Open Source Graph Tool STEMs the Battle Against Malaria

A scientific community collaborating around an open source big data modeling tool are making new headway in a quest to combat diseases such as dengue fever and malaria.

Researchers from IBM, Johns Hopkins University, and the University of California say that they are building new analytic models through an open source framework called the Spatio Temporal Epidemiological Modeler (or STEM). Built by the Eclipse Foundation, an open source project started by IBM in 2001 aimed at collaboration on “commercially friendly open source software,” STEM is a graph-based spatiotemporal simulation engine that has been primarily used for mapping the proliferation of infectious diseases.

While disease and vaccine simulations to track these pestilences have previously been available, what results they’ve produced have been shuttered in closed, relatively underpowered systems. This has turned up results that run behind current epidemics. While they may give insights useful for the future, they lack the real-time impact that one might hope for.

Aside from that, the data sets have also been limited, as well as siloed – something that the community around STEM says they’ve made headway on. The researchers at Johns Hopkins, UCSF, and IBM say that their models are shared through the STEM application framework, giving these scientists the opportunity to overlay models and data that they might not previously had available to them with their own. The results, say the researchers, are new predictive insights into how these diseases spread, and what conditions might cause them to wax and wane.

In the case of malaria, the researchers were able combine data from the World Health Organization, IBM, and Johns Hopkins to develop new analytic measures that reveal how malaria reacts to changes in the local climate such as temperature and precipitation. Having this information, they are now able to predict what regions during a malaria outbreak are most at risk (and conversely, least at risk) and tailor intervention strategies (such as vector control or vaccination) based on the data.

“There are a lot of tacit assumptions out there about how changes in climate will impact the distribution of diseases like malaria. This work suggests that things probably are not so simple, a change that has a huge effect on malaria transmission in one place might not be as important somewhere else,” said Justin Lessler of the Johns Hopkins Bloomberg School of Public Health. “One of the nice things about open source projects like STEM is that now whoever wants to can download the model and start tweaking it, seeing if their own data or assumptions fundamentally change the results.” 

Predicting the rise and proliferation of these diseases, however, is only half the battle. Being able to effectively respond to the data comes with its own challenges. “We have to be ready at the drop of a hat to parse through disparate data from global disease surveillance systems, conduct computationally intense research and transfer our knowledge to public health officials to help them visualize population health, detect outbreaks, develop new models, and evaluate the effectiveness of policies,” Simone Bianco, UC San Francisco, Bioengineering and Therapeutic Sciences in a statement.

As with any open source endeavor, the results are only as good as the community that engages with it. Given the early indicators, STEM looks like it has potential as a mainstay in the effort to control, and eventually eradicate diseases that have plagued mankind for centuries.

Related items:

UN Taking Big Data Pulse for Humanitarian Efforts 

Doctors Look to Medical Informatics for Novel Cures 

The Power and Promise of Data Driven Medicine