Automated screening for myelodysplastic syndromes through analysis of complete blood count and cell population data parameters

Phil Raess, Gert Jan M. van de Geijn, Tjin L. Njo, Boudewijn Klop, Dmitry Sukhachev, Gerald Wertheim, Tom Mcaleer, Stephen R. Master, Adam Bagg

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The diagnosis of myelodysplastic syndromes (MDS) requires a high clinical index of suspicion to prompt bone marrow studies as well as subjective assessment of dysplastic morphology. We sought to determine if data collected by automated hematology analyzers during complete blood count (CBC) analysis might help to identify MDS in a routine clinical setting. We collected CBC parameters (including those for research use only and cell population data) and demographic information in a large (>5,000), unselected sequential cohort of outpatients. The cohort was divided into independent training and test groups to develop and validate a random forest classifier that identifies MDS. The classifier effectively identified MDS and had a receiver operating characteristic area under the curve (AUC) of 0.942. Platelet distribution width and the standard deviation of red blood cell distribution width were the most discriminating variables within the classifier. Additionally, a similar classifier was validated with an additional, independent set of >200 patients from a second institution with an AUC of 0.93. This retrospective study demonstrates the feasibility of identifying MDS in an unselected outpatient population using data routinely collected during CBC analysis with a classifier that has been validated using two independent data sets from different institutions.

Original languageEnglish (US)
Pages (from-to)369-374
Number of pages6
JournalAmerican Journal of Hematology
Volume89
Issue number4
DOIs
StatePublished - Jan 1 2014
Externally publishedYes

Fingerprint

Blood Cell Count
Myelodysplastic Syndromes
Blood Cells
Population
Area Under Curve
Outpatients
Erythrocyte Indices
Hematology
ROC Curve
Blood Platelets
Retrospective Studies
Erythrocytes
Bone Marrow
Demography
Research

ASJC Scopus subject areas

  • Hematology

Cite this

Automated screening for myelodysplastic syndromes through analysis of complete blood count and cell population data parameters. / Raess, Phil; van de Geijn, Gert Jan M.; Njo, Tjin L.; Klop, Boudewijn; Sukhachev, Dmitry; Wertheim, Gerald; Mcaleer, Tom; Master, Stephen R.; Bagg, Adam.

In: American Journal of Hematology, Vol. 89, No. 4, 01.01.2014, p. 369-374.

Research output: Contribution to journalArticle

Raess, P, van de Geijn, GJM, Njo, TL, Klop, B, Sukhachev, D, Wertheim, G, Mcaleer, T, Master, SR & Bagg, A 2014, 'Automated screening for myelodysplastic syndromes through analysis of complete blood count and cell population data parameters', American Journal of Hematology, vol. 89, no. 4, pp. 369-374. https://doi.org/10.1002/ajh.23643
Raess, Phil ; van de Geijn, Gert Jan M. ; Njo, Tjin L. ; Klop, Boudewijn ; Sukhachev, Dmitry ; Wertheim, Gerald ; Mcaleer, Tom ; Master, Stephen R. ; Bagg, Adam. / Automated screening for myelodysplastic syndromes through analysis of complete blood count and cell population data parameters. In: American Journal of Hematology. 2014 ; Vol. 89, No. 4. pp. 369-374.
@article{27527e03481b44e7a21e5a85f164e1fe,
title = "Automated screening for myelodysplastic syndromes through analysis of complete blood count and cell population data parameters",
abstract = "The diagnosis of myelodysplastic syndromes (MDS) requires a high clinical index of suspicion to prompt bone marrow studies as well as subjective assessment of dysplastic morphology. We sought to determine if data collected by automated hematology analyzers during complete blood count (CBC) analysis might help to identify MDS in a routine clinical setting. We collected CBC parameters (including those for research use only and cell population data) and demographic information in a large (>5,000), unselected sequential cohort of outpatients. The cohort was divided into independent training and test groups to develop and validate a random forest classifier that identifies MDS. The classifier effectively identified MDS and had a receiver operating characteristic area under the curve (AUC) of 0.942. Platelet distribution width and the standard deviation of red blood cell distribution width were the most discriminating variables within the classifier. Additionally, a similar classifier was validated with an additional, independent set of >200 patients from a second institution with an AUC of 0.93. This retrospective study demonstrates the feasibility of identifying MDS in an unselected outpatient population using data routinely collected during CBC analysis with a classifier that has been validated using two independent data sets from different institutions.",
author = "Phil Raess and {van de Geijn}, {Gert Jan M.} and Njo, {Tjin L.} and Boudewijn Klop and Dmitry Sukhachev and Gerald Wertheim and Tom Mcaleer and Master, {Stephen R.} and Adam Bagg",
year = "2014",
month = "1",
day = "1",
doi = "10.1002/ajh.23643",
language = "English (US)",
volume = "89",
pages = "369--374",
journal = "American Journal of Hematology",
issn = "0361-8609",
publisher = "Wiley-Liss Inc.",
number = "4",

