Covics19

The prototype: https://covics-19.herokuapp.com/#!/home

The problem

COVID-19 is spreading rapidly around the world. Hospitals are struggling to cope with the influx of patients and are reaching a point of saturation. Without medical assistance, far more COVID-19 patients die.

The solution

We propose a scheme that allows countries to predict how many COVID-19 patients they will have to provide intensive medical care for in the next 3 weeks. This will be achieved by a machine learning model. Countries that will not have enough resources will be matched to countries that will have a surplus of medical resources (ICU beds) that week, so that the burden can be shared and more patients can receive life-saving treatment. As the infection moves globally, countries that bring their cases under control will be able to provide aid to countries where cases are rising rapidly.

The impact

The map could be used for any pandemic (in the future) by national governments and health officials all around the world as well by a single country to manage regional supplies of ICU. It can be scaled to accommodate millions of people.

What was done?

We built a Web Application that does the following:

1. For a given country, it predicts the number of COVID-19 cases that will require intensive medical care over the next three weeks. This is done by a combination of standard models (data: Hopkins https://coronavirus.jhu.edu/map.html). We are working on more elaborate models (including a recursive neural network approach).
2. It compares the requirement for ICU beds to the capacity of ICU beds in the country to determine whether the health system will be overwhelmed. (data: World Bank https://data.worldbank.org/)
3. If there is insufficient medical capacity, it finds the nearest country that will have excess capacity for upcoming three weeks so that medical supplies or patients can be redistributed.
4. It provides the above information to the user in an intuitive manner.

Next steps

1. Get in contact with the European national governments regarding their political position about sharing medical resources with other countries.
2. Plan on how long will it take to mobilize medical resources/patients.
3. Improve the prediction model.
4. Improve the redistribution proposal.

Built With

• angular.js
• mongodb
• node.js
• python
• sql