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 - CSF
KW - Cerebrospinal fluid
KW - Clinical implementation
KW - Cutoff
KW - Decision tree
KW - Tau
UR - http://www.scopus.com/inward/record.url?scp=85057800488&partnerID=8YFLogxK
U2 - https://doi.org/10.1016/j.dadm.2018.10.004
DO - https://doi.org/10.1016/j.dadm.2018.10.004
M3 - Article
C2 - 30569013
SN - 2352-8729
VL - 11
SP - 1
EP - 9
JO - Alzheimer's and Dementia: Diagnosis, Assessment and Disease Monitoring
JF - Alzheimer's and Dementia: Diagnosis, Assessment and Disease Monitoring
ER -