Can data from an electronic medical record identify which patients with pneumonia have Pneumocystis carinii infection?

Lameck Diero, Troy Stiffler, Robert Einterz, William M. Tierney

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Pneumocystis carinii is the leading opportunistic pulmonary infection in HIV-infected patients. Invasive diagnostic procedures might be avoided if available electronic data can accurately identify patients with Pneumocystis pneumonia (PCP). We extracted data from electronic hospital records, emergency department records, and a pathology database for 299 HIV-infected patients with pneumonia who underwent bronchoscopy. We identified independent indicators of confirmed PCP using logistic regression analysis on a random half of the patients and validated the predictive power of the resulting model on the other half. Bronchoscopy confirmed pneumocystis carinii in 111 patients (37%). Five of the seven significant independent predictors of PCP came from patients' electronic medical records: infiltrate on chest radiograph, male gender, lower red cell distribution width, lower serum creatinine, and a prior positive HIV test. The other two (duration of illness and presence of dyspnea) came from the emergency department record. A simple index found 43% of patients at low risk (18% with pneumocystis), 37% at moderate risk (36% with pneumocystis), and 20% at high risk (74% with pneumocystis). Data from electronic medical records can help quantify the risk of PCP among HIV-infected patients. However, the model failed to identify 18% of patients with PCP in the low risk group, and empiric therapy would erroneously treat 26% of patients classified as high risk. Bronchoscopy is needed to accurately diagnose PCP among HIV-infected patients with pneumonia. However, if bronchoscopy is not available, the model can help with initial decisions about antibiotic therapy.

Original languageEnglish
Pages (from-to)743-750
Number of pages8
JournalInternational Journal of Medical Informatics
Volume73
Issue number11-12
DOIs
StatePublished - Nov 2004

Fingerprint

Pneumocystis Infections
Electronic Health Records
Pneumonia
Pneumocystis Pneumonia
Pneumocystis
Bronchoscopy
HIV
Pneumocystis carinii
Hospital Emergency Service
Erythrocyte Indices
Hospital Records
Opportunistic Infections
Group Psychotherapy
Dyspnea
Creatinine

Keywords

  • Acquired immunodeficiency syndrome
  • AIDS
  • Clinical prediction
  • HIV
  • Opportunistic infections
  • Pneumocystis carinii

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Can data from an electronic medical record identify which patients with pneumonia have Pneumocystis carinii infection? / Diero, Lameck; Stiffler, Troy; Einterz, Robert; Tierney, William M.

In: International Journal of Medical Informatics, Vol. 73, No. 11-12, 11.2004, p. 743-750.

Research output: Contribution to journalArticle

@article{6467360c72f04e9dbd6f48bc09048eb5,
title = "Can data from an electronic medical record identify which patients with pneumonia have Pneumocystis carinii infection?",
abstract = "Pneumocystis carinii is the leading opportunistic pulmonary infection in HIV-infected patients. Invasive diagnostic procedures might be avoided if available electronic data can accurately identify patients with Pneumocystis pneumonia (PCP). We extracted data from electronic hospital records, emergency department records, and a pathology database for 299 HIV-infected patients with pneumonia who underwent bronchoscopy. We identified independent indicators of confirmed PCP using logistic regression analysis on a random half of the patients and validated the predictive power of the resulting model on the other half. Bronchoscopy confirmed pneumocystis carinii in 111 patients (37{\%}). Five of the seven significant independent predictors of PCP came from patients' electronic medical records: infiltrate on chest radiograph, male gender, lower red cell distribution width, lower serum creatinine, and a prior positive HIV test. The other two (duration of illness and presence of dyspnea) came from the emergency department record. A simple index found 43{\%} of patients at low risk (18{\%} with pneumocystis), 37{\%} at moderate risk (36{\%} with pneumocystis), and 20{\%} at high risk (74{\%} with pneumocystis). Data from electronic medical records can help quantify the risk of PCP among HIV-infected patients. However, the model failed to identify 18{\%} of patients with PCP in the low risk group, and empiric therapy would erroneously treat 26{\%} of patients classified as high risk. Bronchoscopy is needed to accurately diagnose PCP among HIV-infected patients with pneumonia. However, if bronchoscopy is not available, the model can help with initial decisions about antibiotic therapy.",
keywords = "Acquired immunodeficiency syndrome, AIDS, Clinical prediction, HIV, Opportunistic infections, Pneumocystis carinii",
author = "Lameck Diero and Troy Stiffler and Robert Einterz and Tierney, {William M.}",
year = "2004",
month = "11",
doi = "10.1016/j.ijmedinf.2004.07.002",
language = "English",
volume = "73",
pages = "743--750",
journal = "International Journal of Medical Informatics",
issn = "1386-5056",
publisher = "Elsevier Ireland Ltd",
number = "11-12",

