Alliance for Pandemic Preparedness

March 2, 2020

Prediction of survival for severe Covid-19 patients with three clinical features: development of a machine learning-based prognostic model with clinical data in Wuhan

Category:

Topic:

  • A new machine learning prognostic model was found to have 90% accuracy in predicting mortality among COVID-19 patients based on just three clinical characteristics: lactic dehydrogenase (LDH), lymphocyte and high-sensitivity C-reactive protein (hsCRP).

Yan et al. (Mar 1, 2020). Prediction of survival for severe Covid-19 patients with three clinical features: development of a machine learning-based prognostic model with clinical data in Wuhan. Pre-print downloaded Mar 2 from https://doi.org/10.1101/2020.02.27.20028027