A joint latent class model for classifying severely hemorrhaging trauma patients Emergency Medicine

Mohammad H. Rahbar, Jing Ning, Sangbum Choi, Jin Piao, Chuan Hong, Hanwen Huang, Deborah J. Del Junco, Erin E. Fox, Elaheh Rahbar, John B. Holcomb

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Background: In trauma research, "massive transfusion" (MT), historically defined as receiving =10 units of red blood cells (RBCs) within 24 h of admission, has been routinely used as a "gold standard" for quantifying bleeding severity. Due to early in-hospital mortality, however, MT is subject to survivor bias and thus a poorly defined criterion to classify bleeding trauma patients. Methods: Using the data from a retrospective trauma transfusion study, we applied a latent-class (LC) mixture model to identify severely hemorrhaging (SH) patients. Based on the joint distribution of cumulative units of RBCs and binary survival outcome at 24 h of admission, we applied an expectation-maximization (EM) algorithm to obtain model parameters. Estimated posterior probabilities were used for patients' classification and compared with the MT rule. To evaluate predictive performance of the LC-based classification, we examined the role of six clinical variables as predictors using two separate logistic regression models. Results: Out of 471 trauma patients, 211 (45 %) were MT, while our latent SH classifier identified only 127 (27 %) of patients as SH. The agreement between the two classification methods was 73 %. A non-ignorable portion of patients (17 out of 68, 25 %) who died within 24 h were not classified as MT but the SH group included 62 patients (91 %) who died during the same period. Our comparison of the predictive models based on MT and SH revealed significant differences between the coefficients of potential predictors of patients who may be in need of activation of the massive transfusion protocol. Conclusions: The traditional MT classification does not adequately reflect transfusion practices and outcomes during the trauma reception and initial resuscitation phase. Although we have demonstrated that joint latent class modeling could be used to correct for potential bias caused by misclassification of severely bleeding patients, improvement in this approach could be made in the presence of time to event data from prospective studies.

Original languageEnglish
Article number602
JournalBMC Research Notes
Volume8
Issue number1
DOIs
Publication statusPublished - 2015 Oct 24
Externally publishedYes

Fingerprint

Emergency Medicine
Medicine
Joints
Wounds and Injuries
Blood
Resuscitation
Hemorrhage
Logistics
Classifiers
Chemical activation
Cells
Erythrocytes
Logistic Models
Hospital Mortality
Survivors
Cell Survival
Prospective Studies

Keywords

  • Induced censoring
  • Joint model
  • Latent variable
  • Massive transfusion
  • Mixture
  • Trauma

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

A joint latent class model for classifying severely hemorrhaging trauma patients Emergency Medicine. / Rahbar, Mohammad H.; Ning, Jing; Choi, Sangbum; Piao, Jin; Hong, Chuan; Huang, Hanwen; Del Junco, Deborah J.; Fox, Erin E.; Rahbar, Elaheh; Holcomb, John B.

In: BMC Research Notes, Vol. 8, No. 1, 602, 24.10.2015.

Research output: Contribution to journalArticle

Rahbar, MH, Ning, J, Choi, S, Piao, J, Hong, C, Huang, H, Del Junco, DJ, Fox, EE, Rahbar, E & Holcomb, JB 2015, 'A joint latent class model for classifying severely hemorrhaging trauma patients Emergency Medicine', BMC Research Notes, vol. 8, no. 1, 602. https://doi.org/10.1186/s13104-015-1563-4
Rahbar, Mohammad H. ; Ning, Jing ; Choi, Sangbum ; Piao, Jin ; Hong, Chuan ; Huang, Hanwen ; Del Junco, Deborah J. ; Fox, Erin E. ; Rahbar, Elaheh ; Holcomb, John B. / A joint latent class model for classifying severely hemorrhaging trauma patients Emergency Medicine. In: BMC Research Notes. 2015 ; Vol. 8, No. 1.
@article{4f8404221182469aa590f42853e8251b,
title = "A joint latent class model for classifying severely hemorrhaging trauma patients Emergency Medicine",
abstract = "Background: In trauma research, {"}massive transfusion{"} (MT), historically defined as receiving =10 units of red blood cells (RBCs) within 24 h of admission, has been routinely used as a {"}gold standard{"} for quantifying bleeding severity. Due to early in-hospital mortality, however, MT is subject to survivor bias and thus a poorly defined criterion to classify bleeding trauma patients. Methods: Using the data from a retrospective trauma transfusion study, we applied a latent-class (LC) mixture model to identify severely hemorrhaging (SH) patients. Based on the joint distribution of cumulative units of RBCs and binary survival outcome at 24 h of admission, we applied an expectation-maximization (EM) algorithm to obtain model parameters. Estimated posterior probabilities were used for patients' classification and compared with the MT rule. To evaluate predictive performance of the LC-based classification, we examined the role of six clinical variables as predictors using two separate logistic regression models. Results: Out of 471 trauma patients, 211 (45 {\%}) were MT, while our latent SH classifier identified only 127 (27 {\%}) of patients as SH. The agreement between the two classification methods was 73 {\%}. A non-ignorable portion of patients (17 out of 68, 25 {\%}) who died within 24 h were not classified as MT but the SH group included 62 patients (91 {\%}) who died during the same period. Our comparison of the predictive models based on MT and SH revealed significant differences between the coefficients of potential predictors of patients who may be in need of activation of the massive transfusion protocol. Conclusions: The traditional MT classification does not adequately reflect transfusion practices and outcomes during the trauma reception and initial resuscitation phase. Although we have demonstrated that joint latent class modeling could be used to correct for potential bias caused by misclassification of severely bleeding patients, improvement in this approach could be made in the presence of time to event data from prospective studies.",
keywords = "Induced censoring, Joint model, Latent variable, Massive transfusion, Mixture, Trauma",
author = "Rahbar, {Mohammad H.} and Jing Ning and Sangbum Choi and Jin Piao and Chuan Hong and Hanwen Huang and {Del Junco}, {Deborah J.} and Fox, {Erin E.} and Elaheh Rahbar and Holcomb, {John B.}",
year = "2015",
month = "10",
day = "24",
doi = "10.1186/s13104-015-1563-4",
language = "English",
volume = "8",
journal = "BMC Research Notes",
issn = "1756-0500",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - A joint latent class model for classifying severely hemorrhaging trauma patients Emergency Medicine

