Booz Allen Data Science Bowl a Finalist for SXSW Innovation Award

The 2017 Data Science Bowl (DSB), Turning Machine Intelligence Against Lung Cancer—presented by Booz Allen Hamilton and Kaggle, challenged the data science and medical communities to develop algorithms that can accurately determine when lesions in the lungs are cancerous. It has been chosen as a finalist for a prestigious SXSW Innovation Award in the category of Health, Med, & BioTech.

The SXSW advisory board reviewed hundreds of applications from around the world before selecting finalists. In each of the 13 categories, the board chose the top five entries in what SXSW calls, “the world’s best and most forward-thinking.”

Josh Sullivan, senior vice president at Booz Allen, said, “The Data Science Bowl shows that the power of collective ingenuity, data science and advanced analytics can be harnessed to tackle society’s toughest challenges like eradicating cancer. The complex problem presented in 2017—improving the accuracy of lung cancer screening—required the diversity of perspectives and approaches that only a crowd-sourced challenge like the Data Science Bowl can provide.”

Lung cancer is the most common type of cancer worldwide, affecting nearly 225,000 people each year in the United States alone. Low-dose computed tomography (CT) is a breakthrough technology for early detection, with the potential to reduce lung cancer deaths by 20 percent. But, the technology must overcome a relatively high false positive rate.

“This was one of the most important competitions Kaggle has ever hosted,” said Anthony Goldbloom, CEO, Kaggle. “Recent breakthroughs in deep neural networks may make it feasible to diagnose lung cancer from CT scans with higher accuracy than previously possible. The interest in the 2017 Data Science Bowl was been unprecedented for a competition of this size. The results are incredibly promising.”

Nearly 10,000 people competed in 2017 and preliminary findings suggest that the top 10 solutions outperform best-in-class models by 10 percent with a clinically meaningful decrease in false positives. Competitors used anonymized, high-resolution lung scans from hundreds of patients provided by the National Cancer Institute (NCI), to create algorithms that can improve lung cancer screening technology.

Scientists at NCI and their colleagues are currently working to integrate ensemble models of the winning solutions into clinical prototypes. And, a new competition is underway to integrate the algorithms into practical, open-source, clinic-ready software and systems.

The 2017 Data Science Bowl, hosted by Booz Allen Hamilton and Kaggle, will be part of the Interactive Innovation Awards Showcase on Sunday, March 11, where 65 finalists across 13 categories will exhibit their work for SXSW registrants, who vote to determine the winner of the People’s Choice Award. Meanwhile, the panel of SXSW Innovation Awards judges vote to determine the winners of each of the 13 categories. Winners will be announced at an awards ceremony on Tuesday, March 13, 2018.

The Data Science Bowl continues this year as competitors put artificial intelligence to work accelerating biomedical research. Learn more at DataScienceBowl.com.