Neel Mehta
Booz Allen Hamilton and Kaggle co-sponsored a data science competition that has challenged participants to produce algorithms to enable automated analysis of cardiac magnetic resonance imaging scans.
More than 993 people of different genders and ages submitted approximately 1,392 algorithms for Kaggle’s second annual Data Science Bowl contest, Booz Allen said Wednesday.
“This particular challenge was one that the medical community had not been able to solve,” said Josh Sullivan, a Booz Allen executive vice president.
“It needed to harness the power of crowd-sourcing,” Sullivan added.
Hedge fund analysts Qi Liu and Tencia Lee jointly built the winning algorithm that Booz Allen says is based on a deep-learning model.
Kaggle CEO Anthony Goldbloom said he believes the algorithm has the potential to help clinicians diagnose people with heart disease.
A research team at the National Heart, Lung and Blood Institute will collaborate with Liu and Lee to test the effectiveness of their algorithm in clinical settings and aims to fuse it with existing medical technology.
