An adaptive genetic algorithm for selection of blood-based biomarkers for prediction of Alzheimer's disease progression

Luke Vandewater, Vladimir Brusic, William Wilson, Lance Macaulay, Ping Zhang

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Background: Alzheimer's disease is a multifactorial disorder that may be diagnosed earlier using a combination of tests rather than any single test. Search algorithms and optimization techniques in combination with model evaluation techniques have been used previously to perform the selection of suitable feature sets. Previously we successfully applied GA with LR to neuropsychological data contained within the The Australian Imaging, Biomarkers and Lifestyle (AIBL) study of aging, to select cognitive tests for prediction of progression of AD. This research addresses an Adaptive Genetic Algorithm (AGA) in combination with LR for identifying the best biomarker combination for prediction of the progression to AD. Results: The model has been explored in terms of parameter optimization to predict conversion from healthy stage to AD with high accuracy. Several feature sets were selected - the resulting prediction moddels showed higher area under the ROC values (0.83-0.89). The results has shown consistency with some of the medical research reported in literature. Conclusion: The AGA has proven useful in selecting the best combination of biomarkers for prediction of AD progression. The algorithm presented here is generic and can be extended to other data sets generated in projects that seek to identify combination of biomarkers or other features that are predictive of disease onset or progression.

Original languageEnglish
Article numberS1
JournalBMC Bioinformatics
Volume16
Issue number18
DOIs
Publication statusPublished - Dec 9 2015

Fingerprint

Adaptive Genetic Algorithm
Alzheimer's Disease
Biomarkers
Adaptive algorithms
Progression
Blood
Disease Progression
Alzheimer Disease
Genetic algorithms
Prediction
Biomedical Research
Life Style
Model Evaluation
Aging of materials
Parameter Optimization
Imaging techniques
Optimization Techniques
Search Algorithm
Disorder
High Accuracy

Keywords

  • Adaptive genetic algorithm
  • Alzheimer's
  • Biomarkers
  • Logistic regression
  • Prediction

ASJC Scopus subject areas

  • Applied Mathematics
  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications

Cite this

An adaptive genetic algorithm for selection of blood-based biomarkers for prediction of Alzheimer's disease progression. / Vandewater, Luke; Brusic, Vladimir; Wilson, William; Macaulay, Lance; Zhang, Ping.

In: BMC Bioinformatics, Vol. 16, No. 18, S1, 09.12.2015.

Research output: Contribution to journalArticle

Vandewater, Luke ; Brusic, Vladimir ; Wilson, William ; Macaulay, Lance ; Zhang, Ping. / An adaptive genetic algorithm for selection of blood-based biomarkers for prediction of Alzheimer's disease progression. In: BMC Bioinformatics. 2015 ; Vol. 16, No. 18.
@article{9e3d468ac1384a29a03acc2c6390f95d,
title = "An adaptive genetic algorithm for selection of blood-based biomarkers for prediction of Alzheimer's disease progression",
abstract = "Background: Alzheimer's disease is a multifactorial disorder that may be diagnosed earlier using a combination of tests rather than any single test. Search algorithms and optimization techniques in combination with model evaluation techniques have been used previously to perform the selection of suitable feature sets. Previously we successfully applied GA with LR to neuropsychological data contained within the The Australian Imaging, Biomarkers and Lifestyle (AIBL) study of aging, to select cognitive tests for prediction of progression of AD. This research addresses an Adaptive Genetic Algorithm (AGA) in combination with LR for identifying the best biomarker combination for prediction of the progression to AD. Results: The model has been explored in terms of parameter optimization to predict conversion from healthy stage to AD with high accuracy. Several feature sets were selected - the resulting prediction moddels showed higher area under the ROC values (0.83-0.89). The results has shown consistency with some of the medical research reported in literature. Conclusion: The AGA has proven useful in selecting the best combination of biomarkers for prediction of AD progression. The algorithm presented here is generic and can be extended to other data sets generated in projects that seek to identify combination of biomarkers or other features that are predictive of disease onset or progression.",
keywords = "Adaptive genetic algorithm, Alzheimer's, Biomarkers, Logistic regression, Prediction",
author = "Luke Vandewater and Vladimir Brusic and William Wilson and Lance Macaulay and Ping Zhang",
year = "2015",
month = "12",
day = "9",
doi = "10.1186/1471-2105-16-S18-S1",
language = "English",
volume = "16",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",
number = "18",

}

TY - JOUR

T1 - An adaptive genetic algorithm for selection of blood-based biomarkers for prediction of Alzheimer's disease progression

AU - Vandewater, Luke

AU - Brusic, Vladimir

AU - Wilson, William

AU - Macaulay, Lance

AU - Zhang, Ping

PY - 2015/12/9

Y1 - 2015/12/9

N2 - Background: Alzheimer's disease is a multifactorial disorder that may be diagnosed earlier using a combination of tests rather than any single test. Search algorithms and optimization techniques in combination with model evaluation techniques have been used previously to perform the selection of suitable feature sets. Previously we successfully applied GA with LR to neuropsychological data contained within the The Australian Imaging, Biomarkers and Lifestyle (AIBL) study of aging, to select cognitive tests for prediction of progression of AD. This research addresses an Adaptive Genetic Algorithm (AGA) in combination with LR for identifying the best biomarker combination for prediction of the progression to AD. Results: The model has been explored in terms of parameter optimization to predict conversion from healthy stage to AD with high accuracy. Several feature sets were selected - the resulting prediction moddels showed higher area under the ROC values (0.83-0.89). The results has shown consistency with some of the medical research reported in literature. Conclusion: The AGA has proven useful in selecting the best combination of biomarkers for prediction of AD progression. The algorithm presented here is generic and can be extended to other data sets generated in projects that seek to identify combination of biomarkers or other features that are predictive of disease onset or progression.

AB - Background: Alzheimer's disease is a multifactorial disorder that may be diagnosed earlier using a combination of tests rather than any single test. Search algorithms and optimization techniques in combination with model evaluation techniques have been used previously to perform the selection of suitable feature sets. Previously we successfully applied GA with LR to neuropsychological data contained within the The Australian Imaging, Biomarkers and Lifestyle (AIBL) study of aging, to select cognitive tests for prediction of progression of AD. This research addresses an Adaptive Genetic Algorithm (AGA) in combination with LR for identifying the best biomarker combination for prediction of the progression to AD. Results: The model has been explored in terms of parameter optimization to predict conversion from healthy stage to AD with high accuracy. Several feature sets were selected - the resulting prediction moddels showed higher area under the ROC values (0.83-0.89). The results has shown consistency with some of the medical research reported in literature. Conclusion: The AGA has proven useful in selecting the best combination of biomarkers for prediction of AD progression. The algorithm presented here is generic and can be extended to other data sets generated in projects that seek to identify combination of biomarkers or other features that are predictive of disease onset or progression.

KW - Adaptive genetic algorithm

KW - Alzheimer's

KW - Biomarkers

KW - Logistic regression

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=84961588385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961588385&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-16-S18-S1

DO - 10.1186/1471-2105-16-S18-S1

M3 - Article

VL - 16

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - 18

M1 - S1

ER -