12 Sep 2023

Earlier this month, the National Institute on Aging announced a new competition: the Pioneering Research for Early Prediction of Alzheimer’s and Related Dementias EUREKA Challenge, aka PREPARE. The goal? To improve early detection of AD and to address diagnosis gaps among minority racial and ethnic groups, who are underrepresented in most clinical studies and databases to date.

The challenge has three phases. In the first, the NIA calls for scientists to submit existing data to create an open-access dataset suitable for machine-learning algorithms. The data can include memory or cognitive measures, biomarker data, including those of the AT(N) framework, and medical and behavioral data, such as speech or writing patterns. During the second phase, researchers will use the data to create AI tools that better predict who will develop AD. In the final phase teams will demonstrate how their algorithm works, share their results, and compete for the final prize.

The deadline to apply for phase 1 is January 31, 2024. Phase 2 is slated to begin next September, and phase 3 in March 2025.

For phase 1, a top prize of $50,000 will go to the team that submits the most "representative, inclusive, open, and shareable datasets that can be used for a data science competition focused on the early prediction of AD/ADRD,” according to the announcement. Four runners-up will receive $10,000 to $40,000. The team that assembles the dataset best suited to address biases in research and diagnoses among populations disproportionately affected by AD will get a $25,000 bonus. Up to five more applicants will receive $5,000 for proposals to collect new data, especially those that address biases in existing datasets. The total prizes for phases 2 and 3 are $250,000 and $200,000, respectively with further details to come.

To learn more, and apply, see here.—Chelsea Weidman Burke