}

TY - JOUR

T1 - Automated screening for myelodysplastic syndromes through analysis of complete blood count and cell population data parameters

AU - Raess, Phil

AU - van de Geijn, Gert Jan M.

AU - Njo, Tjin L.

AU - Klop, Boudewijn

AU - Sukhachev, Dmitry

AU - Wertheim, Gerald

AU - Mcaleer, Tom

AU - Master, Stephen R.

AU - Bagg, Adam

PY - 2014/1/1

Y1 - 2014/1/1

N2 - The diagnosis of myelodysplastic syndromes (MDS) requires a high clinical index of suspicion to prompt bone marrow studies as well as subjective assessment of dysplastic morphology. We sought to determine if data collected by automated hematology analyzers during complete blood count (CBC) analysis might help to identify MDS in a routine clinical setting. We collected CBC parameters (including those for research use only and cell population data) and demographic information in a large (>5,000), unselected sequential cohort of outpatients. The cohort was divided into independent training and test groups to develop and validate a random forest classifier that identifies MDS. The classifier effectively identified MDS and had a receiver operating characteristic area under the curve (AUC) of 0.942. Platelet distribution width and the standard deviation of red blood cell distribution width were the most discriminating variables within the classifier. Additionally, a similar classifier was validated with an additional, independent set of >200 patients from a second institution with an AUC of 0.93. This retrospective study demonstrates the feasibility of identifying MDS in an unselected outpatient population using data routinely collected during CBC analysis with a classifier that has been validated using two independent data sets from different institutions.

AB - The diagnosis of myelodysplastic syndromes (MDS) requires a high clinical index of suspicion to prompt bone marrow studies as well as subjective assessment of dysplastic morphology. We sought to determine if data collected by automated hematology analyzers during complete blood count (CBC) analysis might help to identify MDS in a routine clinical setting. We collected CBC parameters (including those for research use only and cell population data) and demographic information in a large (>5,000), unselected sequential cohort of outpatients. The cohort was divided into independent training and test groups to develop and validate a random forest classifier that identifies MDS. The classifier effectively identified MDS and had a receiver operating characteristic area under the curve (AUC) of 0.942. Platelet distribution width and the standard deviation of red blood cell distribution width were the most discriminating variables within the classifier. Additionally, a similar classifier was validated with an additional, independent set of >200 patients from a second institution with an AUC of 0.93. This retrospective study demonstrates the feasibility of identifying MDS in an unselected outpatient population using data routinely collected during CBC analysis with a classifier that has been validated using two independent data sets from different institutions.

UR - http://www.scopus.com/inward/record.url?scp=84897472101&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897472101&partnerID=8YFLogxK

U2 - 10.1002/ajh.23643

DO - 10.1002/ajh.23643

M3 - Article

VL - 89

SP - 369

EP - 374

JO - American Journal of Hematology

JF - American Journal of Hematology

SN - 0361-8609

IS - 4

ER -