Integrating biomarkers for underlying Alzheimer's disease in mild cognitive impairment in daily practice

Comparison of a clinical decision support system with individual biomarkers

Hanneke F.M. Rhodius-Meester (Corresponding Author), Juha Koikkalainen, Jussi Mattila, Charlotte E. Teunissen, Frederik Barkhof, Afina W. Lemstra, Philip Scheltens, Jyrki Lötjönen, Wiesje M. van der Flier

Research output: Contribution to journalArticleScientificpeer-review

9 Citations (Scopus)

Abstract

Background:Recent criteria allow biomarkers to provide evidence of Alzheimer's disease (AD) pathophysiology. How they should be implemented in daily practice remains unclear, especially in mild cognitive impairment (MCI) patients. Objective:We evaluated how a clinical decision support system such as the PredictAD tool can aid clinicians to integrate biomarker evidence to support AD diagnosis. Methods:With available data on demographics, cerebrospinal fluid (CSF), and MRI, we trained the PredictAD tool on a reference population of 246 controls and 491 AD patients. We then applied the identified algorithm to 211 MCI patients. For comparison, we also classified patients based on individual biomarkers (MRI; CSF) and the NIA-AA criteria. Progression to dementia was used as outcome measure. Results:After a median follow up of 3 years, 72 (34% ) MCI patients remained stable and 139 (66%) progressed to AD. The PredictAD tool assigned a likelihood of underlying AD to each patient (AUC 0.82). Excluding patients with missing data resulted in an AUC of 0.87. According to the NIA-AA criteria, half of the MCI patients had uninformative biomarkers, precluding an assignment of AD likelihood. A minority (41%) was assigned to high or low AD likelihood with good predictive value. The individual biomarkers showed best value for CSF total tau (AUC 0.86). Conclusion:The ability of the PredictAD tool to identify AD pathophysiology was comparable to individual biomarkers. The PredictAD tool has the advantage that it assigns likelihood to all patients, regardless of missing or conflicting data, allowing clinicians to integrate biomarker data in daily practice.
Original languageEnglish
Pages (from-to)261-270
JournalJournal of Alzheimer's Disease
Volume50
Issue number1
DOIs
Publication statusPublished - 2015
MoE publication typeA1 Journal article-refereed

Fingerprint

Clinical Decision Support Systems
Alzheimer Disease
Biomarkers
Area Under Curve
Cerebrospinal Fluid
Cognitive Dysfunction
Aptitude
Population Control
Dementia
Demography
Outcome Assessment (Health Care)

Keywords

  • Alzheimer's disease
  • clinical decision support system
  • diagnostic test assessment
  • mild cognitive impairment
  • prognosis

Cite this

Rhodius-Meester, Hanneke F.M. ; Koikkalainen, Juha ; Mattila, Jussi ; Teunissen, Charlotte E. ; Barkhof, Frederik ; Lemstra, Afina W. ; Scheltens, Philip ; Lötjönen, Jyrki ; van der Flier, Wiesje M. / Integrating biomarkers for underlying Alzheimer's disease in mild cognitive impairment in daily practice : Comparison of a clinical decision support system with individual biomarkers. In: Journal of Alzheimer's Disease. 2015 ; Vol. 50, No. 1. pp. 261-270.
@article{8580bb3ec5e044f18e18da846b7159dc,
title = "Integrating biomarkers for underlying Alzheimer's disease in mild cognitive impairment in daily practice: Comparison of a clinical decision support system with individual biomarkers",
abstract = "Background:Recent criteria allow biomarkers to provide evidence of Alzheimer's disease (AD) pathophysiology. How they should be implemented in daily practice remains unclear, especially in mild cognitive impairment (MCI) patients. Objective:We evaluated how a clinical decision support system such as the PredictAD tool can aid clinicians to integrate biomarker evidence to support AD diagnosis. Methods:With available data on demographics, cerebrospinal fluid (CSF), and MRI, we trained the PredictAD tool on a reference population of 246 controls and 491 AD patients. We then applied the identified algorithm to 211 MCI patients. For comparison, we also classified patients based on individual biomarkers (MRI; CSF) and the NIA-AA criteria. Progression to dementia was used as outcome measure. Results:After a median follow up of 3 years, 72 (34{\%} ) MCI patients remained stable and 139 (66{\%}) progressed to AD. The PredictAD tool assigned a likelihood of underlying AD to each patient (AUC 0.82). Excluding patients with missing data resulted in an AUC of 0.87. According to the NIA-AA criteria, half of the MCI patients had uninformative biomarkers, precluding an assignment of AD likelihood. A minority (41{\%}) was assigned to high or low AD likelihood with good predictive value. The individual biomarkers showed best value for CSF total tau (AUC 0.86). Conclusion:The ability of the PredictAD tool to identify AD pathophysiology was comparable to individual biomarkers. The PredictAD tool has the advantage that it assigns likelihood to all patients, regardless of missing or conflicting data, allowing clinicians to integrate biomarker data in daily practice.",
keywords = "Alzheimer's disease, clinical decision support system, diagnostic test assessment, mild cognitive impairment, prognosis",
author = "Rhodius-Meester, {Hanneke F.M.} and Juha Koikkalainen and Jussi Mattila and Teunissen, {Charlotte E.} and Frederik Barkhof and Lemstra, {Afina W.} and Philip Scheltens and Jyrki L{\"o}tj{\"o}nen and {van der Flier}, {Wiesje M.}",
year = "2015",
doi = "10.3233/JAD-150548",
language = "English",
volume = "50",
pages = "261--270",
journal = "Journal of Alzheimer's Disease",
issn = "1387-2877",
publisher = "IOS Press",
number = "1",

