Ksana Health Awarded ARPA-H Contract to Build a Behavioral Health Foundation Model

Multi-institutional initiative aims to transform behavioral health through AI, leveraging smartphones and electronic health record data to enable earlier detection and more effective proactive intervention

EUGENE, Ore., May 13, 2026 /PRNewswire/ -- Ksana Health Inc. today announced it has received a contract award from the Advanced Research Projects Agency for Health (ARPA-H) under their EVIDENT initiative to lead a multi-institutional effort titled "Building a Behavioral Health Foundation Model." The project will develop a Large Health Behavior Model (LHBM), a new class of artificial intelligence designed to advance the prediction, prevention, and management of mental health and substance use disorders.

The total agreement is valued at up to $17.9 million, with $5.1 million in base funding currently obligated and additional options for scaled phases of work. Ksana Health leads the project in partnership with Providence Health & Services, MedStar Health, and the University of Washington.

"Behavioral factors contribute to 90 percent of the nation's $4.9 trillion in annual health expenditures, yet we still rely on fragmented, episodic approaches to detection and intervention," said Nick Allen, PhD, CEO of Ksana Health and Principal Investigator on the project. "This project will harness the sensing capabilities of people's personal smartphones and link those behavioral signals to health records at scale. The goal is to build a foundation model that can enable a new era of proactive, personalized behavioral healthcare."

A Moonshot for Behavioral Health

Despite the enormous burden of behavioral health conditions, which contribute to an estimated eight percent loss of annual GDP, the current tools for screening and early intervention remain limited. Measurement-based care is rarely implemented in behavioral health settings, and the approaches that do exist rely heavily on subjective self-report. Patients and providers navigate a time-consuming process of trial and error to find effective treatments, with clinicians often unable to reliably predict patient outcomes using clinical judgment alone.

The LHBM project aims to change this by developing AI models trained on continuous behavioral data from smartphones and wearables, including patterns of physical activity, sleep, mobility, social connection, and language use linked to large-scale electronic health records. The approach draws on three converging technological advances: the ability to measure behavior at population scale through ubiquitous mobile devices, the aggregation of digitized medical records, and breakthroughs in foundation model architectures that can learn powerful representations from multi-modal data.

A Multi-Institutional Collaboration

The project brings together complementary expertise across healthcare delivery, computer science, and digital health technology. Researchers from Providence Health & Services and MedStar Health Research Institute will lead research participant recruitment, bringing geographic and demographic diversity to the study. Scientists at the University of Washington's Paul Allen School of Computer Science & Engineering will spearhead the computational modeling effort, drawing on deep expertise in behavioral data science and foundation model development.

Ksana Health's EARS platform will serve as the primary data collection infrastructure, capturing multi-modal behavioral signals from both Android and iOS devices.

Ethics and Lived Experience at the Center

A defining feature of the project is its commitment to integrating ethical oversight and the perspectives of people with lived experience from the outset. The Lived Experience and Ethics Panel (LEEP) will bring together individuals with personal experience of mental health challenges alongside experts in AI, bioethics, and healthcare to evaluate model development plans, assess potential biases, review training data, and develop guidelines for safe and effective use. The panel's guidance will be woven into every major phase of the project.

"We believe that the people most affected by behavioral health conditions must have a meaningful voice in shaping the tools designed to help them," Allen said. "The LEEP panel is not an afterthought—it is built into the project's structure from day one."

Looking Ahead

The project will unfold in phases, beginning with a proof-of-concept study and pilot data collection, then scaling to tens of thousands of participants across multiple health systems. The team intends to make the resulting model available to the broader scientific and clinical community, with appropriate safeguards developed in consultation with the LEEP panel.

"This initiative augments Ksana's current efforts to shift behavioral healthcare from episodic, subjective assessment toward continuous, data-driven health promotion, reducing healthcare spending, improving quality of life, and reaching populations that currently lack access to effective behavioral health support," said Tony Scripa, COO of Ksana Health and Co-Investigator on the project.

About Ksana Health

Ksana Health Inc., based in Eugene, Oregon, develops digital health technology that leverages sensing capabilities from consumer mobile devices to advance behavioral health research and rapidly translates it into scalable clinical impact. The company's EARS platform is the leading research infrastructure for mobile sensing and digital phenotyping, while their Vira platform applies these capabilities in clinical settings to support continuous, evidence-based care. For more information, visit ksanahealth.com.

SOURCE Ksana Health