Application of the PredictAD Decision Support Tool to a Danish Cohort of Patients with Alzheimer's Disease and Other Dementias

Anja Simonsen, Jussi Mattila, Anne-Mette Hejl, Ellen Garde, Mark van Gils, Carsten Thomsen, Jyrki Lötjönen, Hilkka Soininen, Gunhild Waldemar

Research output: Contribution to journalArticleScientificpeer-review

5 Citations (Scopus)

Abstract

The diagnosis of Alzheimer's disease (AD) is based on an ever-increasing body of data and knowledge making it a complex task. The PredictAD tool integrates heterogeneous patient data using an interactive user interface to provide decision support. The aim of this project was to investigate the performance of the tool in distinguishing AD from non-AD dementia using a realistic clinical dataset. Methods: We retrieved clinical data from a group of patients diagnosed with AD (n = 72), vascular dementia (VaD, n = 30), frontotemporal dementia (FTD, n = 25) or dementia with Lewy bodies (DLB, n = 14) at the Copenhagen Memory Clinic at Rigshospitalet. Three classification methods were applied to the data in order to differentiate between AD and a group of non-AD dementias. The methods were the PredictAD tool's Disease State Index (DSI), the naïve Bayesian classifier and the random forest. Results: The DSI performed best for this realistic dataset with an accuracy of 76.6% compared to the accuracies for the naïve Bayesian classifier and random forest of 67.4 and 66.7%, respectively. Furthermore, the DSI differentiated between the four diagnostic groups with a p value of
Original languageEnglish
Pages (from-to)207-213
JournalDementia and Geriatric Cognitive Disorders
Volume37
Issue number3-4
DOIs
Publication statusPublished - 2014
MoE publication typeA1 Journal article-refereed

Fingerprint

Dementia
Alzheimer Disease
Lewy Body Disease
Frontotemporal Dementia
Vascular Dementia
Datasets
Forests

Keywords

  • Alzheimer’s disease
  • Dementia
  • Software agents
  • Differential diagnosis
  • Decision support

Cite this

Simonsen, Anja ; Mattila, Jussi ; Hejl, Anne-Mette ; Garde, Ellen ; van Gils, Mark ; Thomsen, Carsten ; Lötjönen, Jyrki ; Soininen, Hilkka ; Waldemar, Gunhild. / Application of the PredictAD Decision Support Tool to a Danish Cohort of Patients with Alzheimer's Disease and Other Dementias. In: Dementia and Geriatric Cognitive Disorders. 2014 ; Vol. 37, No. 3-4. pp. 207-213.
@article{84f5bbf0c483411e87c4bf3ac3e070a5,
title = "Application of the PredictAD Decision Support Tool to a Danish Cohort of Patients with Alzheimer's Disease and Other Dementias",
abstract = "The diagnosis of Alzheimer's disease (AD) is based on an ever-increasing body of data and knowledge making it a complex task. The PredictAD tool integrates heterogeneous patient data using an interactive user interface to provide decision support. The aim of this project was to investigate the performance of the tool in distinguishing AD from non-AD dementia using a realistic clinical dataset. Methods: We retrieved clinical data from a group of patients diagnosed with AD (n = 72), vascular dementia (VaD, n = 30), frontotemporal dementia (FTD, n = 25) or dementia with Lewy bodies (DLB, n = 14) at the Copenhagen Memory Clinic at Rigshospitalet. Three classification methods were applied to the data in order to differentiate between AD and a group of non-AD dementias. The methods were the PredictAD tool's Disease State Index (DSI), the na{\"i}ve Bayesian classifier and the random forest. Results: The DSI performed best for this realistic dataset with an accuracy of 76.6{\%} compared to the accuracies for the na{\"i}ve Bayesian classifier and random forest of 67.4 and 66.7{\%}, respectively. Furthermore, the DSI differentiated between the four diagnostic groups with a p value of",
keywords = "Alzheimer’s disease, Dementia, Software agents, Differential diagnosis, Decision support",
author = "Anja Simonsen and Jussi Mattila and Anne-Mette Hejl and Ellen Garde and {van Gils}, Mark and Carsten Thomsen and Jyrki L{\"o}tj{\"o}nen and Hilkka Soininen and Gunhild Waldemar",
note = "Project code: 79748",
year = "2014",
doi = "10.1159/000354372",
language = "English",
volume = "37",
pages = "207--213",
journal = "Dementia and Geriatric Cognitive Disorders",
issn = "1420-8008",
publisher = "S. Karger AG",
number = "3-4",