}

Rhodius-Meester, HFM, Koikkalainen, J, Mattila, J, Teunissen, CE, Barkhof, F, Lemstra, AW, Scheltens, P, Lötjönen, J & van der Flier, WM 2015, 'Integrating biomarkers for underlying Alzheimer's disease in mild cognitive impairment in daily practice: Comparison of a clinical decision support system with individual biomarkers', Journal of Alzheimer's Disease, vol. 50, no. 1, pp. 261-270. https://doi.org/10.3233/JAD-150548

Integrating biomarkers for underlying Alzheimer's disease in mild cognitive impairment in daily practice : Comparison of a clinical decision support system with individual biomarkers. / Rhodius-Meester, Hanneke F.M. (Corresponding Author); Koikkalainen, Juha; Mattila, Jussi; Teunissen, Charlotte E.; Barkhof, Frederik; Lemstra, Afina W.; Scheltens, Philip; Lötjönen, Jyrki; van der Flier, Wiesje M.

In: Journal of Alzheimer's Disease, Vol. 50, No. 1, 2015, p. 261-270.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Integrating biomarkers for underlying Alzheimer's disease in mild cognitive impairment in daily practice

T2 - Comparison of a clinical decision support system with individual biomarkers

AU - Rhodius-Meester, Hanneke F.M.

AU - Koikkalainen, Juha

AU - Mattila, Jussi

AU - Teunissen, Charlotte E.

AU - Barkhof, Frederik

AU - Lemstra, Afina W.

AU - Scheltens, Philip

AU - Lötjönen, Jyrki

AU - van der Flier, Wiesje M.

PY - 2015

Y1 - 2015

N2 - Background:Recent criteria allow biomarkers to provide evidence of Alzheimer's disease (AD) pathophysiology. How they should be implemented in daily practice remains unclear, especially in mild cognitive impairment (MCI) patients. Objective:We evaluated how a clinical decision support system such as the PredictAD tool can aid clinicians to integrate biomarker evidence to support AD diagnosis. Methods:With available data on demographics, cerebrospinal fluid (CSF), and MRI, we trained the PredictAD tool on a reference population of 246 controls and 491 AD patients. We then applied the identified algorithm to 211 MCI patients. For comparison, we also classified patients based on individual biomarkers (MRI; CSF) and the NIA-AA criteria. Progression to dementia was used as outcome measure. Results:After a median follow up of 3 years, 72 (34% ) MCI patients remained stable and 139 (66%) progressed to AD. The PredictAD tool assigned a likelihood of underlying AD to each patient (AUC 0.82). Excluding patients with missing data resulted in an AUC of 0.87. According to the NIA-AA criteria, half of the MCI patients had uninformative biomarkers, precluding an assignment of AD likelihood. A minority (41%) was assigned to high or low AD likelihood with good predictive value. The individual biomarkers showed best value for CSF total tau (AUC 0.86). Conclusion:The ability of the PredictAD tool to identify AD pathophysiology was comparable to individual biomarkers. The PredictAD tool has the advantage that it assigns likelihood to all patients, regardless of missing or conflicting data, allowing clinicians to integrate biomarker data in daily practice.

AB - Background:Recent criteria allow biomarkers to provide evidence of Alzheimer's disease (AD) pathophysiology. How they should be implemented in daily practice remains unclear, especially in mild cognitive impairment (MCI) patients. Objective:We evaluated how a clinical decision support system such as the PredictAD tool can aid clinicians to integrate biomarker evidence to support AD diagnosis. Methods:With available data on demographics, cerebrospinal fluid (CSF), and MRI, we trained the PredictAD tool on a reference population of 246 controls and 491 AD patients. We then applied the identified algorithm to 211 MCI patients. For comparison, we also classified patients based on individual biomarkers (MRI; CSF) and the NIA-AA criteria. Progression to dementia was used as outcome measure. Results:After a median follow up of 3 years, 72 (34% ) MCI patients remained stable and 139 (66%) progressed to AD. The PredictAD tool assigned a likelihood of underlying AD to each patient (AUC 0.82). Excluding patients with missing data resulted in an AUC of 0.87. According to the NIA-AA criteria, half of the MCI patients had uninformative biomarkers, precluding an assignment of AD likelihood. A minority (41%) was assigned to high or low AD likelihood with good predictive value. The individual biomarkers showed best value for CSF total tau (AUC 0.86). Conclusion:The ability of the PredictAD tool to identify AD pathophysiology was comparable to individual biomarkers. The PredictAD tool has the advantage that it assigns likelihood to all patients, regardless of missing or conflicting data, allowing clinicians to integrate biomarker data in daily practice.

KW - Alzheimer's disease

KW - clinical decision support system

KW - diagnostic test assessment

KW - mild cognitive impairment

KW - prognosis

U2 - 10.3233/JAD-150548

DO - 10.3233/JAD-150548

M3 - Article

VL - 50

SP - 261

EP - 270

JO - Journal of Alzheimer's Disease

JF - Journal of Alzheimer's Disease

SN - 1387-2877

IS - 1

ER -