Determining cut-points for Alzheimer's disease biomarkers

statistical issues, methods and challenges

Jonathan W Bartlett, Chris Frost, Niklas Mattsson, Tobias Skillbäck, Kaj Blennow, Henrik Zetterberg, Jonathan M Schott

Research output: Contribution to journalReview article

26 Citations (Scopus)

Abstract

New proposed criteria for the clinical diagnosis of Alzheimer's disease increasingly incorporate biomarkers, most of which are normally measured on a continuous scale. Operationalizing such criteria thus requires continuous biomarkers to be dichotomized, which in turns requires the selection of a cut-point at which to dichotomize. In this article, we review the statistical principles underlying the choice of cut-points, describe some of the most commonly adopted statistical approaches used to estimate cut-points, highlight potential pitfalls in some of the approaches and characterize in what sense the estimated cut-point from each approach is optimal. We also emphasize that how a cut-point is selected must be made in reference to how the resulting dichotomized biomarker is to be used, and in particular what actions will follow from a positive or negative test result.

Original languageEnglish
Pages (from-to)391-400
Number of pages10
JournalBiomarkers in Medicine
Volume6
Issue number4
Early online date23 Aug 2012
DOIs
Publication statusPublished - Aug 2012

Keywords

  • Alzheimer Disease/diagnosis
  • Amyloid beta-Peptides/cerebrospinal fluid
  • Biomarkers/cerebrospinal fluid
  • Humans
  • Likelihood Functions
  • Magnetic Resonance Imaging
  • Peptide Fragments/cerebrospinal fluid
  • Positron-Emission Tomography
  • ROC Curve
  • Uncertainty

Cite this

Bartlett, J. W., Frost, C., Mattsson, N., Skillbäck, T., Blennow, K., Zetterberg, H., & Schott, J. M. (2012). Determining cut-points for Alzheimer's disease biomarkers: statistical issues, methods and challenges. Biomarkers in Medicine, 6(4), 391-400. https://doi.org/10.2217/bmm.12.49

Determining cut-points for Alzheimer's disease biomarkers : statistical issues, methods and challenges. / Bartlett, Jonathan W; Frost, Chris; Mattsson, Niklas; Skillbäck, Tobias; Blennow, Kaj; Zetterberg, Henrik; Schott, Jonathan M.

In: Biomarkers in Medicine, Vol. 6, No. 4, 08.2012, p. 391-400.

Research output: Contribution to journalReview article

Bartlett, JW, Frost, C, Mattsson, N, Skillbäck, T, Blennow, K, Zetterberg, H & Schott, JM 2012, 'Determining cut-points for Alzheimer's disease biomarkers: statistical issues, methods and challenges', Biomarkers in Medicine, vol. 6, no. 4, pp. 391-400. https://doi.org/10.2217/bmm.12.49
Bartlett, Jonathan W ; Frost, Chris ; Mattsson, Niklas ; Skillbäck, Tobias ; Blennow, Kaj ; Zetterberg, Henrik ; Schott, Jonathan M. / Determining cut-points for Alzheimer's disease biomarkers : statistical issues, methods and challenges. In: Biomarkers in Medicine. 2012 ; Vol. 6, No. 4. pp. 391-400.
@article{7bee6ca5657e4422a871ebd4dabda6b4,
title = "Determining cut-points for Alzheimer's disease biomarkers: statistical issues, methods and challenges",
abstract = "New proposed criteria for the clinical diagnosis of Alzheimer's disease increasingly incorporate biomarkers, most of which are normally measured on a continuous scale. Operationalizing such criteria thus requires continuous biomarkers to be dichotomized, which in turns requires the selection of a cut-point at which to dichotomize. In this article, we review the statistical principles underlying the choice of cut-points, describe some of the most commonly adopted statistical approaches used to estimate cut-points, highlight potential pitfalls in some of the approaches and characterize in what sense the estimated cut-point from each approach is optimal. We also emphasize that how a cut-point is selected must be made in reference to how the resulting dichotomized biomarker is to be used, and in particular what actions will follow from a positive or negative test result.",
keywords = "Alzheimer Disease/diagnosis, Amyloid beta-Peptides/cerebrospinal fluid, Biomarkers/cerebrospinal fluid, Humans, Likelihood Functions, Magnetic Resonance Imaging, Peptide Fragments/cerebrospinal fluid, Positron-Emission Tomography, ROC Curve, Uncertainty",
author = "Bartlett, {Jonathan W} and Chris Frost and Niklas Mattsson and Tobias Skillb{\"a}ck and Kaj Blennow and Henrik Zetterberg and Schott, {Jonathan M}",
year = "2012",
month = "8",
doi = "10.2217/bmm.12.49",
language = "English",
volume = "6",
pages = "391--400",
journal = "Biomarkers in Medicine",
issn = "1752-0363",
publisher = "Future Medicine",
number = "4",

}

TY - JOUR

T1 - Determining cut-points for Alzheimer's disease biomarkers

T2 - statistical issues, methods and challenges

AU - Bartlett, Jonathan W

AU - Frost, Chris

AU - Mattsson, Niklas

AU - Skillbäck, Tobias

AU - Blennow, Kaj

AU - Zetterberg, Henrik

AU - Schott, Jonathan M

PY - 2012/8

Y1 - 2012/8

N2 - New proposed criteria for the clinical diagnosis of Alzheimer's disease increasingly incorporate biomarkers, most of which are normally measured on a continuous scale. Operationalizing such criteria thus requires continuous biomarkers to be dichotomized, which in turns requires the selection of a cut-point at which to dichotomize. In this article, we review the statistical principles underlying the choice of cut-points, describe some of the most commonly adopted statistical approaches used to estimate cut-points, highlight potential pitfalls in some of the approaches and characterize in what sense the estimated cut-point from each approach is optimal. We also emphasize that how a cut-point is selected must be made in reference to how the resulting dichotomized biomarker is to be used, and in particular what actions will follow from a positive or negative test result.

AB - New proposed criteria for the clinical diagnosis of Alzheimer's disease increasingly incorporate biomarkers, most of which are normally measured on a continuous scale. Operationalizing such criteria thus requires continuous biomarkers to be dichotomized, which in turns requires the selection of a cut-point at which to dichotomize. In this article, we review the statistical principles underlying the choice of cut-points, describe some of the most commonly adopted statistical approaches used to estimate cut-points, highlight potential pitfalls in some of the approaches and characterize in what sense the estimated cut-point from each approach is optimal. We also emphasize that how a cut-point is selected must be made in reference to how the resulting dichotomized biomarker is to be used, and in particular what actions will follow from a positive or negative test result.

KW - Alzheimer Disease/diagnosis

KW - Amyloid beta-Peptides/cerebrospinal fluid

KW - Biomarkers/cerebrospinal fluid

KW - Humans

KW - Likelihood Functions

KW - Magnetic Resonance Imaging

KW - Peptide Fragments/cerebrospinal fluid

KW - Positron-Emission Tomography

KW - ROC Curve

KW - Uncertainty

U2 - 10.2217/bmm.12.49

DO - 10.2217/bmm.12.49

M3 - Review article

VL - 6

SP - 391

EP - 400

JO - Biomarkers in Medicine

JF - Biomarkers in Medicine

SN - 1752-0363

IS - 4

ER -