Healthcare is something that we pour huge amounts of resources annually, and yet haven’t been able to tackle common problems like how to stop the spread of viral infections (i.e COVID-19), or how to fight influenza efficiently with data driven decision making. With the latest development of data analytics and open data sources, our societies around the world have taken promising steps towards better options.
Identifying the right data to help tackle COVID-19
There are hundreds of different kinds of datasets available which could be useful in fighting against COVID-19. Sorting out which ones are the most utilizable is a crucial task. First you should ask yourself “what will the data be used for”. This question helps you to pick out the most important data for you.
You might need broader data about healthcare operations, location of housing, hospitals and airports, demographic data about where people live or information of mobility, or data about how past viral-infections have spread. Try to narrow down these datasets to only few that are the most relevant for your needs.
Disregarding to what purpose you’re using the data for, you should look into national level datasets. Globally several national level organisations provide data that is also regulated in terms of quality. This makes these data sources reliable to begin with. You can browse different open geospatial web services for example Spatineo Directory, which is a free catalogue of all open geospatial web services we have discovered.
One datasource that has to be mentioned when writing about COVID-19 is a map layer by John Hopkins University. The data layer is maintained by JHU’s Center for Systems Science and Engineering department. It tracks known COVID-19 cases at country (and in some countries at provincial) level. The data contains confirmed cases, deaths and amount of people recovered from the virus. This dataset is currently used for example by a Finnish newspaper Helsingin Sanomat and BBC News. You can check JHU’s github repository for more information about the dashboard and it’s data.
Once you have found a couple of reliable sources you can work with, it’s time to get creative.
How long it takes for you to get to a hospital and how many airports are in your area?
The spread of certain diseases are often more influential in high population density areas, and places where airports are nearby. Living in close proximity to an airport has proved to have an effect on your chances of catching viral infection. As we saw with the spread of COVID-19, the global outbreak happened within a couple of weeks eventually via air travel.
So now that you have in example data about the location of your country’s hospitals and airports, you can start to estimate which hospital could need extra resources in the near future.
Combining different types of information could be essential in evaluating where resources should be allocated. And when we also add a bit of location intelligence to the mix, some amazing results could be created.
A study published by a team in Boston Children’s Hospital used several sources of data, and machine learning to pinpoint trends of influenza in the United States. They trained their algorithm with weekly total visit count of hospitals and visit count for flu and flu-like illness, and gave a finishing touch with visit count of flu vaccination during 2009 to 2012.
Utilizing geospatial data and machine learning has proved its effectiveness in creating more accurate predictions and relations between different information.
With these models getting more complex and accurate, we should be able to utilize data even better in decision making. Building hospitals in optimal locations, and pouring more resources to areas where risk of viral infections is higher might be worthwhile things to consider.
Measures taken in Finland to combat the virus
One of the first things our geospatial community did, when the gravity of the situation became clear was to gather a group of specialists of geospatial data together: CoronaGISFinland. This coordination started from Geoforum Finland, and they have since rounded up nearly thirty highly skilled professionals who are offering their knowledge to combat the pandemic. Check the Geoforum Finland website for more information, and don’t hesitate to contact them for more insights about the working group.
Spatineo is also actively taking part in the group. Jaana Mäkelä and Ilkka Rinne are specialists Spatineo offers to aid in fighting COVID-19 with geospatial data.
One of the first contributions we actually did was a geoJSON format, which was Ilkka’s creation.
“A GeoJSON data model for viral infection testing data based on Observations & measurements standard (O&M, ISO 19156) concepts. Created specifically for recording and exchanging data on SARS-CoV-2 infection tests, but likely applicable also to describing test data for detecting other infectious diseases too.
The data model is based on concepts of the international standard “Observations and measurements” (ISO 19156) that defines a conceptual model for describing observation events and their results as geospatial features. This specification uses an early draft proposal version of the ISO 19156 Edition 2 data model currently under preparation in the OGC O&M Standards Working Group. The O&M GeoJSON mapping follows the proposed O&M GeoJSON encoding profile by Ilkka Rinne.”
You can read more about CovidJSON from https://covidjson.org/. We will be writing more about this geoJSON and how it was created in the future as well so stay tuned.
With all the huge efforts on societal and personal level, we truly believe that we can win this pandemic. As last weeks have shown, humanity has vast resources and will to fight these kind of common enemies together. Building boundaries and walls between us hasn’t stopped the virus, but cooperation will. So let us continue on that path working together.