Automated prozone effect detection in ferritin homogeneous immunoassays using neural network classifiers

Kornel Papik, B. Molnár, Peter Fedorcsak, Rainer Schaefer, Fridl Lang, Lydia Sreter, J. Fehér, Z. Tulassay

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The application of turbidimetric homogeneous immunoassays made the determination of several plasma components widely available. The sensitivity and accuracy of these assays are appropriate enough for routine laboratory use; however, in the case of many pathologically high concentration samples, prozone effect (high dose hook effect) can be observed, that leads to false-negative determination. Up to the present there are no cost-effective algorithms available for the safe detection of the prozone effect. Pathological serum ferritin values can be elevated up to 5000 ng/ml, while the measuring range covers only the 0-440 ng/ml range by a commercial assay. The determination of samples with ferritin concentration 1500 ng/ml results in false-negative because of the overlapping measuring range and prozone effect range. The prozone effect can be recognised by analysis of reaction kinetics after measurement. We have developed a neural network classifier system to analyse reaction kinetics of the measurements and check the prozone effect. One thousand five hundred determinations and 77 patient samples were used for neural network training and test. Using the trained neural networks, false-negative results can be filtered immediately after the determination, without re-run; thus, the sensitivity of plasma ferritin determination may become reliable enough, even in the case of high concentration samples. Applying this new technology, false-negative serum ferritin determinations can be avoided, thus even a relatively high hook effect rate (5-12% in different patient groups) can be handled safely.

Original languageEnglish
Pages (from-to)471-476
Number of pages6
JournalClinical Chemistry and Laboratory Medicine
Volume37
Issue number4
DOIs
Publication statusPublished - 1999

Fingerprint

Ferritins
Immunoassay
Classifiers
Neural networks
Hooks
Reaction kinetics
Assays
Plasmas
Serum
Technology
Costs and Cost Analysis
Costs

Keywords

  • Ferritin
  • High-dose hook effect
  • Neural networks
  • Prozone effect
  • Turbidimetry

ASJC Scopus subject areas

  • Clinical Biochemistry

Cite this

Automated prozone effect detection in ferritin homogeneous immunoassays using neural network classifiers. / Papik, Kornel; Molnár, B.; Fedorcsak, Peter; Schaefer, Rainer; Lang, Fridl; Sreter, Lydia; Fehér, J.; Tulassay, Z.

In: Clinical Chemistry and Laboratory Medicine, Vol. 37, No. 4, 1999, p. 471-476.

Research output: Contribution to journalArticle

Papik, Kornel ; Molnár, B. ; Fedorcsak, Peter ; Schaefer, Rainer ; Lang, Fridl ; Sreter, Lydia ; Fehér, J. ; Tulassay, Z. / Automated prozone effect detection in ferritin homogeneous immunoassays using neural network classifiers. In: Clinical Chemistry and Laboratory Medicine. 1999 ; Vol. 37, No. 4. pp. 471-476.
@article{7f2ec1a70d9d42608b9ba04e133640d3,
title = "Automated prozone effect detection in ferritin homogeneous immunoassays using neural network classifiers",
abstract = "The application of turbidimetric homogeneous immunoassays made the determination of several plasma components widely available. The sensitivity and accuracy of these assays are appropriate enough for routine laboratory use; however, in the case of many pathologically high concentration samples, prozone effect (high dose hook effect) can be observed, that leads to false-negative determination. Up to the present there are no cost-effective algorithms available for the safe detection of the prozone effect. Pathological serum ferritin values can be elevated up to 5000 ng/ml, while the measuring range covers only the 0-440 ng/ml range by a commercial assay. The determination of samples with ferritin concentration 1500 ng/ml results in false-negative because of the overlapping measuring range and prozone effect range. The prozone effect can be recognised by analysis of reaction kinetics after measurement. We have developed a neural network classifier system to analyse reaction kinetics of the measurements and check the prozone effect. One thousand five hundred determinations and 77 patient samples were used for neural network training and test. Using the trained neural networks, false-negative results can be filtered immediately after the determination, without re-run; thus, the sensitivity of plasma ferritin determination may become reliable enough, even in the case of high concentration samples. Applying this new technology, false-negative serum ferritin determinations can be avoided, thus even a relatively high hook effect rate (5-12{\%} in different patient groups) can be handled safely.",
keywords = "Ferritin, High-dose hook effect, Neural networks, Prozone effect, Turbidimetry",
author = "Kornel Papik and B. Moln{\'a}r and Peter Fedorcsak and Rainer Schaefer and Fridl Lang and Lydia Sreter and J. Feh{\'e}r and Z. Tulassay",
year = "1999",
doi = "10.1515/CCLM.1999.076",
language = "English",
volume = "37",
pages = "471--476",
journal = "Clinical Chemistry and Laboratory Medicine",
issn = "1434-6621",
publisher = "Walter de Gruyter GmbH & Co. KG",
number = "4",