AU - Rahbar, Mohammad H.

AU - Ning, Jing

AU - Choi, Sangbum

AU - Piao, Jin

AU - Hong, Chuan

AU - Huang, Hanwen

AU - Del Junco, Deborah J.

AU - Fox, Erin E.

AU - Rahbar, Elaheh

AU - Holcomb, John B.

PY - 2015/10/24

Y1 - 2015/10/24

N2 - Background: In trauma research, "massive transfusion" (MT), historically defined as receiving =10 units of red blood cells (RBCs) within 24 h of admission, has been routinely used as a "gold standard" for quantifying bleeding severity. Due to early in-hospital mortality, however, MT is subject to survivor bias and thus a poorly defined criterion to classify bleeding trauma patients. Methods: Using the data from a retrospective trauma transfusion study, we applied a latent-class (LC) mixture model to identify severely hemorrhaging (SH) patients. Based on the joint distribution of cumulative units of RBCs and binary survival outcome at 24 h of admission, we applied an expectation-maximization (EM) algorithm to obtain model parameters. Estimated posterior probabilities were used for patients' classification and compared with the MT rule. To evaluate predictive performance of the LC-based classification, we examined the role of six clinical variables as predictors using two separate logistic regression models. Results: Out of 471 trauma patients, 211 (45 %) were MT, while our latent SH classifier identified only 127 (27 %) of patients as SH. The agreement between the two classification methods was 73 %. A non-ignorable portion of patients (17 out of 68, 25 %) who died within 24 h were not classified as MT but the SH group included 62 patients (91 %) who died during the same period. Our comparison of the predictive models based on MT and SH revealed significant differences between the coefficients of potential predictors of patients who may be in need of activation of the massive transfusion protocol. Conclusions: The traditional MT classification does not adequately reflect transfusion practices and outcomes during the trauma reception and initial resuscitation phase. Although we have demonstrated that joint latent class modeling could be used to correct for potential bias caused by misclassification of severely bleeding patients, improvement in this approach could be made in the presence of time to event data from prospective studies.

AB - Background: In trauma research, "massive transfusion" (MT), historically defined as receiving =10 units of red blood cells (RBCs) within 24 h of admission, has been routinely used as a "gold standard" for quantifying bleeding severity. Due to early in-hospital mortality, however, MT is subject to survivor bias and thus a poorly defined criterion to classify bleeding trauma patients. Methods: Using the data from a retrospective trauma transfusion study, we applied a latent-class (LC) mixture model to identify severely hemorrhaging (SH) patients. Based on the joint distribution of cumulative units of RBCs and binary survival outcome at 24 h of admission, we applied an expectation-maximization (EM) algorithm to obtain model parameters. Estimated posterior probabilities were used for patients' classification and compared with the MT rule. To evaluate predictive performance of the LC-based classification, we examined the role of six clinical variables as predictors using two separate logistic regression models. Results: Out of 471 trauma patients, 211 (45 %) were MT, while our latent SH classifier identified only 127 (27 %) of patients as SH. The agreement between the two classification methods was 73 %. A non-ignorable portion of patients (17 out of 68, 25 %) who died within 24 h were not classified as MT but the SH group included 62 patients (91 %) who died during the same period. Our comparison of the predictive models based on MT and SH revealed significant differences between the coefficients of potential predictors of patients who may be in need of activation of the massive transfusion protocol. Conclusions: The traditional MT classification does not adequately reflect transfusion practices and outcomes during the trauma reception and initial resuscitation phase. Although we have demonstrated that joint latent class modeling could be used to correct for potential bias caused by misclassification of severely bleeding patients, improvement in this approach could be made in the presence of time to event data from prospective studies.

KW - Induced censoring

KW - Joint model

KW - Latent variable

KW - Massive transfusion

KW - Mixture

KW - Trauma

UR - http://www.scopus.com/inward/record.url?scp=84945133214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945133214&partnerID=8YFLogxK

U2 - 10.1186/s13104-015-1563-4

DO - 10.1186/s13104-015-1563-4

M3 - Article

VL - 8

JO - BMC Research Notes

JF - BMC Research Notes

SN - 1756-0500

IS - 1

M1 - 602

ER -