In:
PLOS ONE, Public Library of Science (PLoS), Vol. 18, No. 2 ( 2023-2-22), p. e0278466-
Abstract:
There have been over 621 million cases of COVID-19 worldwide with over 6.5 million deaths. Despite the high secondary attack rate of COVID-19 in shared households, some exposed individuals do not contract the virus. In addition, little is known about whether the occurrence of COVID-19 resistance differs among people by health characteristics as stored in the electronic health records (EHR). In this retrospective analysis, we develop a statistical model to predict COVID-19 resistance in 8,536 individuals with prior COVID-19 exposure using demographics, diagnostic codes, outpatient medication orders, and count of Elixhauser comorbidities in EHR data from the COVID-19 Precision Medicine Platform Registry. Cluster analyses identified 5 patterns of diagnostic codes that distinguished resistant from non-resistant patients in our study population. In addition, our models showed modest performance in predicting COVID-19 resistance (best performing model AUROC = 0.61). Monte Carlo simulations conducted indicated that the AUROC results are statistically significant ( p 〈 0.001) for the testing set. We hope to validate the features found to be associated with resistance/non-resistance through more advanced association studies.
Type of Medium:
Online Resource
ISSN:
1932-6203
DOI:
10.1371/journal.pone.0278466
DOI:
10.1371/journal.pone.0278466.g001
DOI:
10.1371/journal.pone.0278466.g002
DOI:
10.1371/journal.pone.0278466.g003
DOI:
10.1371/journal.pone.0278466.g004
DOI:
10.1371/journal.pone.0278466.g005
DOI:
10.1371/journal.pone.0278466.t001
DOI:
10.1371/journal.pone.0278466.t002
DOI:
10.1371/journal.pone.0278466.t003
DOI:
10.1371/journal.pone.0278466.s001
DOI:
10.1371/journal.pone.0278466.s002
DOI:
10.1371/journal.pone.0278466.r001
DOI:
10.1371/journal.pone.0278466.r002
DOI:
10.1371/journal.pone.0278466.r003
DOI:
10.1371/journal.pone.0278466.r004
Language:
English
Publisher:
Public Library of Science (PLoS)
Publication Date:
2023
detail.hit.zdb_id:
2267670-3
Bookmarklink