}

TY - JOUR

T1 - Automated prozone effect detection in ferritin homogeneous immunoassays using neural network classifiers

AU - Papik, Kornel

AU - Molnár, B.

AU - Fedorcsak, Peter

AU - Schaefer, Rainer

AU - Lang, Fridl

AU - Sreter, Lydia

AU - Fehér, J.

AU - Tulassay, Z.

PY - 1999

Y1 - 1999

N2 - The application of turbidimetric homogeneous immunoassays made the determination of several plasma components widely available. The sensitivity and accuracy of these assays are appropriate enough for routine laboratory use; however, in the case of many pathologically high concentration samples, prozone effect (high dose hook effect) can be observed, that leads to false-negative determination. Up to the present there are no cost-effective algorithms available for the safe detection of the prozone effect. Pathological serum ferritin values can be elevated up to 5000 ng/ml, while the measuring range covers only the 0-440 ng/ml range by a commercial assay. The determination of samples with ferritin concentration 1500 ng/ml results in false-negative because of the overlapping measuring range and prozone effect range. The prozone effect can be recognised by analysis of reaction kinetics after measurement. We have developed a neural network classifier system to analyse reaction kinetics of the measurements and check the prozone effect. One thousand five hundred determinations and 77 patient samples were used for neural network training and test. Using the trained neural networks, false-negative results can be filtered immediately after the determination, without re-run; thus, the sensitivity of plasma ferritin determination may become reliable enough, even in the case of high concentration samples. Applying this new technology, false-negative serum ferritin determinations can be avoided, thus even a relatively high hook effect rate (5-12% in different patient groups) can be handled safely.

AB - The application of turbidimetric homogeneous immunoassays made the determination of several plasma components widely available. The sensitivity and accuracy of these assays are appropriate enough for routine laboratory use; however, in the case of many pathologically high concentration samples, prozone effect (high dose hook effect) can be observed, that leads to false-negative determination. Up to the present there are no cost-effective algorithms available for the safe detection of the prozone effect. Pathological serum ferritin values can be elevated up to 5000 ng/ml, while the measuring range covers only the 0-440 ng/ml range by a commercial assay. The determination of samples with ferritin concentration 1500 ng/ml results in false-negative because of the overlapping measuring range and prozone effect range. The prozone effect can be recognised by analysis of reaction kinetics after measurement. We have developed a neural network classifier system to analyse reaction kinetics of the measurements and check the prozone effect. One thousand five hundred determinations and 77 patient samples were used for neural network training and test. Using the trained neural networks, false-negative results can be filtered immediately after the determination, without re-run; thus, the sensitivity of plasma ferritin determination may become reliable enough, even in the case of high concentration samples. Applying this new technology, false-negative serum ferritin determinations can be avoided, thus even a relatively high hook effect rate (5-12% in different patient groups) can be handled safely.

KW - Ferritin

KW - High-dose hook effect

KW - Neural networks

KW - Prozone effect

KW - Turbidimetry

UR - http://www.scopus.com/inward/record.url?scp=0032951017&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032951017&partnerID=8YFLogxK

U2 - 10.1515/CCLM.1999.076

DO - 10.1515/CCLM.1999.076

M3 - Article

C2 - 10369120

AN - SCOPUS:0032951017

VL - 37

SP - 471

EP - 476

JO - Clinical Chemistry and Laboratory Medicine

JF - Clinical Chemistry and Laboratory Medicine

SN - 1434-6621

IS - 4

ER -