uses Artificial Intelligence in Syrian Polio Vaccination Analyses

One aspect of our Collaboration program is that it has such an extraordinary capacity to better the human condition. Whether it is finding new sub-types of diabetes, helping the NFL understand concussions or working to understand Parkinson’s more completely, our partners are pushing us and our software in ways that matter.

Our partnership with is another wonderful example of this work in practice. We have been providing them with a license to our software for a roughly four months now, and they have been employing it in a unique fashion — as a rapid response data analysis application with incredible results. In fact, within a month of starting with us, they had generated the analysis detailed below — impressive to be sure.

The Crisis

Specifically, used Ayasdi software to perform a quick systemic cluster analysis of a Polio vaccination campaign for Syrian children. The data was provided by and was complex in that it contained patient, temporal and geographical data — but was fluid given the study area was an active warzone.

This humanitarian effort in a conflict zone reaches millions of people per campaign, however, there is a need to quickly and easily understand which locations are most impacted from the constantly fluctuating refugee population. This is especially important, as follow-on doses are necessary for the Polio vaccine to be effective in protecting the population.

What made this work so complex is that and Ayasdi needed to take into account all available features in the data set, not just ranking doses. In a traditional analysis of this data one would first need to examine each district and try to locate outliers in terms of each feature class. After that, one or several hypothesis would need to be formed and tested, which in this case would involve testing and validation between over 100 districts.

Our software was able to interact with all of the available feature classes at once and the results are then visualized in such a way that any interesting behavior in the data can was quickly identified.

The Results identified two statistically distinct groups where Not Reached Doses were the largest defining factor, with statistically significant districts within each group. There were no significant differences for those receiving their first dose. Based on insight from the vaccination team, it is likely the reason why children are not reached for follow-up doses is because of the high fluidity of refugee populations at vaccination sites.

The Impact

By understanding where children are most likely not reachable for follow up doses, is able to work with Humanitarian Tracker and help examine strategy to ensure that all individuals are receiving their doses. For humanitarian aid organizations strapped for time and resources, the ease and efficiency of reliable statistics and reporting are critical, and in cases such as this, Ayasdi can significantly reduce the investment needed for analysis. By saving this time, organizations can keep their focus on providing the aid and saving lives.

See the coverage in Fast Company in 2015.

This original blog appeared on the Ayasdi website in 2014. Here is the original report written by

This is the type of work we imagined when we started the collaborations program — impactful, fast, fluid and interesting. We look forward to being able to publish more in the coming weeks and months.

To become a collaborator email us as