Using clinical data to predict abnormal serum electrolytes and blood cell profiles

William M. Tierney, Douglas Martin, Siu Hui, Clement J. McDonald

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Objective: To identify clinical predictors of five abnormalities on the serum electrolyte panel and two abnormalities on the blood cell profile, to study which data elements carried predictive information, and to measure the predictive accuracy and stability of the resulting predictive equations. Design: Prospective data collection from a computerized medical database supplemented by data entered by physicians who ordered outpatient tests into microcomputers. Equations were derived during an eight-month period and later validated twice in the same setting. Setting: Academic primary care practice affiliated with a county hospital. Patients and participants: Patients were mostly black women; physicians were full-time academic general internists and medical residents. Measurements and main results: There were 6,570 electrolyte and blood cell profile panels ordered during the equation derivation period. The mean receiver operating characteristic (ROC) curve area for the seven equations was 0.849. For the 4,977 tests ordered during ten months of prospective validation, the mean ROC curve area was only 3% less. For three equations, ROC curve areas were lower for patients with unscheduled visits than for those with scheduled visits (p<0.05). Except for two equations involving abnormalities with very low prevalences, the equations were also well calibrated. Prior results for the abnormality being considered were the strongest predictors, followed by other laboratory results, diagnoses, and the physicians' estimate of the probability that the test would be abnormal. Conclusions: Clinical data can accurately predict abnormal results of common outpatient laboratory tests. Computers can help find the necessary data and produce estimates of risk.

Original languageEnglish
Pages (from-to)375-383
Number of pages9
JournalJournal of General Internal Medicine
Volume4
Issue number5
DOIs
StatePublished - Sep 1989

Fingerprint

ROC Curve
Electrolytes
Blood Cells
Physicians
Outpatients
Serum
County Hospitals
Clinical Laboratory Techniques
Microcomputers
Primary Health Care
Databases

Keywords

  • anemia, leukocytosis
  • computers
  • hyperkalemia
  • hypokalemia
  • hyponatremia
  • metabolic acidosis
  • metabolic alkalosis
  • prediction

ASJC Scopus subject areas

  • Internal Medicine

Cite this

Using clinical data to predict abnormal serum electrolytes and blood cell profiles. / Tierney, William M.; Martin, Douglas; Hui, Siu; McDonald, Clement J.

In: Journal of General Internal Medicine, Vol. 4, No. 5, 09.1989, p. 375-383.

Research output: Contribution to journalArticle

@article{d75e1f9d4f5f4e46967f8956e48a89bb,
title = "Using clinical data to predict abnormal serum electrolytes and blood cell profiles",
abstract = "Objective: To identify clinical predictors of five abnormalities on the serum electrolyte panel and two abnormalities on the blood cell profile, to study which data elements carried predictive information, and to measure the predictive accuracy and stability of the resulting predictive equations. Design: Prospective data collection from a computerized medical database supplemented by data entered by physicians who ordered outpatient tests into microcomputers. Equations were derived during an eight-month period and later validated twice in the same setting. Setting: Academic primary care practice affiliated with a county hospital. Patients and participants: Patients were mostly black women; physicians were full-time academic general internists and medical residents. Measurements and main results: There were 6,570 electrolyte and blood cell profile panels ordered during the equation derivation period. The mean receiver operating characteristic (ROC) curve area for the seven equations was 0.849. For the 4,977 tests ordered during ten months of prospective validation, the mean ROC curve area was only 3{\%} less. For three equations, ROC curve areas were lower for patients with unscheduled visits than for those with scheduled visits (p<0.05). Except for two equations involving abnormalities with very low prevalences, the equations were also well calibrated. Prior results for the abnormality being considered were the strongest predictors, followed by other laboratory results, diagnoses, and the physicians' estimate of the probability that the test would be abnormal. Conclusions: Clinical data can accurately predict abnormal results of common outpatient laboratory tests. Computers can help find the necessary data and produce estimates of risk.",
keywords = "anemia, leukocytosis, computers, hyperkalemia, hypokalemia, hyponatremia, metabolic acidosis, metabolic alkalosis, prediction",
author = "Tierney, {William M.} and Douglas Martin and Siu Hui and McDonald, {Clement J.}",
year = "1989",
month = "9",
doi = "10.1007/BF02599685",
language = "English",
volume = "4",
pages = "375--383",
journal = "Journal of General Internal Medicine",
issn = "0884-8734",
publisher = "Springer New York",
number = "5",

