Cambridge Adjutorium is an AI-powered tool that accurately predicts how COVID-19 will impact resource needs (ventilators, ICU beds, etc.) at the individual patient level and the hospital level, thereby giving a reliable picture of future resource usage and enabling healthcare professionals to make well-informed decisions about how these scarce resources can be used to achieve the maximum benefit.
A detailed introduction with video demonstration is available here.
Note that the included data is synthetic to ensure that the demo runs.
Please first make sure you have installed all the dependencies listed in requirements.txt.
A web demo is available by running main_index.py. All figures presented in the demo are based on synthetic data for illustrative purposes only.
The model training and prediction scripts are in the folder model_training.
The users will need to manage data importing and feature cleaning themselves as we are not able to provide the data set.
This tool is developed and maintained by: Zhaozhi Qian (1), Ahmed M. Alaa (2), Mihaela van der Schaar (1), Ari Ercole (3)
(1) University of Cambridge Centre for Mathematical Sciences, Wilberforce Rd, Cambridge CB3 0WA, UK
(2) University of California, Los Angeles, CA 90095, USA
(3) University of Cambridge Division of Anaesthesia, Addenbrooke's Hospital, Hills Road, Cambridge CB2 0QQ, UK
Please refer to the LICENSE file.