Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19

Sonu Subudhi; Ashish Verma; Ankit B Patel; C Corey Hardin; Melin J Khandekar; Hang Lee; Dustin McEvoy; Triantafyllos Stylianopoulos; Lance L Munn; Sayon Dutta; Rakesh K Jain

doi:10.1038/s41746-021-00456-x

Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19

NPJ Digit Med. 2021 May 21;4(1):87. doi: 10.1038/s41746-021-00456-x.

Authors

Sonu Subudhi¹, Ashish Verma^#², Ankit B Patel^#², C Corey Hardin³, Melin J Khandekar⁴, Hang Lee⁵, Dustin McEvoy⁶, Triantafyllos Stylianopoulos⁷, Lance L Munn⁸, Sayon Dutta^{9

10}, Rakesh K Jain¹¹

Affiliations

¹ Department of Medicine/Gastroenterology Division, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA.
² Department of Medicine/Renal Division, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA.
³ Department of Pulmonary and Critical Care Medicine, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA.
⁴ Department of Radiation Oncology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA.
⁵ Biostatistics Center, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA.
⁶ Mass General Brigham Digital Health eCare, Somerville, MA, USA.
⁷ Cancer Biophysics Laboratory, Department of Mechanical and Manufacturing Engineering, University of Cyprus, Nicosia, Cyprus.
⁸ Edwin L. Steele Laboratories, Department of Radiation Oncology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA.
⁹ Mass General Brigham Digital Health eCare, Somerville, MA, USA. sdutta1@partners.org.
¹⁰ Department of Emergency Medicine, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA. sdutta1@partners.org.
¹¹ Edwin L. Steele Laboratories, Department of Radiation Oncology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA. jain@steele.mgh.harvard.edu.

^# Contributed equally.

Abstract

As predicting the trajectory of COVID-19 is challenging, machine learning models could assist physicians in identifying high-risk individuals. This study compares the performance of 18 machine learning algorithms for predicting ICU admission and mortality among COVID-19 patients. Using COVID-19 patient data from the Mass General Brigham (MGB) Healthcare database, we developed and internally validated models using patients presenting to the Emergency Department (ED) between March-April 2020 (n = 3597) and further validated them using temporally distinct individuals who presented to the ED between May-August 2020 (n = 1711). We show that ensemble-based models perform better than other model types at predicting both 5-day ICU admission and 28-day mortality from COVID-19. CRP, LDH, and O₂ saturation were important for ICU admission models whereas eGFR <60 ml/min/1.73 m², and neutrophil and lymphocyte percentages were the most important variables for predicting mortality. Implementing such models could help in clinical decision-making for future infectious disease outbreaks including COVID-19.

Abstract

Grants and funding