A hybrid computational approach for efficient Alzheimer’s disease classification based on heterogeneous data

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

There is currently a lack of an efficient, objective and systemic approach towards the classification of Alzheimer’s disease (AD), due to its complex etiology and pathogenesis. As AD is inherently dynamic, it is also not clear how the relationships among AD indicators vary over time. To address these issues, we propose a hybrid computational approach for AD classification and evaluate it on the heterogeneous longitudinal AIBL dataset. Specifically, using clinical dementia rating as an index of AD severity, the most important indicators (mini-mental state examination, logical memory recall, grey matter and cerebrospinal volumes from MRI and active voxels from PiB-PET brain scans, ApoE, and age) can be automatically identified from parallel data mining algorithms. In this work Bayesian network modelling across different time points is used to identify and visualize time-varying relationships among the significant features, importantly in an efficient way using only coarse-grained data. Crucially, our approach suggests key data features and their appropriate combinations that are relevant for AD severity classification with high accuracy. Overall, our study provides insights into AD developments and demonstrates potential of our approach in supporting efficient AD diagnosis.
LanguageEnglish
Article number9774 (2018)
Pages1-10
Number of pages10
JournalScientific Reports
DOIs
Publication statusPublished - 27 Jun 2018

Fingerprint

Bayesian networks
Magnetic resonance imaging
Data mining
Brain
Data storage equipment

Keywords

  • Computational modelling
  • Data analytics
  • Alzheimer's disease
  • Data mining
  • Classification

Cite this

@article{16612adc6c114dceaf5da9bd34c6cc26,
title = "A hybrid computational approach for efficient Alzheimer’s disease classification based on heterogeneous data",
abstract = "There is currently a lack of an efficient, objective and systemic approach towards the classification of Alzheimer’s disease (AD), due to its complex etiology and pathogenesis. As AD is inherently dynamic, it is also not clear how the relationships among AD indicators vary over time. To address these issues, we propose a hybrid computational approach for AD classification and evaluate it on the heterogeneous longitudinal AIBL dataset. Specifically, using clinical dementia rating as an index of AD severity, the most important indicators (mini-mental state examination, logical memory recall, grey matter and cerebrospinal volumes from MRI and active voxels from PiB-PET brain scans, ApoE, and age) can be automatically identified from parallel data mining algorithms. In this work Bayesian network modelling across different time points is used to identify and visualize time-varying relationships among the significant features, importantly in an efficient way using only coarse-grained data. Crucially, our approach suggests key data features and their appropriate combinations that are relevant for AD severity classification with high accuracy. Overall, our study provides insights into AD developments and demonstrates potential of our approach in supporting efficient AD diagnosis.",
keywords = "Computational modelling, Data analytics, Alzheimer's disease, Data mining, Classification",
author = "Xuemei Ding and Magda Bucholc and Wang, {Haiying / HY} and Glass, {David H.} and H. Wang and Dave Clarke and AJ Bjourson and L Dowey and Maurice O'Kane and Girijesh Prasad and Liam Maguire and KongFatt Wong-Lin",
year = "2018",
month = "6",
day = "27",
doi = "10.1038/s41598-018-27997-8",
language = "English",
pages = "1--10",
journal = "Scientific Reports",
issn = "2045-2322",

}

TY - JOUR

T1 - A hybrid computational approach for efficient Alzheimer’s disease classification based on heterogeneous data

AU - Ding, Xuemei

AU - Bucholc, Magda

AU - Wang, Haiying / HY

AU - Glass, David H.

AU - Wang, H.

AU - Clarke, Dave

AU - Bjourson, AJ

AU - Dowey, L

AU - O'Kane, Maurice

AU - Prasad, Girijesh

AU - Maguire, Liam

AU - Wong-Lin, KongFatt

PY - 2018/6/27

Y1 - 2018/6/27

N2 - There is currently a lack of an efficient, objective and systemic approach towards the classification of Alzheimer’s disease (AD), due to its complex etiology and pathogenesis. As AD is inherently dynamic, it is also not clear how the relationships among AD indicators vary over time. To address these issues, we propose a hybrid computational approach for AD classification and evaluate it on the heterogeneous longitudinal AIBL dataset. Specifically, using clinical dementia rating as an index of AD severity, the most important indicators (mini-mental state examination, logical memory recall, grey matter and cerebrospinal volumes from MRI and active voxels from PiB-PET brain scans, ApoE, and age) can be automatically identified from parallel data mining algorithms. In this work Bayesian network modelling across different time points is used to identify and visualize time-varying relationships among the significant features, importantly in an efficient way using only coarse-grained data. Crucially, our approach suggests key data features and their appropriate combinations that are relevant for AD severity classification with high accuracy. Overall, our study provides insights into AD developments and demonstrates potential of our approach in supporting efficient AD diagnosis.

AB - There is currently a lack of an efficient, objective and systemic approach towards the classification of Alzheimer’s disease (AD), due to its complex etiology and pathogenesis. As AD is inherently dynamic, it is also not clear how the relationships among AD indicators vary over time. To address these issues, we propose a hybrid computational approach for AD classification and evaluate it on the heterogeneous longitudinal AIBL dataset. Specifically, using clinical dementia rating as an index of AD severity, the most important indicators (mini-mental state examination, logical memory recall, grey matter and cerebrospinal volumes from MRI and active voxels from PiB-PET brain scans, ApoE, and age) can be automatically identified from parallel data mining algorithms. In this work Bayesian network modelling across different time points is used to identify and visualize time-varying relationships among the significant features, importantly in an efficient way using only coarse-grained data. Crucially, our approach suggests key data features and their appropriate combinations that are relevant for AD severity classification with high accuracy. Overall, our study provides insights into AD developments and demonstrates potential of our approach in supporting efficient AD diagnosis.

KW - Computational modelling

KW - Data analytics

KW - Alzheimer's disease

KW - Data mining

KW - Classification

U2 - 10.1038/s41598-018-27997-8

DO - 10.1038/s41598-018-27997-8

M3 - Article

SP - 1

EP - 10

JO - Scientific Reports

T2 - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 9774 (2018)

ER -