Model code for Hospital load and increased COVID-19 related mortality in Israel (Nature communications 2021)
Based on the model developed and described in:
Development and validation of a machine learning model for predicting illness trajectory and hospital resource utilization of COVID-19 hospitalized patients - a nationwide study
Original model code here
Updated to include new patient states (including PCR positive to hospitalization transitions) and based on Israel data from July-December
This repository contains code for a multi-state survival analysis model which can be used to predict covid-19 patients' illness trajectories from time of positive PCR diagnosis or hospitalization up to time of recovery or death.
Transitions between states (such as: "severe" to "death") are modeled using survival models with competing risks, and the patient's trajectory is estimated via Monte-Carlo path sampling over these transitions, while updating time-dependent patient covariates.
Jonathan Somer, Rom Gutman, Asaf Ben Arie, Malka Gorfine & Uri Shalit
Hagai Rossman, Tomer Meir & Eran Segal