Diagnostic accuracy of pancreatic enzymes evaluated by use of multivariate data analysis

Steven (Steve) Kazmierczak, Paul G. Catrou, Frederick Van Lente

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

We analyzed pancreatic enzyme data from 508 patients with suspected pancreatitis by neural network analysis, by an Expert multirule generation protocol, and by receiveroperator characteristic (ROC) curve analysis of a single test result. Neural network analysis showed that use of lipase provided the best means for diagnosing pancreatitis. Diagnostic accuracies achieved by using amylase only, lipase only, and amylase and lipase in combination were 76%, 82%, and 84%, respectively. Use of the Expert rule generation protocol provided a diagnostic accuracy of 92% when rules for single and multiple samplings were combined. ROC curve analysis for initial enzyme activities showed the maximal diagnostic accuracy to be 82% and 85% for amylase and lipase, respectively; use of peak enzyme activities yielded accuracies of 81% and 88%, respectively. The evaluation of laboratory test data should include analysis of the diagnostic accuracy of laboratory tests by multivariate techniques such as neural network analysis or an Expert systems approach. Multivariate analysis should allow for a more realistic assessment of the diagnosis accuracy of laboratory tests because all the available data are included in the evaluation.

Original languageEnglish (US)
Pages (from-to)1960-1965
Number of pages6
JournalClinical Chemistry
Volume39
Issue number9
StatePublished - 1993
Externally publishedYes

Fingerprint

Lipase
Amylases
Multivariate Analysis
Electric network analysis
Enzyme activity
Enzymes
Neural networks
Pancreatitis
Clinical Laboratory Techniques
Systems Analysis
Expert systems
Sampling

Keywords

  • Amylase
  • Lipase
  • Neural networks
  • Pancreatitis
  • Receiver-operator characteristic curve

ASJC Scopus subject areas

  • Clinical Biochemistry

Cite this

Diagnostic accuracy of pancreatic enzymes evaluated by use of multivariate data analysis. / Kazmierczak, Steven (Steve); Catrou, Paul G.; Van Lente, Frederick.

In: Clinical Chemistry, Vol. 39, No. 9, 1993, p. 1960-1965.

Research output: Contribution to journalArticle

Kazmierczak, Steven (Steve) ; Catrou, Paul G. ; Van Lente, Frederick. / Diagnostic accuracy of pancreatic enzymes evaluated by use of multivariate data analysis. In: Clinical Chemistry. 1993 ; Vol. 39, No. 9. pp. 1960-1965.
@article{4f8fe70f9cfa4d058bae782fe67130e7,
title = "Diagnostic accuracy of pancreatic enzymes evaluated by use of multivariate data analysis",
abstract = "We analyzed pancreatic enzyme data from 508 patients with suspected pancreatitis by neural network analysis, by an Expert multirule generation protocol, and by receiveroperator characteristic (ROC) curve analysis of a single test result. Neural network analysis showed that use of lipase provided the best means for diagnosing pancreatitis. Diagnostic accuracies achieved by using amylase only, lipase only, and amylase and lipase in combination were 76{\%}, 82{\%}, and 84{\%}, respectively. Use of the Expert rule generation protocol provided a diagnostic accuracy of 92{\%} when rules for single and multiple samplings were combined. ROC curve analysis for initial enzyme activities showed the maximal diagnostic accuracy to be 82{\%} and 85{\%} for amylase and lipase, respectively; use of peak enzyme activities yielded accuracies of 81{\%} and 88{\%}, respectively. The evaluation of laboratory test data should include analysis of the diagnostic accuracy of laboratory tests by multivariate techniques such as neural network analysis or an Expert systems approach. Multivariate analysis should allow for a more realistic assessment of the diagnosis accuracy of laboratory tests because all the available data are included in the evaluation.",
keywords = "Amylase, Lipase, Neural networks, Pancreatitis, Receiver-operator characteristic curve",
author = "Kazmierczak, {Steven (Steve)} and Catrou, {Paul G.} and {Van Lente}, Frederick",
year = "1993",
language = "English (US)",
volume = "39",
pages = "1960--1965",
journal = "Clinical Chemistry",
issn = "0009-9147",
publisher = "American Association for Clinical Chemistry Inc.",
number = "9",

}

TY - JOUR

T1 - Diagnostic accuracy of pancreatic enzymes evaluated by use of multivariate data analysis

AU - Kazmierczak, Steven (Steve)

AU - Catrou, Paul G.

AU - Van Lente, Frederick

PY - 1993

Y1 - 1993

N2 - We analyzed pancreatic enzyme data from 508 patients with suspected pancreatitis by neural network analysis, by an Expert multirule generation protocol, and by receiveroperator characteristic (ROC) curve analysis of a single test result. Neural network analysis showed that use of lipase provided the best means for diagnosing pancreatitis. Diagnostic accuracies achieved by using amylase only, lipase only, and amylase and lipase in combination were 76%, 82%, and 84%, respectively. Use of the Expert rule generation protocol provided a diagnostic accuracy of 92% when rules for single and multiple samplings were combined. ROC curve analysis for initial enzyme activities showed the maximal diagnostic accuracy to be 82% and 85% for amylase and lipase, respectively; use of peak enzyme activities yielded accuracies of 81% and 88%, respectively. The evaluation of laboratory test data should include analysis of the diagnostic accuracy of laboratory tests by multivariate techniques such as neural network analysis or an Expert systems approach. Multivariate analysis should allow for a more realistic assessment of the diagnosis accuracy of laboratory tests because all the available data are included in the evaluation.

AB - We analyzed pancreatic enzyme data from 508 patients with suspected pancreatitis by neural network analysis, by an Expert multirule generation protocol, and by receiveroperator characteristic (ROC) curve analysis of a single test result. Neural network analysis showed that use of lipase provided the best means for diagnosing pancreatitis. Diagnostic accuracies achieved by using amylase only, lipase only, and amylase and lipase in combination were 76%, 82%, and 84%, respectively. Use of the Expert rule generation protocol provided a diagnostic accuracy of 92% when rules for single and multiple samplings were combined. ROC curve analysis for initial enzyme activities showed the maximal diagnostic accuracy to be 82% and 85% for amylase and lipase, respectively; use of peak enzyme activities yielded accuracies of 81% and 88%, respectively. The evaluation of laboratory test data should include analysis of the diagnostic accuracy of laboratory tests by multivariate techniques such as neural network analysis or an Expert systems approach. Multivariate analysis should allow for a more realistic assessment of the diagnosis accuracy of laboratory tests because all the available data are included in the evaluation.

KW - Amylase

KW - Lipase

KW - Neural networks

KW - Pancreatitis

KW - Receiver-operator characteristic curve

UR - http://www.scopus.com/inward/record.url?scp=0027284264&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027284264&partnerID=8YFLogxK

M3 - Article

VL - 39

SP - 1960

EP - 1965

JO - Clinical Chemistry

JF - Clinical Chemistry

SN - 0009-9147

IS - 9

ER -