugs dramatically faster.

AI and data science improve clinical trial processes

Our data science solution helps our client improve what had historically been a manual, costly and laborious process for cross-referencing research from clinical trials on cancer drugs. It also lays the groundwork for use with a full range of other drugs for conditions ranging from Alzheimer’s to depression and schizophrenia. Our client’s journey ahead is clear: leverage its new automated, data science-driven pipeline for different treatments, and then incorporate machine learning, using AI to speed drug development while improving the safety and efficacy of its clinical trials.

20 days

to review drug outcomes, reduced from 20 months

Up to 4 years

trimmed from the full oncology drug development process of 10 to 18 years

8% to 10%

cost savings per patient in clinical trials