}

TY - JOUR

T1 - Can data from an electronic medical record identify which patients with pneumonia have Pneumocystis carinii infection?

AU - Diero, Lameck

AU - Stiffler, Troy

AU - Einterz, Robert

AU - Tierney, William M.

PY - 2004/11

Y1 - 2004/11

N2 - Pneumocystis carinii is the leading opportunistic pulmonary infection in HIV-infected patients. Invasive diagnostic procedures might be avoided if available electronic data can accurately identify patients with Pneumocystis pneumonia (PCP). We extracted data from electronic hospital records, emergency department records, and a pathology database for 299 HIV-infected patients with pneumonia who underwent bronchoscopy. We identified independent indicators of confirmed PCP using logistic regression analysis on a random half of the patients and validated the predictive power of the resulting model on the other half. Bronchoscopy confirmed pneumocystis carinii in 111 patients (37%). Five of the seven significant independent predictors of PCP came from patients' electronic medical records: infiltrate on chest radiograph, male gender, lower red cell distribution width, lower serum creatinine, and a prior positive HIV test. The other two (duration of illness and presence of dyspnea) came from the emergency department record. A simple index found 43% of patients at low risk (18% with pneumocystis), 37% at moderate risk (36% with pneumocystis), and 20% at high risk (74% with pneumocystis). Data from electronic medical records can help quantify the risk of PCP among HIV-infected patients. However, the model failed to identify 18% of patients with PCP in the low risk group, and empiric therapy would erroneously treat 26% of patients classified as high risk. Bronchoscopy is needed to accurately diagnose PCP among HIV-infected patients with pneumonia. However, if bronchoscopy is not available, the model can help with initial decisions about antibiotic therapy.

AB - Pneumocystis carinii is the leading opportunistic pulmonary infection in HIV-infected patients. Invasive diagnostic procedures might be avoided if available electronic data can accurately identify patients with Pneumocystis pneumonia (PCP). We extracted data from electronic hospital records, emergency department records, and a pathology database for 299 HIV-infected patients with pneumonia who underwent bronchoscopy. We identified independent indicators of confirmed PCP using logistic regression analysis on a random half of the patients and validated the predictive power of the resulting model on the other half. Bronchoscopy confirmed pneumocystis carinii in 111 patients (37%). Five of the seven significant independent predictors of PCP came from patients' electronic medical records: infiltrate on chest radiograph, male gender, lower red cell distribution width, lower serum creatinine, and a prior positive HIV test. The other two (duration of illness and presence of dyspnea) came from the emergency department record. A simple index found 43% of patients at low risk (18% with pneumocystis), 37% at moderate risk (36% with pneumocystis), and 20% at high risk (74% with pneumocystis). Data from electronic medical records can help quantify the risk of PCP among HIV-infected patients. However, the model failed to identify 18% of patients with PCP in the low risk group, and empiric therapy would erroneously treat 26% of patients classified as high risk. Bronchoscopy is needed to accurately diagnose PCP among HIV-infected patients with pneumonia. However, if bronchoscopy is not available, the model can help with initial decisions about antibiotic therapy.

KW - Acquired immunodeficiency syndrome

KW - AIDS

KW - Clinical prediction

KW - HIV

KW - Opportunistic infections

KW - Pneumocystis carinii

UR - http://www.scopus.com/inward/record.url?scp=7444267310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=7444267310&partnerID=8YFLogxK

U2 - 10.1016/j.ijmedinf.2004.07.002

DO - 10.1016/j.ijmedinf.2004.07.002

M3 - Article

C2 - 15491925

AN - SCOPUS:7444267310

VL - 73

SP - 743

EP - 750

JO - International Journal of Medical Informatics

JF - International Journal of Medical Informatics

SN - 1386-5056

IS - 11-12

ER -