covics-19

SARS-CoV-2 is spreading rapidly through communities. Covics-19 matches countries' required medical resources to their actual healthcare capacity and coordinates medical resource sharing among them.

Comment 4

Check out our video

Video was recorded 10 minutes from official deadline. Even the best marketeer's voice would have trembled ;-D Good vision!

https://youtu.be/FpmNE__huM0

Our Web App is online!

We are still working on this MVP, therefore bugs may exist. We are already working on solving them. Also, our data might be couple of days old, but we'll soon improve this.

https://covics-19.herokuapp.com/

Our project, in slides

https://www.slideshare.net/LaylaHosseiniGerami/covics-19-final-231170218

Problem

SARS-CoV-2 is spreading rapidly through communities, and healthcare systems are struggling to keep up. Though most people infected experience mild disease, some, especially older people and those with underlying health conditions, require hospitalization. Many of those infected with SARS-CoV-2 will require hospitalization, and the mortality rate is significant and still uncertain. However, hospitals are struggling to cope with the influx of patients and are reaching a point of saturation. Without medical assistance and cooperation between countries, far more COVID-19 patients die.

Suggested Solution

To help tackle this problem, we propose a scheme that allows regions to predict how many COVID-19 patients they will have to provide in-patient medical care for in the next 3 weeks -- number of weeks still needs to be determined. This will be achieved by modelling the infection rate. Regions that will not have enough resources to cope with their COVID-19 patients in any given week will be matched with regions that will have a surplus of medical resources in the same given time, 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.

Implementation

Core functionalities

Our Web App:

  • Predicts the number of COVID-19 cases in a given region that will require hospitalization over the next 3 weeks. Infection rate growth curve over Hopkins data will be used for the task.
  • Compares required medical resources to the actual healthcare capacity in the region to determine whether the health system will be overwhelmed or not. Data used comes from World Bank
  • Finds the nearest region with excess capacity in the coming weeks, so that medical supplies can be redistributed
  • Provides the above information to the users in an intuitive manner

Nice to have Functionalities

  • Using flights data to better understand the spreading of the virus
  • Extend granularity to city level by using GPS data matching person's location with their health status
    • Person's would need to self assess their health status and communicate it to our App

Considerations

  • Is it better to move medical resources, or patients themselves?
  • How long does it take to mobilize resources?
  • What are the political implications? Are countries keen to help each other?
  • Should we be tracking healthcare resources as a whole, or identifying the specific materials that are required (e.g. masks, ventilation systems, gloves, etc.)?
    • Identifying capacity for different kinds of resources would allow countries to have a better picture of what they need and to whom ask for help

What's next for covics-19

If successful, our project could be moved a step further and be integrated in already existing dashboards used by governments' healthcare systems.

What we wish we'd had time to do

  • The point at which a patient requires critical care is likely to be offset from the point of diagnosis. People who will ultimately end up in hospital may get a positive diagnosis, then have a delay before they require medical intervention. This is important for planning when resources will be required, and would be something to build into V2. (In summary, the growth curve for confirmed cases will be offset from hospitalized cases)
  • Our distribution logic is currently somewhat naive, and would benefit from being optimised. A solution based on the Knapsack problem has been proposed.
  • We are currently working under the naive assumption that countries that are closer together will find it easier to exchange resources. We need to expand on this logic to find countries where good relations and trading agreements make goods transfer efficient.
  • The infection forecast model is currently quite simplistic, so we would like to get epidemiologists and infection growth curve experts on board to produce a more sophisticated and accurate model
  • Our estimate for country resources is currently based on the number of hospital beds available. This is flawed because: ** Not all beds will be open for COVID-19 patients. Many will already be taken up with other patients. ** Not all hospital beds will be technically equipt to cope with COVID-19 patients (have ventilators, etc)

Our GitHub Repos

Our code base will be soon merged and perfectioned.

+ 24 more
Share this project:

Updates