Skip to main content

Table 2 Final Model Performance of Logistic and Machine Learning Models Before and After Vaccine Availability

From: Evaluating methods for risk prediction of Covid-19 mortality in nursing home residents before and after vaccine availability: a retrospective cohort study

Model Type

Before Vaccine Availability

Mar 7, 2020 – Dec 31, 2020

(n = 11,291)

After Vaccine Availability

Jan 1, 2021– July 31, 2021

(n = 3686)

Logistic Regression

0.670

0.670

Lasso Regression

0.664

0.664

Random Forest

0.662

0.663

Classification and Regression Tree (CART)

0.641

0.646

Gradient Boosted Trees

0.672

0.670