LLNL Study Finds ALS Drug Hope via AI, Veteran Records

Researchers identify existing medications that may prolong survival for people with ALS using one of the largest electronic health record datasets ever assembled for the disease.

Mar. 12, 2026 at 3:32am

Got story updates? Submit your updates here. ›

A Lawrence Livermore National Laboratory (LLNL)-led team of scientists and computational engineers has identified several existing medications that may be associated with longer survival in people with amyotrophic lateral sclerosis (ALS), using one of the largest electronic health record datasets ever assembled for ALS. The study analyzed health records from more than 11,000 U.S. military veterans diagnosed with ALS between 2009 and 2019 and treated within the Veterans Health Administration.

Why it matters

The work was motivated by recent setbacks in ALS drug development, including the withdrawal of the drug Relyvrio from the market in 2024 after a larger follow-up trial failed to show benefit. The large amount of experience with treating ALS in the VA system provided an alternative approach to identifying medications for the disease.

The details

By combining causal-inference methods with machine learning (ML), researchers evaluated 162 medications to identify drugs prescribed for other conditions that were associated with meaningful differences in survival. The analysis identified 27 medications associated with statistically significant changes in mortality risk, with multiple drugs within the same therapeutic classes - including statins, phosphodiesterase type 5 inhibitors and alpha-adrenergic antagonists - showing similar associations with prolonged survival.

  • The study analyzed health records from more than 11,000 U.S. military veterans diagnosed with ALS between 2009 and 2019.
  • ALS was formally recognized as a service-connected disease in 2009, leading to a sharp increase in veterans receiving ALS care within the VA system.

The players

Lawrence Livermore National Laboratory (LLNL)

A U.S. Department of Energy national laboratory that conducts research in energy, national security, and the environment.

Priyadip Ray

The LLNL principal investigator and a research scientist in the Computational Engineering Division.

Braden Soper

An LLNL data scientist and co-author of the study.

Veterans Health Administration

The health care system of the United States Department of Veterans Affairs, providing medical services to eligible U.S. military veterans.

Stanford University School of Medicine

The medical school of Stanford University, a private research university in California.

Got photos? Submit your photos here. ›

What they’re saying

“We realized that the large amount of experience with treating ALS in the VA system could provide an alternative approach to identifying medications for the disease.”

— Priyadip Ray, LLNL principal investigator (Mirage News)

“Our team developed a set of methods that combine rigorous statistical techniques with modern machine learning to isolate causal effects at the population level, even when data aren't collected in a controlled way.”

— Braden Soper, LLNL data scientist (Mirage News)

What’s next

The researchers are working to release their software pipeline as open source so that other researchers can apply the tools to their own datasets, diseases, and interventions.

The takeaway

This study highlights the potential of leveraging large-scale electronic health record data and advanced computational techniques to identify existing medications that could be repurposed to treat rare diseases like ALS, providing a promising alternative approach to traditional drug development.