Factors associated with resistance to SARSCoV- 2 infection discovered using large-scale medical record data and machine learning

Kai Wen K. Yang; Chloé F. Paris; Kevin T. Gorman; Ilia Rattsev; Rebecca H. Yoo; Yijia Chen; Jacob M. Desman; Tony Y. Wei; Joseph L. Greenstein; Casey Overby Taylor; Stuart C. Ray

doi:10.1371/journal.pone.0278466

Factors associated with resistance to SARSCoV- 2 infection discovered using large-scale medical record data and machine learning

Kai Wen K. Yang, Chloé F. Paris, Kevin T. Gorman, Ilia Rattsev, Rebecca H. Yoo, Yijia Chen, Jacob M. Desman, Tony Y. Wei, Joseph L. Greenstein, Casey Overby Taylor, Stuart C. Ray

School of Medicine

Research output: Contribution to journal › Article › peer-review

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.

Original language	English (US)
Article number	e0278466
Journal	PloS one
Volume	18
Issue number	2 February
DOIs	https://doi.org/10.1371/journal.pone.0278466
State	Published - Feb 2023

ASJC Scopus subject areas

General

Access to Document

10.1371/journal.pone.0278466

Cite this

Yang, K. W. K., Paris, C. F., Gorman, K. T., Rattsev, I., Yoo, R. H., Chen, Y., Desman, J. M., Wei, T. Y., Greenstein, J. L., Taylor, C. O., & Ray, S. C. (2023). Factors associated with resistance to SARSCoV- 2 infection discovered using large-scale medical record data and machine learning. PloS one, 18(2 February), Article e0278466. https://doi.org/10.1371/journal.pone.0278466

@article{8d10fcec2e3b49e5b24f7fbe651418c1,

title = "Factors associated with resistance to SARSCoV- 2 infection discovered using large-scale medical record data and machine learning",

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.",

author = "Yang, {Kai Wen K.} and Paris, {Chlo{\'e} F.} and Gorman, {Kevin T.} and Ilia Rattsev and Yoo, {Rebecca H.} and Yijia Chen and Desman, {Jacob M.} and Wei, {Tony Y.} and Greenstein, {Joseph L.} and Taylor, {Casey Overby} and Ray, {Stuart C.}",

note = "Publisher Copyright: {\textcopyright} 2023 Yang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.",

year = "2023",

month = feb,

doi = "10.1371/journal.pone.0278466",

language = "English (US)",

volume = "18",

journal = "PloS one",

issn = "1932-6203",

publisher = "Public Library of Science",

number = "2 February",

}

TY - JOUR

T1 - Factors associated with resistance to SARSCoV- 2 infection discovered using large-scale medical record data and machine learning

AU - Yang, Kai Wen K.

AU - Paris, Chloé F.

AU - Gorman, Kevin T.

AU - Rattsev, Ilia

AU - Yoo, Rebecca H.

AU - Chen, Yijia

AU - Desman, Jacob M.

AU - Wei, Tony Y.

AU - Greenstein, Joseph L.

AU - Taylor, Casey Overby

AU - Ray, Stuart C.

N1 - Publisher Copyright: © 2023 Yang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

PY - 2023/2

Y1 - 2023/2

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85148549214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85148549214&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0278466

DO - 10.1371/journal.pone.0278466

M3 - Article

C2 - 36812214

AN - SCOPUS:85148549214

SN - 1932-6203

VL - 18

JO - PloS one

JF - PloS one

IS - 2 February

M1 - e0278466

ER -

Factors associated with resistance to SARSCoV- 2 infection discovered using large-scale medical record data and machine learning

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this