November 10-15

The official news source of

ACR Convergence 2023

San Diego, CA

Home // Harnessing of Big Data to transform treatment

Harnessing of Big Data to transform treatment


2 minutes

An increasing amount of data is being generated across the continuum of biomedical research and patient care. Accessing and integrating those data is key to the idea of “precision medicine” and the ability to transform the process of treating and, ultimately, curing disease.

Atul Butte, MD, PhD

A special symposium on Tuesday afternoon, Utilizing Big Data to Advance Rheumatology, part of the Annual Meeting’s new TechMed sub-track, will feature one of the nation’s leading bioinformatics and medical technology experts, Atul Butte, MD, PhD, Director of the Institute for Computational Health Sciences at the University of California, San Francisco.

“We’re well into this mode in medicine now where we’re measuring and recording more and more things about our patients,” Dr. Butte said. “A lot of this data is already publicly available, and the scientists of the future, maybe even scientists of the present, have the potential to use this data to make amazing new discoveries — to find out why people get diseases, to find new ways to diagnose them sooner and new ways to treat those diseases.”

Dr. Butte will describe the computational tools and other resources required to convert “hundreds of trillions of points of molecular, clinical, and epidemiological data” into new diagnostics, therapeutics, and insights into both rare and common disease, including autoimmune and rheumatic diseases.

“There are enormous data sets on disease tissues from biopsies, for example, including those for rheumatology diseases,” he said. “Then, we have databases of drugs that we can use to combine with the disease databases. That might lead us to a drug that seems to match a disease, a drug that we didn’t know before might be useful to help us treat that disease.”

As the technologies for collecting, organizing, and warehousing huge amounts of data continue to evolve, an extremely important and growing source of “open data” is data collected from unpublished clinical trials.

“When clinical trials are run and they fail, for whatever reason, a lot of that data has historically been kept private,” he said. “We’re now starting to see that the FDA and other regulatory groups are requiring more and more data to be released to the public from all clinical trials.”