Aug82017

Bonnie J. Addario Lung Cancer Foundation Launches the Lung Cancer Early Detection Challenge: Concept to Clinic

Posted by Kassy Perry

$10ALCF logo0,000 prize for clinic-ready software that changes the way radiologists are able to help patients

San Carlos, Calif. (August 8, 2017)–The Bonnie J. Addario Lung Cancer Foundation (ALCF) is calling on data scientists, software engineers, designers and researchers to build an open source software application that puts advances from machine learning into the hands of practicing clinicians. In addition to creating cutting-edge clinical software that helps detect lung cancer early, top contributors are eligible for a share of $100,000 in prize money.

“The earlier lung cancer can be detected, the better,” said Bonnie J. Addario, a 13-year lung cancer survivor and ALCF founder. “My hope is that the winners of this challenge create software that achieves real change in the way radiologists are able to help patients and save lives now.”

The five-year survival rate for lung cancer is 55 percent when the disease is still in the lung, but just four percent once it has spread. Lung cancer is the number one cancer killer in the world, killing more people than the next three most common cancers (breast, colon, prostate) combined. This year physicians will diagnose nearly 225,000 Americans with lung cancer.

ALCF has partnered with DrivenData, a mission-driven company that brings advances from data science and artificial intelligence to organizations tackling the world’s greatest challenges. DrivenData runs online competitions where technical experts from around the world compete to build the best solutions for tough questions in big data and machine learning. The goal of this challenge is to bridge the gap between research algorithms and clinical practice in early detection by developing an end-to-end application, as a community, that connects the predictive power of machine learning with functional software tested against errors and a clean user interface focused on clinical use.

Throughout this challenge, contributors will have the chance to submit code patches that add features to the software, improve functionality and make the predictive algorithms more precise. As project maintainers review and adopt code patches, the most advanced version will become the new starting point for the community to build on.

Meanwhile, contributions that provide meaningful progress can earn points from a technical panel of experts in machine learning, engineering and clinical settings. A live leaderboard will keep track of points earned throughout the challenge. At the end of the challenge, ALCF and DrivenData will award prizes to top overall contributors.

There will also be prizes for top contributors filling key roles throughout the process. The project needs:

  • Data scientists to build out the machine learning algorithms
  • Software engineers to develop backend functions and data pipelines to run the tool
  • Engineers and designers to build out the user interface
  • Community contributors to enrich the documentation, discussions and outreach

“We are excited to bring together the most brilliant technical and medical minds to create technology that will help clinicians catch lung cancer early enough to manage its impact on patients and save lives,” Addario said. “We designed The Lung Cancer Early Detection Challenge based on conversations with practicing clinicians, lung cancer survivors, researchers and engineers. I am optimistic that this challenge will help turn lung cancer into a chronically managed disease by the year 2023.”

To learn more about the challenge, watch the video here.