eARDS: A multi-center validation of an interpretable machine learning algorithm of early onset Acute Respiratory Distress Syndrome (ARDS) among critically ill adults with COVID-19

Lakshya Singhal; Yash Garg; Philip Yang; Azade Tabaie; A. Ian Wong; Akram Mohammed; Lokesh Chinthala; Dipen Kadaria; Amik Sodhi; Andre L. Holder; Annette Esper; James M. Blum; Robert L. Davis; Gari D. Clifford; Greg S. Martin; Rishikesan Kamaleswaran

doi:10.1371/journal.pone.0257056

Back

eARDS: A multi-center validation of an interpretable machine learning algorithm of early onset Acute Respiratory Distress Syndrome (ARDS) among critically ill adults with COVID-19

Journal article

Open access

Peer reviewed

eARDS: A multi-center validation of an interpretable machine learning algorithm of early onset Acute Respiratory Distress Syndrome (ARDS) among critically ill adults with COVID-19

Lakshya Singhal, Yash Garg, Philip Yang, Azade Tabaie, A. Ian Wong, Akram Mohammed, Lokesh Chinthala, Dipen Kadaria, Amik Sodhi, Andre L. Holder, …

PloS one, Vol.16(9), pp.e0257056-e0257056

09/24/2021

DOI: 10.1371/journal.pone.0257056

PMCID: PMC8462682

PMID: 34559819

Files and links (1)

url

https://doi.org/10.1371/journal.pone.0257056View

Published (Version of record) Open Access

Abstract

We present an interpretable machine learning algorithm called 'eARDS' for predicting ARDS in an ICU population comprising COVID-19 patients, up to 12-hours before satisfying the Berlin clinical criteria. The analysis was conducted on data collected from the Intensive care units (ICU) at Emory Healthcare, Atlanta, GA and University of Tennessee Health Science Center, Memphis, TN and the Cerner (R) Health Facts Deidentified Database, a multi-site COVID-19 EMR database. The participants in the analysis consisted of adults over 18 years of age. Clinical data from 35,804 patients who developed ARDS and controls were used to generate predictive models that identify risk for ARDS onset up to 12-hours before satisfying the Berlin criteria. We identified salient features from the electronic medical record that predicted respiratory failure among this population. The machine learning algorithm which provided the best performance exhibited AUROC of 0.89 (95% CI = 0.88-0.90), sensitivity of 0.77 (95% CI = 0.75-0.78), specificity 0.85 (95% CI = 085-0.86). Validation performance across two separate health systems (comprising 899 COVID-19 patients) exhibited AUROC of 0.82 (0.81-0.83) and 0.89 (0.87, 0.90). Important features for prediction of ARDS included minimum oxygen saturation (SpO(2)), standard deviation of the systolic blood pressure (SBP), O-2 flow, and maximum respiratory rate over an observational window of 16-hours. Analyzing the performance of the model across various cohorts indicates that the model performed best among a younger age group (18-40) (AUROC = 0.93 [0.92-0.94]), compared to an older age group (80+) (AUROC = 0.81 [0.81-0.82]). The model performance was comparable on both male and female groups, but performed significantly better on the severe ARDS group compared to the mild and moderate groups. The eARDS system demonstrated robust performance for predicting COVID19 patients who developed ARDS at least 12-hours before the Berlin clinical criteria, across two independent health systems.

Multidisciplinary Sciences

Science & Technology

Science & Technology - Other Topics

Details

Title: Subtitle: eARDS: A multi-center validation of an interpretable machine learning algorithm of early onset Acute Respiratory Distress Syndrome (ARDS) among critically ill adults with COVID-19
Creators: Lakshya Singhal - Emory University
Yash Garg - Emory University
Philip Yang - Emory University
Azade Tabaie - Emory University
A. Ian Wong - Emory University
Akram Mohammed - Univ Tennessee, Hlth Sci Ctr, Dept Pediat, Memphis, TN USA
Lokesh Chinthala - University of Tennessee Health Science Center
Dipen Kadaria - University of Tennessee Health Science Center
Amik Sodhi - University of Tennessee Health Science Center
Andre L. Holder - Emory University
Annette Esper - Emory University
James M. Blum - Emory University
Robert L. Davis - University of Tennessee Health Science Center
Gari D. Clifford - Georgia Institute of Technology
Greg S. Martin - Emory University
Rishikesan Kamaleswaran - Georgia Institute of Technology
Resource Type: Journal article
Publication Details: PloS one, Vol.16(9), pp.e0257056-e0257056
DOI: 10.1371/journal.pone.0257056
PMID: 34559819
PMCID: PMC8462682
NLM abbreviation: PLoS One
ISSN: 1932-6203
eISSN: 1932-6203
Publisher: Public Library Science
Number of pages: 17
Grant note: 2T32GM095442 / NIGMS; United States Department of Health & Human Services; National Institutes of Health (NIH) - USA; NIH National Institute of General Medical Sciences (NIGMS) UL1TR002378 / NCATS of the NIH UL1TR002378; TL1TR002382 / National Center for Advancing Translational Sciences of the National Institutes of Health; United States Department of Health & Human Services; National Institutes of Health (NIH) - USA; NIH National Center for Advancing Translational Sciences (NCATS) USUHS HT9404-13-1-0032; HU0001-15-2-0001 / Surgical Critical Care Initiative (SC2i), Department of Defenses Defense Health Program Joint Program Committee 6 / Combat Casualty Care K23GM137182 / National Institute for General Medical Sciences of the National Institutes of Health
Language: English
Date published: 09/24/2021
Academic Unit: Anesthesia
Record Identifier: 9984295926102771

Metrics

12 Record Views

33 Times Cited - Web of Science