Skip to content

This repository contains the raw data and a python notebook to ingest historical A&E attendance data and then use a simple Prophet model to predict the number of A&E attendances in England if the COVID-19 pandemic had not happened. The predicted A&E attendance values from (2020-01 to 2021-12) are then compared to the actual data to quantify the …

License

mattia-ficarelli/ae_attendances_modelling

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ae_attendances_modelling

This repository contains the raw data and a python notebook to ingest historical A&E attendance data and then use a simple Prophet model to predict the number of A&E attendances in England if the COVID-19 pandemic had not happened. The predicted A&E attendance values from (2020-01 to 2021-12) are then compared to the actual data to quantify the impact of the pandemic on A&E attendances.

Raw monthly A&E attendance data sourced from NHS England; HERE

Further infromation of AE attendance data can be found HERE

The mean absolute percentage error (MAPE) of the model when predicting the last 12 months of data is 26%.

Percent difference in actual total A&E attendances vs. predicted attendances during the course of the COVID-19 Pandemic

alt text

About

This repository contains the raw data and a python notebook to ingest historical A&E attendance data and then use a simple Prophet model to predict the number of A&E attendances in England if the COVID-19 pandemic had not happened. The predicted A&E attendance values from (2020-01 to 2021-12) are then compared to the actual data to quantify the …

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published