Nightingale, Association for Health Learning & Inference (AHLI) and Providence St. Joseph Health hosted a High Risk Breast Cancer Prediction Contest 2 with support from the Gordon and Betty Moore Foundation that ended in May 2023. We are now pleased to announce the results.
Every year, 40 million women get a mammogram; some go on to have an invasive biopsy to better examine a concerning area. Underneath these routine tests lies a deep—and disturbing—mystery. Since the 1990s, we have found far more ‘cancers’, which has in turn prompted vastly more surgical procedures and chemotherapy. But death rates from metastatic breast cancer have hardly changed. To advance medical knowledge on identifying features of cancers that will metastasize, we hosted an earlier machine contest to identify the cancer stage from more than 72,000 biopsy slides provided by Providence Oncology.
Based on our findings from the first contest, we hosted a second high risk breast cancer contest on a balanced subset in terms of the race and ethnicity of patients as well as cancer stages. We updated the scoring technique to use one-vs-rest average AUC as the scoring technique. We also added a baseline score obtained using the CLAM model, which served as the 'score to beat'. 30 teams entered this contest, and we are happy to announce the top 2 teams that submitted the winning models.
Team name: csabAIbio
Team members: András M. Biricz1, Zsolt Bedőházi1,2, Oz Kilim1, István Csabai1
Organization: Eötvös Loránd University (ELTE), Budapest, 1117, Hungary
(1) Eötvös Loránd University (ELTE), Department of Complex Systems in Physics, Budapest, 1117, Hungary
(2) Eötvös Loránd University (ELTE), Doctoral School of Informatics, Budapest, 1117, Hungary
Code on GitHub
Team name/member: Bonaventure Dossou
Organization: McGill University, Mila Quebec AI Institute, Montreal, Quebec, Canada
Code on GitHub
Congratulations to the winners and all the participating teams! The winners will be invited to present their results at the ML4H 2023 conference.
To support repeatable science and collaborative research, the winners have open sourced their solutions according to contest rules. We invite healthcare ML researchers worldwide to move the needle forward in our understanding of cancer.