Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 1.06 MB
Add to list
  1. Search results
  2. Using structured pathology data to pr...

Using structured pathology data to predict hospital-wide mortality at admission

Mieke Deschepper (UGent) , Willem Waegeman (UGent) , Dirk Vogelaers (UGent) and Kristof Eeckloo (UGent)
(2020) PLOS ONE. 15(6).
Author
Organization
Abstract
Early prediction of in-hospital mortality can improve patient outcome. Current prediction models for in-hospital mortality focus mainly on specific pathologies. Structured pathology data is hospital-wide readily available and is primarily used for e.g. financing purposes. We aim to build a predictive model at admission using the International Classification of Diseases (ICD) codes as predictors and investigate the effect of the self-evident DNR ("Do Not Resuscitate") diagnosis codes and palliative care codes. We compare the models using ICD-10-CM codes with Risk of Mortality (RoM) and Charlson Comorbidity Index (CCI) as predictors using the Random Forests modeling approach. We use the Present on Admission flag to distinguish which diagnoses are present on admission. The study is performed in a single center (Ghent University Hospital) with the inclusion of 36 368 patients, all discharged in 2017. Our model at admission using ICD-10-CM codes (AUCROC = 0.9477) outperforms the model using RoM (AUCROC = 0.8797 and CCI (AUCROC = 0.7435). We confirmed that DNR and palliative care codes have a strong impact on the model resulting in a decrease of 7% for the ICD model (AUCROC = 0.8791) at admission. We therefore conclude that a model with a sufficient predictive performance can be derived from structured pathology data, and if real-time available, can serve as a prerequisite to develop a practical clinical decision support system for physicians.
Keywords
General Biochemistry, Genetics and Molecular Biology, General Agricultural and Biological Sciences, General Medicine, INTENSIVE-CARE-UNIT, IMPROVE RISK-ADJUSTMENT, INPATIENT MORTALITY, ICD-9-CM, MODELS

Downloads

  • Download
    KERMIT-A1-579.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.06 MB

Citation

Please use this url to cite or link to this publication:

MLA
Deschepper, Mieke, et al. “Using Structured Pathology Data to Predict Hospital-Wide Mortality at Admission.” PLOS ONE, vol. 15, no. 6, 2020, doi:10.1371/journal.pone.0235117.
APA
Deschepper, M., Waegeman, W., Vogelaers, D., & Eeckloo, K. (2020). Using structured pathology data to predict hospital-wide mortality at admission. PLOS ONE, 15(6). https://doi.org/10.1371/journal.pone.0235117
Chicago author-date
Deschepper, Mieke, Willem Waegeman, Dirk Vogelaers, and Kristof Eeckloo. 2020. “Using Structured Pathology Data to Predict Hospital-Wide Mortality at Admission.” PLOS ONE 15 (6). https://doi.org/10.1371/journal.pone.0235117.
Chicago author-date (all authors)
Deschepper, Mieke, Willem Waegeman, Dirk Vogelaers, and Kristof Eeckloo. 2020. “Using Structured Pathology Data to Predict Hospital-Wide Mortality at Admission.” PLOS ONE 15 (6). doi:10.1371/journal.pone.0235117.
Vancouver
1.
Deschepper M, Waegeman W, Vogelaers D, Eeckloo K. Using structured pathology data to predict hospital-wide mortality at admission. PLOS ONE. 2020;15(6).
IEEE
[1]
M. Deschepper, W. Waegeman, D. Vogelaers, and K. Eeckloo, “Using structured pathology data to predict hospital-wide mortality at admission,” PLOS ONE, vol. 15, no. 6, 2020.
@article{8671038,
  abstract     = {{Early prediction of in-hospital mortality can improve patient outcome. Current prediction models for in-hospital mortality focus mainly on specific pathologies. Structured pathology data is hospital-wide readily available and is primarily used for e.g. financing purposes. We aim to build a predictive model at admission using the International Classification of Diseases (ICD) codes as predictors and investigate the effect of the self-evident DNR ("Do Not Resuscitate") diagnosis codes and palliative care codes. We compare the models using ICD-10-CM codes with Risk of Mortality (RoM) and Charlson Comorbidity Index (CCI) as predictors using the Random Forests modeling approach. We use the Present on Admission flag to distinguish which diagnoses are present on admission. The study is performed in a single center (Ghent University Hospital) with the inclusion of 36 368 patients, all discharged in 2017. Our model at admission using ICD-10-CM codes (AUCROC = 0.9477) outperforms the model using RoM (AUCROC = 0.8797 and CCI (AUCROC = 0.7435). We confirmed that DNR and palliative care codes have a strong impact on the model resulting in a decrease of 7% for the ICD model (AUCROC = 0.8791) at admission. We therefore conclude that a model with a sufficient predictive performance can be derived from structured pathology data, and if real-time available, can serve as a prerequisite to develop a practical clinical decision support system for physicians.}},
  articleno    = {{e0235117}},
  author       = {{Deschepper, Mieke and Waegeman, Willem and Vogelaers, Dirk and Eeckloo, Kristof}},
  issn         = {{1932-6203}},
  journal      = {{PLOS ONE}},
  keywords     = {{General Biochemistry,Genetics and Molecular Biology,General Agricultural and Biological Sciences,General Medicine,INTENSIVE-CARE-UNIT,IMPROVE RISK-ADJUSTMENT,INPATIENT MORTALITY,ICD-9-CM,MODELS}},
  language     = {{eng}},
  number       = {{6}},
  pages        = {{11}},
  title        = {{Using structured pathology data to predict hospital-wide mortality at admission}},
  url          = {{http://doi.org/10.1371/journal.pone.0235117}},
  volume       = {{15}},
  year         = {{2020}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: