The Advanced Research Projects Agency for Health (ARPA-H) is experimenting with AI to accelerate technology and outcomes across the sector, the head of ARPA-H said on Thursday.
According to the agency’s Director Renee Wegrzyn, ARPA-H is leveraging AI for everything from detecting ransomware vulnerabilities in hospitals to replacing drug experiments on animals with more human-like technology models.
“For ARPA-H, I think it’s the promise of what does the future of health look like that’s completely different? How do we accelerate not just cool technologies, but actually outcomes? How do we keep people from becoming patients in the first place? What are those investments,” Wegrzyn said during a Washington Post Live event on June 13. “Two years ago, we launched the agency in order to make those investments to get us there.”
Wegrzyn highlighted ARPA-H’s recent launch of the Universal PatchinG and Remediation for Autonomous DEfense (UPGRADE) program, which will leverage AI to defend hospital environments against cyber threats.
“UPGRADE … is looking at autonomous AI systems to help patch vulnerabilities to prevent ransomware attacks from taking down hospitals,” she said. “These are big things that have big implications that we don’t have technologies yet to address. So those are some of the investments that we’re going to be making.”
Looking towards the future of AI in healthcare, Wegrzyn said ARPA-H is hoping to take drug discovery from a process that takes years to one that takes just months.
“What if we can completely replace animal models with models that actually look like a human and behave like a human in those studies,” she said. “If you stack all of those innovations on top of the other you can take drug discovery and bringing that … from something that takes years to something that may take just months, and really before you even start an experiment, be able to predict your success in a much better way.”
“At ARPA, what we would do is break that down into the projects and the transactions that we need to invest in to make that true,” Wegrzyn added.
The agency lead highlighted some of the projects ARPA-H currently has in the works related to drug discovery leveraging predictive AI.
The ML/AI-Aided Therapeutic Repurposing In eXtended uses (MATRIX) project intends to use AI to rapidly pinpoint and validate existing medications to treat diseases that currently have no therapies.
On the generative AI side, Wegrzyn highlighted ARPA-H’s Antigens Predicted for Broad Viral Efficacy through Computational Experimentation (APECx) program, which will leverage AI to help design vaccines that target many viruses at once.
“We don’t know the limits of this technology and if it will even work for the task at hand,” Wegrzyn said. “A lot of what ARPA’s [job] is demonstrate the art of what’s possible, and de-risks that, and so it really is a series of hypotheses that we’ll be testing in these programs.”
“These are big moonshot questions,” she continued, “We might not hit the moon on these but if we hit low earth orbit, maybe there will be some learnings that really advance the state of the art.”
