Atman Health Wins ARPA-H Award to Build Heart Failure AI

September 09, 2026
Atman Health was selected for an ARPA-H award to develop an agentic AI system for cardiovascular care, starting with heart failure.

Atman Health says in a press release it was selected by ARPA-H to develop an agentic AI system for cardiovascular care, starting with heart failure. The award is part of the ADVOCATE program, which will run for 39 months and focus on chronic cardiovascular disease management in the US. ADVOCATE has more than one lead performer: UpDoc announced a separate award under the same program on the same day.

The system will use a large language model to interpret medical records and communicate with patients by telephone and chat. A deterministic clinical engine will make decisions using more than 9,000 clinical criteria, 9,600 medication and indication pairings, 6,900 dosage adjustment profiles, and over 100 symptom triage flows. It will record the evidence and logic behind each recommendation and check exclusion criteria before proposing medication.

Atman plans to engage with the FDA during the first year, apply for an Investigational Device Exemption at month 12, and target a De Novo submission within 24 months. A single center study operating in shadow mode will precede those regulatory steps.

We hope you enjoyed this article.

Subscribe to AI Policy Brief

Weekly report on AI regulations, safety standards, government policies, and compliance requirements worldwide.

Market report

2025 Generative AI in Professional Services Report

Thomson Reuters

This report by Thomson Reuters explores the integration and impact of generative AI technologies, such as ChatGPT and Microsoft Copilot, within the professional services sector. It highlights the growing adoption of GenAI tools across industries like legal, tax, accounting, and government, and discusses the challenges and opportunities these technologies present. The report also examines professionals' perceptions of GenAI and the need for strategic integration to maximize its value.

Read more