Key Dates

Related Announcements

Issued by

National Institute on Aging (NIA)

Purpose

This Notice informs potential solvers of an upcoming opportunity to compete in the NIH Early Prediction of Alzheimer's Disease and Alzheimer's Disease Related Dementias (AD/ADRD) Open Innovation Challenge.

 The National Institute on Aging (NIA) is developing a challenge prize competition to discover the best data, methods, and strategies for the early prediction of Alzheimer's disease (AD) and AD-related dementias (ADRD). This includes an emphasis on building diverse teams and solutions that generalize to groups that historically have been excluded from participation in AD/ADRD research, despite being disproportionately impacted by these conditions.

NIA, part of the National Institutes of Health (NIH), leads a broad scientific effort to understand the nature of aging and to extend the healthy, active years of life. NIA is the primary federal agency supporting and conducting AD research. NIA is providing this opportunity because Section 2002 "Eureka Prize Competitions" of the 21st Century Cures Act, enacted on December 13, 2016 (P.L. 114-255), requires NIH to support and report on prize competitions in areas of biomedical science that could: 1) realize significant advancements and 2) improve health outcomes in human diseases and conditions that have a disproportionately small research investment relative to expenses for prevention and treatment, represent a serious and significant disease burden, or for which there is potential for significant return on investment.

Section 2002 prize competitions, like other NIH prize competitions, must be carried out pursuant to NIH’s existing prize authority, i.e., the America COMPETES Act (P.L. 111-358), as revised by the American Innovation and Competitiveness Act (P.L. 114-326).

Background

The main clinical features of AD are progressive impairments of cognition and function and changes in behavior. We have learned that early intervention may be important for successful disease modification, but we have significant limitations with early prediction of cognitive decline and AD/ADRD, and subsequent diagnosis, using standard research and clinical tools. Standard clinical approaches to detecting changes in cognition in aging and AD/ADRD are not sensitive enough for early prediction of AD/ADRD onset. Potentially more sensitive approaches (e.g., neuroimaging, fluid biomarkers, neuropsychological tasks, digital and passive measures) can be expensive, difficult to interpret or have unclear performance in some individuals and groups, and may require access to academic medical centers, protected databases, or industry partners to ascertain data. Data sources, analytical algorithms, interpretations and applications of test results have known (and unknown) biases, methodological limitations, and questionable predictive validity, especially for groups that have historically been excluded from participation in AD/ADRD research.

 NIA seeks to stimulate the use of data resources, especially those with appropriate sample diversity, including data inclusive of low-resourced, underserved communities disproportionately burdened by AD/ADRD. Adequate population representation is an important priority for NIA and the field because the use and accuracy of AD/ADRD biomarkers may vary across and within the broader population. For example, for Asian, Black, or Hispanic older adults, the protein amyloid – which has long been considered a biomarker for AD – might have a smaller role in determining cognitive impairment than other factors, such as co-occurring chronic medical conditions (e.g., hypertension, diabetes) and sociodemographic and systemic factors, each of which has been found to contribute to racial and ethnic disparities in dementia diagnoses (Wilkins et al., 2022). This highlights the importance of identifying novel (non-amyloid, non-tau) biomarkers and non-biological (e.g., social determinants of health) predictors in adults from underrepresented racial and ethnic groups (Dark and Walker, 2022). The goal is to inform novel approaches to early detection that might ultimately lead to better tests, tools, and methodologies for clinical and research purposes.

Advances in artificial intelligence (AI), machine learning (ML), and computing ecosystems increase possibilities of intelligent data collection and analysis, including better algorithms and methods that could be leveraged for the prediction of early biological, behavioral, psychological, functional, and clinical changes related to AD/ADRD.

To make progress, there is a need for the following: 

1.  Data from a wider set of sources and types, including data relevant to low-resourced, underserved communities disproportionately burdened by AD/ADRD to better understand and address biases in existing data sources; 
2.  Open, shareable data, stored in trusted repositories to determine “distributional robustness” of predictive algorithms; and 
3.  Algorithms that meet “right to explanation” mandates (i.e., if an AI algorithm impacts people, people have a right to an explanation of how AI conclusions were reached). 

 The aim is to find, access, and use data from the following sources:

•  NIA-supported (e.g., population-representative longitudinal studies like the Health and Retirement Study, Alzheimer’s Disease Sequencing Project, Alzheimer’s Disease Neuroimaging Initiative, and open datasets), 
• Real world data like electronic health records, Centers for Medicare and Medicaid Services claims, or from users themselves (e.g., through direct-to-consumer blood-based biomarkers and online cognitive testing),  
• Social media or device use, and/or
• Combined data from different sources.

Competition Details

The Goal

The goal of this challenge is to deliver solutions for accurate, representative, inclusive, open, and robust early prediction of AD/ADRD. To achieve this goal, the challenge will feature the following three phases that successively build on each other:

1. Phase I [Find IT!]: Data for Early Prediction-Solvers engage with the problem scope and propose datasets for use in early prediction of AD/ADRD. This period may include the contribution of an existing dataset (i.e. identifying and collating data from existing sources) and proposed data collection (i.e. designing new data sources).
2. Phase II [Build IT!]: Algorithms and Approaches - Solvers develop and submit algorithms, study designs, and/or analytic approaches for pushing forward the state of the art in early prediction, which can be demonstrated on data from the challenge.
3. Phases III [Put IT All Together!]: Proof of Principle Demonstration - Building on the prior phases, finalist solutions from Phase II will be invited to apply their approaches to diverse datasets and demonstrate their potential for early prediction of AD/ADRD. This phase will include an innovation event to pitch solutions, share results, exchange ideas, and award prizes.

Challenge Prize

The challenge intends to offer cash awards totaling $650,000 which will be distributed across three phases of the competition and awarded to participants who successfully complete the objectives and requirements of each phase.

Eligibility

Participation in the challenge is open to citizens or permanent residents of the United States, or in the case of a private entity, be incorporated in or maintain a primary place of business in the United States. Full eligibility criteria will be available in the challenge announcement.

Key Dates

The anticipated key dates of the challenge are the following: 

• Publication Date of Challenge Announcement on Challenge.gov: September 1, 2023 
• Application Submission Due Date to the Challenge.gov portal: January 31, 2024
• Phase I Award Date: September 1, 2024

Inquiries

Please direct all inquiries to:

National Institute on Aging (NIA)
Email: NIAPrizeInput@nih.gov