Mount Sinai researchers develop COVID-19 mortality prediction model

September 22, 2020

Bottom Line:

Given the toll that the COVID-19 pandemic has taken on people's health and lives worldwide, it is crucial to be able to accurately predict patients' outcomes, including their chances of mortality from the disease. Using the largest clinical dataset to date, and a systematical machine learning framework, the research team at Mount Sinai identified an accurate and parsimonious prediction model of COVID-19 mortality.

This model was based on only three routinely collected clinical features, namely patient's age, minimum oxygen saturation over the course of their medical encounter, and type of patient encounter (inpatient vs outpatient and telehealth visits).

This model could yield an additional "vital sign" that is assessed regularly during a patient's hospital course, that can be integrated into the clinical care flow of a COVID-19 patient. Clinical teams could use results from the prediction model throughout COVID-19 patients' hospital courses to flag individuals at high risk of death so that they can promptly focus treatment and attention on such individuals to prevent their mortality.

Main Findings:

Using the largest development dataset yet (n=3841), and a systematic machine learning framework, we developed a COVID-19 mortality prediction model that showed high accuracy (AUC=0·91) when applied to test datasets of retrospective (n=961) and prospective (n=249) patients. This model was based on three clinical features: patient's age, minimum oxygen saturation over the course of their medical encounter, and type of patient encounter (inpatient vs outpatient and telehealth visits).

Motivation of the research:

The COVID-19 pandemic has affected millions of individuals and caused hundreds of thousands of deaths worldwide;

"Predicting mortality among patients with COVID-19 who present with a spectrum of complications is very difficult, hindering the prognostication and management of the disease," said Dr. Gaurav Pandey, Assistant Professor of Genetics and Genomic Sciences. "We aimed to develop an accurate prediction model of COVID-19 mortality using unbiased computational methods, and identify the clinical features most predictive of this outcome."
Yadaw AS, Li Y-C, Bose S, Iyengar R, Bunyavanich S, Pandey G. Clinical features of COVID-19 mortality: development and validation of a clinical prediction model. Lancet Digital Health 2020; 2: e516-25, doi: 10.1016/S2589-7500(20)30217-X

Manuscript Title:

Clinical features of COVID-19 mortality: development and validation of a clinical prediction model



The Lancet Digital Health

The Mount Sinai Hospital / Mount Sinai School of Medicine

Related Mortality Articles from Brightsurf:

Being in treatment with statins reduces COVID-19 mortality by 22% to 25%
A research by the Universitat Rovira i Virgili (URV) and Pere Virgili Institut (IISPV) led by Lluís Masana has found that people who are being treated with statins have a 22% to 25% lower risk of dying from COVID-19.

Mortality rate higher for US rural residents
A recent study by Syracuse University sociology professor Shannon Monnat shows that mortality rates are higher for U.S. working-age residents who live in rural areas instead of metro areas, and the gap is getting wider.

COVID-19, excess all-cause mortality in US, 18 comparison countries
COVID-19 deaths and excess all-cause mortality in the U.S. are compared with 18 countries with diverse COVID-19 responses in this study.

New analysis shows hydroxychloroquine does not lower mortality in COVID-19 patients, and is associated with increased mortality when combined with the antibiotic azithromycin
A new meta-analysis of published studies into the drug hydroxychloroquine shows that it does not lower mortality in COVID-19 patients, and using it combined with the antibiotic azithromycin is associated with a 27% increased mortality.

Hydroxychloroquine reduces in-hospital COVID-19 mortality
An Italian observational study contributes to the ongoing debate regarding the use of hydroxychloroquine in the current pandemic.

What's the best way to estimate and track COVID-19 mortality?
When used correctly, the symptomatic case fatality ratio (sCFR) and the infection fatality ratio (IFR) are better measures by which to monitor COVID-19 epidemics than the commonly reported case fatality ratio (CFR), according to a new study published this week in PLOS Medicine by Anthony Hauser of the University of Bern, Switzerland, and colleagues.

COVID-19: Bacteriophage could decrease mortality
Bacteriophage can reduce bacterial growth in the lungs, limiting fluid build-up.

COPD and smoking associated with higher COVID-19 mortality
Current smokers and people with chronic obstructive pulmonary disease (COPD) have an increased risk of severe complications and higher mortality with COVID-19 infection, according to a new study published May 11, 2020 in the open-access journal PLOS ONE by Jaber Alqahtani of University College London, UK, and colleagues.

Highest mortality risks for poor and unemployed
Large dataset shows that income, work status and education have a clear influence on mortality in Germany.

Addressing causes of mortality in Zambia
Despite the fact that people in sub-Saharan Africa are now living longer than they did two decades ago, their average life expectancy remains below that of the rest of the world population.

Read More: Mortality News and Mortality Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to