ARPA-H launches program to accelerate rare disease diagnosis

Program intends to eliminate the current multi-year diagnostic odyssey for rare and ultra-rare disorders 

The Advanced Research Projects Agency for Health (ARPA-H), an agency within the U.S. Department of Health and Human Services (HHS), today announced a new funding opportunity through the Rare disease AI/ML for Precision Integrated Diagnostics (RAPID) program. RAPID intends to transform the rare disease diagnostic odyssey through the development and real-world validation of AI-enabled diagnostic support systems, helping patients reach an accurate diagnosis in a fraction of the time it takes today. 

Collectively, rare diseases are far from rare — more than 10,000 unique conditions affect over 350 million people worldwide including one in ten Americans. Most patients face a lengthy diagnostic journey, averaging six years but sometimes taking decades. This delay often stems from complex, overlapping symptoms and a shortage of specialist expertise. As a result, it is estimated that up to half of all people with a rare disease remain undiagnosed or misdiagnosed. These individuals face inappropriate care, irreversible disease progression, and rising medical costs. Addressing the need for earlier, more accurate diagnoses is critical. 

"RAPID represents a paradigm shift in how we approach rare disease diagnosis, with the potential to transform the long and difficult journey experienced by many rare disease patients and their families," said ARPA-H Director Renee Wegrzyn, Ph.D. "Timely, accurate diagnoses can lead to earlier interventions, reduced health care costs, and better outcomes for millions navigating these complex conditions." 

The RAPID program is designed to accelerate the diagnosis of rare and ultra-rare diseases by developing highly accurate artificial intelligence (AI)-based detection models for both clinical diagnostic support and direct-to-patient systems. To enable model development, RAPID will integrate data from a fragmented landscape and build the largest curated dataset of longitudinal rare disease patient data, optimized for training advanced diagnostic algorithms. Provider-facing tools will prioritize data interoperability for seamless integration into existing clinical workflows and scalability across health care organizations. Additionally, RAPID seeks to develop cost-effective, remotely deployable tools to help individuals and their families detect rare diseases at home or in non-clinical settings and route them to appropriate medical support. 

"By leveraging AI, we can expand access to rare disease expertise and greatly reduce time to diagnosis — from years to months or even days,” said RAPID Program Manager Scott Gorman. “AI-enabled support tools allow us to sift through the 'haystack' of patient data more efficiently and pinpoint the 'needles' of rare diseases. Combined with access to confirmatory testing, such as whole genome sequencing, these tools can greatly accelerate the path to support and available treatments.” 

Through a forthcoming Innovative Solutions Opening (ISO), RAPID will invite performer teams to submit proposals across three technical areas: massive-scale rare disease data collection, discovery of novel diagnostic indicators, and a sustainable platform for the development and evaluation of AI-driven diagnostic tools. A second solicitation will focus on system development and implementation across diverse real-world settings. The program will also fund partnerships with patient advocacy groups to ensure a patient-centered approach to data collection and tool development. 

Multiple awards under this ISO are anticipated. Awards will depend on the quality of the proposals received and the availability of funds. To learn more about RAPID, including information about the solicitation, Proposers’ Day registration, and guidance on how to submit a teaming profile, visit the RAPID program page.