LABSWe're excited to be supporting the first stages of a new challenge with the Department of Homeland Security that seeks to use data to detect emerging biothreats earlier. To announce the finalists from the first phase, we're pleased to share a guest post from our good friends over at Luminary Labs.
Today, at the American Society for Microbiology 2018 ASM Biothreats meeting, we announced the five Hidden Signals Challenge finalists. These novel concepts utilize a variety of data sources along with machine learning and predictive analytics to design an early warning system to uncover emerging biothreats. Each finalist will receive $20,000 and advance to Stage 2 of the competition.
A panel of judges with expertise in areas such as bioinformatics, biological defense, epidemiology, and emergency management helped to select these five finalists. The judges made their selections based on several criteria, such as impact, feasibility, and originality.
Congratulations to the five finalists:
- Commuter Pattern Analysis for Early Biothreat Detection (RAIN): A system that cross-references de-identified traffic information with existing municipal health data and internet keyword searches. The tool will be developed to recognize commuter absenteeism to flag a possible disease outbreak.
- Monitoring emergency department wait times to detect emergent influenza pandemics (Vituity): A model that alerts authorities of spikes in emergency room wait times that can be attributed to emergent flu pandemics. The solution sources real-time data from a network of 142 hospitals in 19 states and is updated hourly, allowing agencies to quickly intervene.
- One Health Alert System (William Pilkington, Angi English, Merideth Bastiani, and Steven Polunsky): A symptoms database that analyzes the Daily Disease Report’s top ten symptoms as seen by 43 health care providers in North Carolina. The model flags disease outbreak using textual predictive analytics and accounts for seasonal rates of change.
- Pandemic Pulse (Computational Epidemiology Lab at Boston Children's Hospital): A tool that integrates six data streams to detect bio-threat signals. First, it alerts agencies using Twitter, Google Search, transportation, news, and HealthMap data of an anomaly in the data stream, then it tracks potential biothreats using live transportation data on Flu Near You.
- Pre-syndromic Surveillance (Daniel B. Neill and Mallory Nobles): A machine learning system that overlays real-time emergency room chief complaint data with social media and news data using the semantic scan, a novel approach to text analysis. The model detects emerging clusters of rare disease cases that do not correspond to known syndrome types.
Stage 1 constituted the first step in the design of a system that can enable city-level operators to make critical decisions based on the most relevant insights. During Stage 2, finalists will further develop their concepts into detailed system designs with guidance from expert mentors. At the conclusion, the judges will select a winner to receive the $200,000 grand prize.
Stay tuned for a Q&A with the finalists and the winner announcement later this year.