U.S. Department of Homeland Security
Hidden Signals Challenge

This is the first post in our Q&A series featuring the five Hidden Signals Challenge finalists. These solutions demonstrate the exciting potential for open data to help identify biothreats in real time.

Our opening Q&A features the finalist team from Readiness Acceleration & Innovation Network(RAIN). This team’s system, Commuter Pattern Analysis for Early Biothreat Detection,cross-references de-identified traffic information with existing municipal health information outcomes and internet keyword searches. The tool will be developed to recognize commuter absenteeism to flag a possible disease outbreak.

“We wanted to take a different approach to health monitoring by using data that wasn’t obviously health-related.”

– Readiness  Acceleration & Innovation Network

What inspired you to submit this concept?

We wanted to take a different approach to health monitoring by using data that wasn’t obviously health-related. There are many privacy concerns when it comes to health data and we wanted to respect the privacy of individuals and healthcare-related institutions as much as possible. While it is essential to eventually use that data to understand outbreak potential, we felt that using commuter data to trigger the initial warning would give us greater credibility when requesting health information.

We also relied on existing infrastructure as much as possible. We felt that there were many devices and software already created which could be leveraged for our concept and this would help streamline the testing and implementation of the concept.

How will your concept enable city-level operators to make critical and proactive decisions?

Our concept provides city-level traffic operators with data that helps them understand traffic patterns and whether there is an unusual number of commuters traveling to or from a location. The signs will be subtle, but with the right inputs we can tune our algorithms to be sensitive enough to make conclusions about commuter data. The operators will be able to further analyze the traffic data to verify conclusions before submitting requests to evaluate health information.

The operators are the first line of people to flag and escalate a commuter health concern. The concept helps an operator create links among health information that takes into account where a commuter may choose to receive healthcare, based on proximity to the workplace, home, or commuter route. This data will help us develop a geographic link of where people may become ill, not where people seek treatment. Understanding the geographic commonalities of the commuters helps identify where commuters become ill and prevents undue attention towards a healthcare provider.

What sets your concept apart from existing solutions?

Our proposal to analyze commuter patterns is novel because it does not initially involve health data and because it collects raw traffic data straight from the source. Having the commuter analysis be a standalone process allows better control over the algorithms used to detect potentially significant commuter changes that warrant concern. This is beneficial for developing machine learning methods that can identify the hidden signals which can be an early warning sign of an outbreak.

How did you see your concept evolving during Stage 2 of the Challenge?

Our concept has made progress in developing solutions that allow it to be scaled to cities with less resources dedicated to monitoring. These solutions may require some investments into infrastructure, but at a cost less than what was required for the original proposal. We also narrowed down some of our data streams to optimize the impact of each data source against the effort needed to acquire and analyze the data.

What is the biggest insight you’ve uncovered through the Challenge thus far?

We knew that this was a very difficult topic to approach and we are thoroughly impressed with the work that has been put into public health monitoring  by our fellow finalists, mentors, and professionals in the field. The biggest insight we have had thus far is that although many excellent tools and methods have been developed, what we need is better integration and adoption. This must occur with the consent of colleagues working in the field, including administrators, developers, and end users, and the public at large. We must balance privacy concerns with safety and ensure all our freedoms are protected. This is a challenge indeed, and we are excited to be part of a process that can advance public health awareness and safety.

Learn more about other finalists’ solutions on the Challenge blog and subscribe to our newsletter to continue receiving updates. The winner(s), who will receive up to $200,000 in cash prizes, will be announced later this spring.