May 1, 2023
AIM-AHEAD's Health Equity Data Challenge
High Risk Breast Cancer Prediction and Health Equity Data Challenge
DSTC and Nightingale Open Science developed this challenge as a training and outreach opportunity for underrepresented students in AI/ML.
The goal of this challenge is to improve the prediction of the cancer stage in minority patient’s cancers above a baseline score derived from all patients, using only the whole slide images generated by a breast biopsy.
Triple negative breast cancers constitute 15% to 20% of breast cancers and have higher incidence in African American and Hispanic women, with African Americans facing worse outcomes than other race and ethnic groups. [2] Determining the stage helps doctors determine how to move forward with treatment.
Overall Budget |
$60,000 |
Completion Date |
August 2023 at Annual AIM-AHEAD meeting |
Prizes |
Prizes for winning teams: Cash (donated), free compute credits, possible publication. Travel Grants awarded to top scoring teams to present solution at AIM-AHEAD Annual meeting |
Teams |
We hope to recruit 10-20 teams of up to 5 persons. Underrepresented populations in the U.S. biomedical, clinical, behavioral and social sciences research enterprise are strongly encouraged to participate. (LINK) We need assistance from AIM-AHEAD HUBs and CORES for recruitment and marketing |
Timeline |
The Data Challenge - May 1 - June 23. Challengers have 2 months to improve their models. All teams will be scored and placed on a Leaderboard. Finalists will be identified based on Leaderboard. All Challengers must make solutions public on Github. |