How finalist Boston Children’s Hospital applies social, news, and epidemiology data
This is the fourth 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 second-to-last Q&A features finalists from the Computational Epidemiology Lab at Boston Children’s Hospital. Their tool, Pandemic Pulse, integrates six data streams to detect bio-threat signals; Twitter, Google Search Trends, news streams, and HealthMap data provide a baseline pulse of the community. Should an anomalous signal be detected, a secondary set of monitoring tools are deployed, including live transportation data and participatory cohorts such as Flu Near You.
“Through the Hidden Signals Virtual Accelerator, we have come to realize that within our single, intended end-user group, the needs and priorities may vary based on position, responsibilities, or even personality. We need our platform to be flexible enough to allow for zooming in and panning out at any given moment, as this will increase understanding and therefore trust among our end-users.”
– Computational Epidemiology Lab at Boston Children’s Hospital
What inspired you to submit this concept?
The Hidden Signals Challenge appeared to have strong synergy with our previous work in innovative disease monitoring and digital disease detection methods research. We saw the Challenge as an opportunity to build off our previous work and to enhance it by way of our new platform. We think there are many great complementary tools and data streams out there for use in public health, and we just need to find ways of bringing them together to increase visibility and help inform decision-making.
How will your concept enable city-level operators to make critical and proactive decisions?
Our concept will provide critical situational awareness regarding bioterrorism threats to American communities. Any signals that can be detected ahead of traditional monitoring can result in saved lives and critical response resources. We aim to decrease the time for public health event detection.
What sets your concept apart from existing solutions?
We are lucky to have access and experience working with multiple high-volume data streams through our previous work. Our multi-stream monitoring approach aims to balance sensitivity and specificity to reduce noise without missing subtle signals. We believe our data visualizations, by way of our platform dashboards, will help end-users assimilate to the platform more easily, and more rapidly identify signals requiring action.
What is the biggest insight you’ve uncovered through the Challenge thus far?
Through the Hidden Signals Virtual Accelerator, we have come to realize that within our single, intended end-user group, the needs and priorities may vary based on position, responsibilities, or even personality. We need our platform to be flexible enough to allow for zooming in and panning out at any given moment, as this will increase understanding and therefore trust among our end-users. The end-user buy-in is a critical step in development, as an under-utilized platform would have limited public health impact, particularly in times of emergencies.
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.