Decision tree supports the interpretation of CSF biomarkers in Alzheimer's disease

Rosha Babapour Mofrad, Niki S.M. Schoonenboom, Betty M. Tijms, Philip Scheltens, Pieter Jelle Visser, Wiesje M. van der Flier, Charlotte E. Teunissen

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Introduction: We developed and validated a clinically applicable decision tree for the use of cerebrospinal fluid biomarkers in the diagnosis of Alzheimer's disease (AD). Methods: Subjects with probable AD (n = 1004) and controls (n = 442) were included. A decision tree was modeled using Classification And Regression Tree analysis in a training cohort (AD n = 221; controls n = 221) and validated in an independent cohort (AD n = 783; controls n = 221). Diagnostic performance was compared to previously defined cutoffs (amyloid β 1-42 < 813 pg/ml; tau>375 pg/ml). Results: Two cerebrospinal fluid AD biomarker profiles were revealed: the “classical” AD biomarker profile (amyloid β 1-42: 647-803 pg/ml; tau >374 pg/ml) and an “atypical” AD biomarker profile with strongly decreased amyloid β 1-42 (<647 pg/ml) and normal tau concentrations (<374 pg/ml). Compared to previous cutoffs, the decision tree performed better on diagnostic accuracy (86% [84-88] vs 80% [78-83]). Discussion: Two cerebrospinal fluid AD biomarker profiles were identified and incorporated in a readily applicable decision tree, which improved diagnostic accuracy.

Original languageEnglish
Pages (from-to)1-9
Number of pages9
JournalAlzheimer's and Dementia: Diagnosis, Assessment and Disease Monitoring
Volume11
DOIs
Publication statusPublished - 1 Dec 2019

Cite this

@article{29a113508a2744219b57ac9742023042,
title = "Decision tree supports the interpretation of CSF biomarkers in Alzheimer's disease",
abstract = "Introduction: We developed and validated a clinically applicable decision tree for the use of cerebrospinal fluid biomarkers in the diagnosis of Alzheimer's disease (AD). Methods: Subjects with probable AD (n = 1004) and controls (n = 442) were included. A decision tree was modeled using Classification And Regression Tree analysis in a training cohort (AD n = 221; controls n = 221) and validated in an independent cohort (AD n = 783; controls n = 221). Diagnostic performance was compared to previously defined cutoffs (amyloid β 1-42 < 813 pg/ml; tau>375 pg/ml). Results: Two cerebrospinal fluid AD biomarker profiles were revealed: the “classical” AD biomarker profile (amyloid β 1-42: 647-803 pg/ml; tau >374 pg/ml) and an “atypical” AD biomarker profile with strongly decreased amyloid β 1-42 (<647 pg/ml) and normal tau concentrations (<374 pg/ml). Compared to previous cutoffs, the decision tree performed better on diagnostic accuracy (86{\%} [84-88] vs 80{\%} [78-83]). Discussion: Two cerebrospinal fluid AD biomarker profiles were identified and incorporated in a readily applicable decision tree, which improved diagnostic accuracy.",
keywords = "Alzheimer's disease, Amyloid β 1-42, CART, Cerebrospinal fluid, Clinical implementation, CSF, Cutoff, Decision tree, Tau",
author = "{Babapour Mofrad}, Rosha and Schoonenboom, {Niki S.M.} and Tijms, {Betty M.} and Philip Scheltens and Visser, {Pieter Jelle} and {van der Flier}, {Wiesje M.} and Teunissen, {Charlotte E.}",
year = "2019",
month = "12",
day = "1",
doi = "10.1016/j.dadm.2018.10.004",
language = "English",
volume = "11",
pages = "1--9",
journal = "Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring",
issn = "2352-8729",
publisher = "Elsevier BV",

}

Decision tree supports the interpretation of CSF biomarkers in Alzheimer's disease. / Babapour Mofrad, Rosha; Schoonenboom, Niki S.M.; Tijms, Betty M.; Scheltens, Philip; Visser, Pieter Jelle; van der Flier, Wiesje M.; Teunissen, Charlotte E.

In: Alzheimer's and Dementia: Diagnosis, Assessment and Disease Monitoring, Vol. 11, 01.12.2019, p. 1-9.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Decision tree supports the interpretation of CSF biomarkers in Alzheimer's disease

AU - Babapour Mofrad, Rosha

AU - Schoonenboom, Niki S.M.

AU - Tijms, Betty M.

AU - Scheltens, Philip

AU - Visser, Pieter Jelle

AU - van der Flier, Wiesje M.

AU - Teunissen, Charlotte E.

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Introduction: We developed and validated a clinically applicable decision tree for the use of cerebrospinal fluid biomarkers in the diagnosis of Alzheimer's disease (AD). Methods: Subjects with probable AD (n = 1004) and controls (n = 442) were included. A decision tree was modeled using Classification And Regression Tree analysis in a training cohort (AD n = 221; controls n = 221) and validated in an independent cohort (AD n = 783; controls n = 221). Diagnostic performance was compared to previously defined cutoffs (amyloid β 1-42 < 813 pg/ml; tau>375 pg/ml). Results: Two cerebrospinal fluid AD biomarker profiles were revealed: the “classical” AD biomarker profile (amyloid β 1-42: 647-803 pg/ml; tau >374 pg/ml) and an “atypical” AD biomarker profile with strongly decreased amyloid β 1-42 (<647 pg/ml) and normal tau concentrations (<374 pg/ml). Compared to previous cutoffs, the decision tree performed better on diagnostic accuracy (86% [84-88] vs 80% [78-83]). Discussion: Two cerebrospinal fluid AD biomarker profiles were identified and incorporated in a readily applicable decision tree, which improved diagnostic accuracy.

AB - Introduction: We developed and validated a clinically applicable decision tree for the use of cerebrospinal fluid biomarkers in the diagnosis of Alzheimer's disease (AD). Methods: Subjects with probable AD (n = 1004) and controls (n = 442) were included. A decision tree was modeled using Classification And Regression Tree analysis in a training cohort (AD n = 221; controls n = 221) and validated in an independent cohort (AD n = 783; controls n = 221). Diagnostic performance was compared to previously defined cutoffs (amyloid β 1-42 < 813 pg/ml; tau>375 pg/ml). Results: Two cerebrospinal fluid AD biomarker profiles were revealed: the “classical” AD biomarker profile (amyloid β 1-42: 647-803 pg/ml; tau >374 pg/ml) and an “atypical” AD biomarker profile with strongly decreased amyloid β 1-42 (<647 pg/ml) and normal tau concentrations (<374 pg/ml). Compared to previous cutoffs, the decision tree performed better on diagnostic accuracy (86% [84-88] vs 80% [78-83]). Discussion: Two cerebrospinal fluid AD biomarker profiles were identified and incorporated in a readily applicable decision tree, which improved diagnostic accuracy.

KW - Alzheimer's disease

KW - Amyloid β 1-42

KW - CART

KW - Cerebrospinal fluid

KW - Clinical implementation

KW - CSF

KW - Cutoff

KW - Decision tree

KW - Tau

UR - http://www.scopus.com/inward/record.url?scp=85057800488&partnerID=8YFLogxK

U2 - 10.1016/j.dadm.2018.10.004

DO - 10.1016/j.dadm.2018.10.004

M3 - Article

VL - 11

SP - 1

EP - 9

JO - Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring

JF - Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring

SN - 2352-8729

ER -