Reduction of multi-dimensional laboratory data to a two-dimensional plot: A novel technique for the identification of laboratory error

Steven (Steve) Kazmierczak, Todd K. Leen, Deniz Erdogmus, Miguel A. Carreira-Perpinan

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Background: The clinical laboratory generates large amounts of patient-specific data. Detection of errors that arise during pre-analytical, analytical, and post-analytical processes is difficult. We performed a pilot study, utilizing a multidimensional data reduction technique, to assess the utility of this method for identifying errors in laboratory data. Methods: We evaluated 13,670 individual patient records collected over a 2-month period from hospital inpatients and outpatients. We utilized those patient records that contained a complete set of 14 different biochemical analytes. We used two-dimensional generative topographic mapping to project the 14-dimensional record to a two-dimensional space. Results and conclusions: The use of a two-dimensional generative topographic mapping technique to plot multi-analyte patient data as a two-dimensional graph allows for the rapid identification of potentially anomalous data. Although we performed a retrospective analysis, this technique has the benefit of being able to assess laboratory-generated data in real time, allowing for the rapid identification and correction of anomalous data before they are released to the physician. In addition, serial laboratory multi-analyte data for an individual patient can also be plotted as a two-dimensional plot. This tool might also be useful for assessing patient wellbeing and prognosis.

Original languageEnglish (US)
Pages (from-to)749-752
Number of pages4
JournalClinical Chemistry and Laboratory Medicine
Volume45
Issue number6
DOIs
StatePublished - Jun 1 2007

Fingerprint

Clinical laboratories
Data reduction
Inpatients
Outpatients
Physicians

Keywords

  • Data reduction techniques
  • Error detection
  • Laboratory error
  • Serial data analysis

ASJC Scopus subject areas

  • Clinical Biochemistry

Cite this

Reduction of multi-dimensional laboratory data to a two-dimensional plot : A novel technique for the identification of laboratory error. / Kazmierczak, Steven (Steve); Leen, Todd K.; Erdogmus, Deniz; Carreira-Perpinan, Miguel A.

In: Clinical Chemistry and Laboratory Medicine, Vol. 45, No. 6, 01.06.2007, p. 749-752.

Research output: Contribution to journalArticle

@article{4b92ce3185264ba7b3fb0cb1977af26a,
title = "Reduction of multi-dimensional laboratory data to a two-dimensional plot: A novel technique for the identification of laboratory error",
abstract = "Background: The clinical laboratory generates large amounts of patient-specific data. Detection of errors that arise during pre-analytical, analytical, and post-analytical processes is difficult. We performed a pilot study, utilizing a multidimensional data reduction technique, to assess the utility of this method for identifying errors in laboratory data. Methods: We evaluated 13,670 individual patient records collected over a 2-month period from hospital inpatients and outpatients. We utilized those patient records that contained a complete set of 14 different biochemical analytes. We used two-dimensional generative topographic mapping to project the 14-dimensional record to a two-dimensional space. Results and conclusions: The use of a two-dimensional generative topographic mapping technique to plot multi-analyte patient data as a two-dimensional graph allows for the rapid identification of potentially anomalous data. Although we performed a retrospective analysis, this technique has the benefit of being able to assess laboratory-generated data in real time, allowing for the rapid identification and correction of anomalous data before they are released to the physician. In addition, serial laboratory multi-analyte data for an individual patient can also be plotted as a two-dimensional plot. This tool might also be useful for assessing patient wellbeing and prognosis.",
keywords = "Data reduction techniques, Error detection, Laboratory error, Serial data analysis",
author = "Kazmierczak, {Steven (Steve)} and Leen, {Todd K.} and Deniz Erdogmus and Carreira-Perpinan, {Miguel A.}",
year = "2007",
month = "6",
day = "1",
doi = "10.1515/CCLM.2007.177",
language = "English (US)",
volume = "45",
pages = "749--752",
journal = "Clinical Chemistry and Laboratory Medicine",
issn = "1434-6621",
publisher = "Walter de Gruyter GmbH & Co. KG",
number = "6",

}

TY - JOUR

T1 - Reduction of multi-dimensional laboratory data to a two-dimensional plot

T2 - A novel technique for the identification of laboratory error

AU - Kazmierczak, Steven (Steve)

AU - Leen, Todd K.

AU - Erdogmus, Deniz

AU - Carreira-Perpinan, Miguel A.

PY - 2007/6/1

Y1 - 2007/6/1

N2 - Background: The clinical laboratory generates large amounts of patient-specific data. Detection of errors that arise during pre-analytical, analytical, and post-analytical processes is difficult. We performed a pilot study, utilizing a multidimensional data reduction technique, to assess the utility of this method for identifying errors in laboratory data. Methods: We evaluated 13,670 individual patient records collected over a 2-month period from hospital inpatients and outpatients. We utilized those patient records that contained a complete set of 14 different biochemical analytes. We used two-dimensional generative topographic mapping to project the 14-dimensional record to a two-dimensional space. Results and conclusions: The use of a two-dimensional generative topographic mapping technique to plot multi-analyte patient data as a two-dimensional graph allows for the rapid identification of potentially anomalous data. Although we performed a retrospective analysis, this technique has the benefit of being able to assess laboratory-generated data in real time, allowing for the rapid identification and correction of anomalous data before they are released to the physician. In addition, serial laboratory multi-analyte data for an individual patient can also be plotted as a two-dimensional plot. This tool might also be useful for assessing patient wellbeing and prognosis.

AB - Background: The clinical laboratory generates large amounts of patient-specific data. Detection of errors that arise during pre-analytical, analytical, and post-analytical processes is difficult. We performed a pilot study, utilizing a multidimensional data reduction technique, to assess the utility of this method for identifying errors in laboratory data. Methods: We evaluated 13,670 individual patient records collected over a 2-month period from hospital inpatients and outpatients. We utilized those patient records that contained a complete set of 14 different biochemical analytes. We used two-dimensional generative topographic mapping to project the 14-dimensional record to a two-dimensional space. Results and conclusions: The use of a two-dimensional generative topographic mapping technique to plot multi-analyte patient data as a two-dimensional graph allows for the rapid identification of potentially anomalous data. Although we performed a retrospective analysis, this technique has the benefit of being able to assess laboratory-generated data in real time, allowing for the rapid identification and correction of anomalous data before they are released to the physician. In addition, serial laboratory multi-analyte data for an individual patient can also be plotted as a two-dimensional plot. This tool might also be useful for assessing patient wellbeing and prognosis.

KW - Data reduction techniques

KW - Error detection

KW - Laboratory error

KW - Serial data analysis

UR - http://www.scopus.com/inward/record.url?scp=34250696557&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250696557&partnerID=8YFLogxK

U2 - 10.1515/CCLM.2007.177

DO - 10.1515/CCLM.2007.177

M3 - Article

C2 - 17579527

AN - SCOPUS:34250696557

VL - 45

SP - 749

EP - 752

JO - Clinical Chemistry and Laboratory Medicine

JF - Clinical Chemistry and Laboratory Medicine

SN - 1434-6621

IS - 6

ER -