Imagine navigating a busy freeway blindfolded. That's what predicting public health risks without big data feels like, as management consultant Geoffrey Moore aptly put it: "Without big data, you are blind and deaf and in the middle of a freeway." This analogy perfectly captures the essence of why open source data is indispensable in improving health outcomes and interventions at the population level.
In our work, building accurate predictive models hinges on the availability of comprehensive and detailed data. Traditional health program data, like the number of disease cases reported, only provides a limited snapshot of an infectious disease within a community. To grasp the full picture at national and global levels, we need to turn to high-resolution context data.
Fortunately, organisations like WorldPop and the Humanitarian Data Exchange make invaluable data accessible for global health efforts. Other significant sources include the World Health Organization (WHO), Centers for Disease Control and Prevention (CDC), and the National Oceanic and Atmospheric Administration (NOAA), etc.
Key types of open source data we utilise
Environmental data - Environmental factors play a crucial role in the spread of epidemic-prone diseases. The WHO highlights that water supply, sanitation facilities, food and climate are pivotal. We leverage environmental data from reputable sources to predict infectious disease hotspots and identify vulnerable populations at risk.
Social-demographic data - Here we look at factors like the regional poverty levels, housing quality, cultural norms, and political contexts. These variables profoundly impact public health. Understanding such factors helps us tailor our health interventions more effectively.
Maximising the value of open source data
Given the vast amounts of open source data available, identifying the most relevant data sets is crucial. For instance, in tackling vector-borne diseases, data on proximity to bodies of water is crucial. Knowing whether a region is rural or urban provides additional context, as rural areas may have lower disease transmission rates but face greater health care access challenges compared to urban areas.
Building data analysis capacity
Effectively using open source data requires advanced data analysis skills, especially for handling geo-referenced data, i.e. data linked to the Earth’s coordinate system. We also help build local capacity if possible. Open source data is a game-changer in public health. By integrating various types of high-resolution context data, we gain a better understanding of health risks and outcomes. This leads to more effective and targeted public health strategies.
In the ever-evolving field of infectious disease control, embracing open source data is not just beneficial — it's essential.