Researchers at the University of California, Berkeley School of Public Health are working to accelerate the development of life-saving drugs by using real-world health data and advanced statistical methods, according to a March 26 announcement. The Center for Targeted Machine Learning and Causal Inference (CTML) at UC Berkeley is leading this initiative.
The effort comes as millions worldwide suffer from diseases without cures, including many cancers, Alzheimer’s disease, Parkinson’s disease, and rare illnesses affecting over 30 million Americans. Drug development is often slow and costly; the National Institutes of Health estimates it takes an average of 12 years and costs between $173 million and $2.6 billion for a new drug to reach approval, with only about 12% making it through regulatory review.
CTML aims to address these challenges by applying causal inference—a scientific approach that seeks cause-and-effect relationships—and targeted learning, which combines machine learning with biostatistics. Dr. Michael C. Lu, Dean of UC Berkeley School of Public Health, said: “Clinical trials, particularly large Phase 2 and 3 trials, are one of the biggest reasons it can take more than a decade and over a billion dollars to bring a new drug to patients. CTML is working with the FDA and pharmaceutical partners to help change that.” He added: “By combining the power of machine learning with the rigor of modern biostatistics, our researchers are developing new methodologies—such as using real-world health data to simulate placebo trials—that could make clinical trials faster, more efficient, and more affordable while maintaining the highest standards of scientific rigor.”
Lu also said: “This is exactly why public research universities matter. CTML exemplifies how the intellectual firepower of Berkeley can help solve some of the world’s most pressing problems.”
The center’s work builds on policy changes introduced by Congress in December 2016 through the passage of the 21st Century Cures Act. This law prompted regulators like the Food and Drug Administration (FDA) to consider using ‘real-world evidence’—clinical data from electronic health records or digital sources—to support drug approvals or post-market studies.
Drs. Maya L. Petersen (professor at UC Berkeley), Mark van der Laan (professor at UC Berkeley), Alan Hubbard (professor at UC Berkeley), along with other collaborators have led workshops for FDA staff on these techniques since Van der Laan was first approached by FDA in 2010.
In recent years CTML launched major collaborations such as its Joint Initiative for Causal Inference (JICI), funded initially by Novo Nordisk in 2020 with $3.2 million; JICI now works with Copenhagen University, Oxford University, Harvard University, University College London among others on statistical methods that integrate observational data into clinical trial analysis.
The success led Gilead Sciences in 2024 to contribute $1.5 million over three years for further research into best uses for real-world evidence.
