Skip to Main Content

ARPA-H Sees Promise in AI with Newest Funding Projects

The agency is tackling initiatives around generative AI and machine learning for research in critical health issues.

Vaccination or drug concept image - panoramic banner
Photo Credit: ffikretow/ iStock

The Advanced Research Projects Agency for Health (ARPA-H) sees generative artificial intelligence as being a major catalyst to overcoming manual processes around addressing antibiotic resistance and addressing cybersecurity in the health care sector.

Identifying new antibiotics traditionally is a very manual process and requires extensive screening, ARPA-H Resilient Systems Mission Office Director Jennifer Roberts told GovCIO Media & Research in an interview.

The agency’s recent Transforming Antibiotic R&D with Generative AI to stop Emerging Threats (TARGET) project from this fall is funding research for using generative AI and deep learning to help speed the discovery and creation of new classes of antibiotics. This makes it a critical component to addressing antibiotic resistance that is a major cause of death globally.

“TARGET aims to close this gap by using deep learning to identify biomolecules with antibiotic and pharmaceutical potential and generative AI to broaden the pool of candidate molecules,” said Dr. Roberts. “Through these approaches, TARGET aims to identify 15 promising leads for new antibiotics, which would help replenish the global pipeline.”

Roberts said generative AI has numerous benefits across the health care ecosystem. Patients can use generative AI-powered chatbots to schedule their appointments. The tech can also help doctors take notes. It also has many applications for researchers

“Using generative AI, researchers can not only expand the pool of molecules that can be tested for antibiotic activity, but it can also be used to accelerate the development of these molecules into antibiotics for patients,” said Roberts. “With generative AI, there is also hope that researchers experience fewer dead ends in researching new antibiotics.”

AI for Health Care Cybersecurity

ARPA-H is also taking a close look at the need for cybersecurity in health care systems and identifying how AI can help. Roberts cited recent cyberattacks targeting digital health infrastructure in the need to develop straightforward and dependable solutions to protect patients’ data and access to care.

“These attacks have profound impacts across the health care ecosystem, and off-the-shelf software tools aren’t cutting it when detecting emerging cyberthreats and protecting our country’s care centers. We need rapid progress to close these gaps,” said Roberts. “In typical ARPA fashion, the agency is taking innovative steps to connect with experts at the forefront of using AI to detect and protect against cyberattacks, including ransomware attacks. This includes programs that use AI to detect ransomware vulnerabilities.”

One of those programs is the Universal Patching Intermediation for Autonomous Defense (UPGRADE) that ARPA-H launched earlier this year. UPGRADE gives health care facilities protection from ransomware attacks by automatically providing proactive and scalable updates to their IT systems.

The agency’s Digital Health Security Initiative (DIGIHEALS) is another project using AI to strengthen electronic health infrastructure and address vulnerabilities in data security.

There are other programs where ARPA-H is employing AI and machine learning to improve health outcomes including the ML/AI-Aided Therapeutic Repurposing in eXtended uses (MATRIX) project, which plans to build a machine-learning platform to rapidly pinpoint and validate existing medications to treat diseases that currently have no therapies.

Roberts also cited the Performance and Reliability Evaluation for Continuous Modifications and Useability of Artificial Intelligence PRECISE-AI program, which intends to develop capabilities that can automatically detect and mitigate AI-model degradation in clinical settings. PRECISE-AI is open for proposals until January 2025.

“One of the most exciting things about ARPA-H is that we don’t go into research with a predetermined focus on one cure, treatment or technology,” said Roberts. “Our programs are driven by the program managers who bring their ideas to the agency.”

Related Content
Woman typing at computer

Stay in the Know

Subscribe now to receive our newsletters.

Subscribe