Website: https://cmaitland.ist.psu.edu/home/research/
Investigators
- Carleen Maitland, Penn State University (Principal Investigator)
- Andrea Tapia, Penn State University (Co-Principal Investigator)
- Daniel Hellmann, Penn State University
Description
Big data science has the potential to improve responses to crises, such as the Ebola outbreak, across several dimensions. In contact tracing, individuals having contact with known patients are identified, located, notified, and potentially monitored. Near real-time spatio-temporal monitoring of outbreaks (cases of positive diagnosis) can help identify spatial vectors of spread, and in turn support containment (e.g. limiting access to areas) as well as resource distribution. Coupled with data on populations, health care resources, and transportation patterns, outbreak monitoring can in turn form the basis for spatial assessments to help assess vulnerabilities, locate strengths and potentially predict the pattern of disease spread both spatially and temporally. In a third dimension, big data analyses can optimize healthcare resource logistics, ensuring facilities and materials are located where and when they are needed. In the Ebola outbreak, healthcare resources have been shown to be critical to improving survival rates. Modeling various resource distribution options based on near real-time as well as established data sets may help decision making and outcomes.
However, before developing such data driven operational capacities, collaborative networks and rules for working together must be developed between organizations. Data sources and a clear understanding of how data is captured as well as what it may be used for is also necessary before sharing, developing, and collaborating across any knowledge developed through a big data approach. Given this, it is necessary to first understand the collaborative environment along with its field and regional level data operations and information behaviors. Through our research on operational and social mechanics that enable data driven collaboration in a humanitarian aid context, we are able to contribute to more effectively designed schemes for the implementation of advanced analytic capacities.