}

TY - JOUR

T1 - Using clinical data to predict abnormal serum electrolytes and blood cell profiles

AU - Tierney, William M.

AU - Martin, Douglas

AU - Hui, Siu

AU - McDonald, Clement J.

PY - 1989/9

Y1 - 1989/9

N2 - Objective: To identify clinical predictors of five abnormalities on the serum electrolyte panel and two abnormalities on the blood cell profile, to study which data elements carried predictive information, and to measure the predictive accuracy and stability of the resulting predictive equations. Design: Prospective data collection from a computerized medical database supplemented by data entered by physicians who ordered outpatient tests into microcomputers. Equations were derived during an eight-month period and later validated twice in the same setting. Setting: Academic primary care practice affiliated with a county hospital. Patients and participants: Patients were mostly black women; physicians were full-time academic general internists and medical residents. Measurements and main results: There were 6,570 electrolyte and blood cell profile panels ordered during the equation derivation period. The mean receiver operating characteristic (ROC) curve area for the seven equations was 0.849. For the 4,977 tests ordered during ten months of prospective validation, the mean ROC curve area was only 3% less. For three equations, ROC curve areas were lower for patients with unscheduled visits than for those with scheduled visits (p<0.05). Except for two equations involving abnormalities with very low prevalences, the equations were also well calibrated. Prior results for the abnormality being considered were the strongest predictors, followed by other laboratory results, diagnoses, and the physicians' estimate of the probability that the test would be abnormal. Conclusions: Clinical data can accurately predict abnormal results of common outpatient laboratory tests. Computers can help find the necessary data and produce estimates of risk.

AB - Objective: To identify clinical predictors of five abnormalities on the serum electrolyte panel and two abnormalities on the blood cell profile, to study which data elements carried predictive information, and to measure the predictive accuracy and stability of the resulting predictive equations. Design: Prospective data collection from a computerized medical database supplemented by data entered by physicians who ordered outpatient tests into microcomputers. Equations were derived during an eight-month period and later validated twice in the same setting. Setting: Academic primary care practice affiliated with a county hospital. Patients and participants: Patients were mostly black women; physicians were full-time academic general internists and medical residents. Measurements and main results: There were 6,570 electrolyte and blood cell profile panels ordered during the equation derivation period. The mean receiver operating characteristic (ROC) curve area for the seven equations was 0.849. For the 4,977 tests ordered during ten months of prospective validation, the mean ROC curve area was only 3% less. For three equations, ROC curve areas were lower for patients with unscheduled visits than for those with scheduled visits (p<0.05). Except for two equations involving abnormalities with very low prevalences, the equations were also well calibrated. Prior results for the abnormality being considered were the strongest predictors, followed by other laboratory results, diagnoses, and the physicians' estimate of the probability that the test would be abnormal. Conclusions: Clinical data can accurately predict abnormal results of common outpatient laboratory tests. Computers can help find the necessary data and produce estimates of risk.

KW - anemia, leukocytosis

KW - computers

KW - hyperkalemia

KW - hypokalemia

KW - hyponatremia

KW - metabolic acidosis

KW - metabolic alkalosis

KW - prediction

UR - http://www.scopus.com/inward/record.url?scp=0024447866&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024447866&partnerID=8YFLogxK

U2 - 10.1007/BF02599685

DO - 10.1007/BF02599685

M3 - Article

VL - 4

SP - 375

EP - 383

JO - Journal of General Internal Medicine

JF - Journal of General Internal Medicine

SN - 0884-8734

IS - 5

ER -