}

Application of the PredictAD Decision Support Tool to a Danish Cohort of Patients with Alzheimer's Disease and Other Dementias. / Simonsen, Anja; Mattila, Jussi; Hejl, Anne-Mette; Garde, Ellen; van Gils, Mark; Thomsen, Carsten; Lötjönen, Jyrki; Soininen, Hilkka; Waldemar, Gunhild.

In: Dementia and Geriatric Cognitive Disorders, Vol. 37, No. 3-4, 2014, p. 207-213.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Application of the PredictAD Decision Support Tool to a Danish Cohort of Patients with Alzheimer's Disease and Other Dementias

AU - Simonsen, Anja

AU - Mattila, Jussi

AU - Hejl, Anne-Mette

AU - Garde, Ellen

AU - van Gils, Mark

AU - Thomsen, Carsten

AU - Lötjönen, Jyrki

AU - Soininen, Hilkka

AU - Waldemar, Gunhild

N1 - Project code: 79748

PY - 2014

Y1 - 2014

N2 - The diagnosis of Alzheimer's disease (AD) is based on an ever-increasing body of data and knowledge making it a complex task. The PredictAD tool integrates heterogeneous patient data using an interactive user interface to provide decision support. The aim of this project was to investigate the performance of the tool in distinguishing AD from non-AD dementia using a realistic clinical dataset. Methods: We retrieved clinical data from a group of patients diagnosed with AD (n = 72), vascular dementia (VaD, n = 30), frontotemporal dementia (FTD, n = 25) or dementia with Lewy bodies (DLB, n = 14) at the Copenhagen Memory Clinic at Rigshospitalet. Three classification methods were applied to the data in order to differentiate between AD and a group of non-AD dementias. The methods were the PredictAD tool's Disease State Index (DSI), the naïve Bayesian classifier and the random forest. Results: The DSI performed best for this realistic dataset with an accuracy of 76.6% compared to the accuracies for the naïve Bayesian classifier and random forest of 67.4 and 66.7%, respectively. Furthermore, the DSI differentiated between the four diagnostic groups with a p value of

AB - The diagnosis of Alzheimer's disease (AD) is based on an ever-increasing body of data and knowledge making it a complex task. The PredictAD tool integrates heterogeneous patient data using an interactive user interface to provide decision support. The aim of this project was to investigate the performance of the tool in distinguishing AD from non-AD dementia using a realistic clinical dataset. Methods: We retrieved clinical data from a group of patients diagnosed with AD (n = 72), vascular dementia (VaD, n = 30), frontotemporal dementia (FTD, n = 25) or dementia with Lewy bodies (DLB, n = 14) at the Copenhagen Memory Clinic at Rigshospitalet. Three classification methods were applied to the data in order to differentiate between AD and a group of non-AD dementias. The methods were the PredictAD tool's Disease State Index (DSI), the naïve Bayesian classifier and the random forest. Results: The DSI performed best for this realistic dataset with an accuracy of 76.6% compared to the accuracies for the naïve Bayesian classifier and random forest of 67.4 and 66.7%, respectively. Furthermore, the DSI differentiated between the four diagnostic groups with a p value of

KW - Alzheimer’s disease

KW - Dementia

KW - Software agents

KW - Differential diagnosis

KW - Decision support

U2 - 10.1159/000354372

DO - 10.1159/000354372

M3 - Article

VL - 37

SP - 207

EP - 213

JO - Dementia and Geriatric Cognitive Disorders

JF - Dementia and Geriatric Cognitive Disorders

SN - 1420-8008

IS - 3-4

ER -