Online learning for classification of Alzheimer disease based on cortical thickness and hippocampal shape analysis

Ga Young Lee, Jeonghun Kim, Ju Han Kim, Kiwoong Kim, Jun Kyung Seong

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Objectives: Mobile healthcare applications are becoming a growing trend. Also, the prevalence of dementia in modern society is showing a steady growing trend. Among degenerative brain diseases that cause dementia, Alzheimer disease (AD) is the most common. The purpose of this study was to identify AD patients using magnetic resonance imaging in the mobile environment. Methods: We propose an incremental classification for mobile healthcare systems. Our classification method is based on incremental learning for AD diagnosis and AD prediction using the cortical thickness data and hippocampus shape. We constructed a classifier based on principal component analysis and linear discriminant analysis. We performed initial learning and mobile subject classification. Initial learning is the group learning part in our server. Our smartphone agent implements the mobile classification and shows various results. Results: With use of cortical thickness data analysis alone, the discrimination accuracy was 87.33% (sensitivity 96.49% and specificity 64.33%). When cortical thickness data and hippocampal shape were analyzed together, the achieved accuracy was 87.52% (sensitivity 96.79% and specificity 63.24%). Conclusions: In this paper, we presented a classification method based on online learning for AD diagnosis by employing both cortical thickness data and hippocampal shape analysis data. Our method was implemented on smartphone devices and discriminated AD patients for normal group.

Original languageEnglish
Pages (from-to)61-68
Number of pages8
JournalHealthcare Informatics Research
Volume20
Issue number1
DOIs
Publication statusPublished - 2014 Feb 13

Fingerprint

Alzheimer Disease
Learning
Smartphones
Dementia
Mobile Applications
Delivery of Health Care
Sensitivity and Specificity
Brain Diseases
Discriminant Analysis
Principal Component Analysis
Discriminant analysis
Magnetic resonance
Hippocampus
Principal component analysis
Magnetic Resonance Imaging
Brain
Classifiers
Servers
Equipment and Supplies
Imaging techniques

Keywords

  • Alzheimer disease
  • Artificial intelligence
  • Classification
  • Delivery of health care
  • Mobile health units

ASJC Scopus subject areas

  • Health Informatics
  • Biomedical Engineering
  • Health Information Management

Cite this

Online learning for classification of Alzheimer disease based on cortical thickness and hippocampal shape analysis. / Lee, Ga Young; Kim, Jeonghun; Kim, Ju Han; Kim, Kiwoong; Seong, Jun Kyung.

In: Healthcare Informatics Research, Vol. 20, No. 1, 13.02.2014, p. 61-68.

Research output: Contribution to journalArticle

@article{364969d9483a4b17a1fe7883e9e10b95,
title = "Online learning for classification of Alzheimer disease based on cortical thickness and hippocampal shape analysis",
abstract = "Objectives: Mobile healthcare applications are becoming a growing trend. Also, the prevalence of dementia in modern society is showing a steady growing trend. Among degenerative brain diseases that cause dementia, Alzheimer disease (AD) is the most common. The purpose of this study was to identify AD patients using magnetic resonance imaging in the mobile environment. Methods: We propose an incremental classification for mobile healthcare systems. Our classification method is based on incremental learning for AD diagnosis and AD prediction using the cortical thickness data and hippocampus shape. We constructed a classifier based on principal component analysis and linear discriminant analysis. We performed initial learning and mobile subject classification. Initial learning is the group learning part in our server. Our smartphone agent implements the mobile classification and shows various results. Results: With use of cortical thickness data analysis alone, the discrimination accuracy was 87.33{\%} (sensitivity 96.49{\%} and specificity 64.33{\%}). When cortical thickness data and hippocampal shape were analyzed together, the achieved accuracy was 87.52{\%} (sensitivity 96.79{\%} and specificity 63.24{\%}). Conclusions: In this paper, we presented a classification method based on online learning for AD diagnosis by employing both cortical thickness data and hippocampal shape analysis data. Our method was implemented on smartphone devices and discriminated AD patients for normal group.",
keywords = "Alzheimer disease, Artificial intelligence, Classification, Delivery of health care, Mobile health units",
author = "Lee, {Ga Young} and Jeonghun Kim and Kim, {Ju Han} and Kiwoong Kim and Seong, {Jun Kyung}",
year = "2014",
month = "2",
day = "13",
doi = "10.4258/hir.2014.20.1.61",
language = "English",
volume = "20",
pages = "61--68",
journal = "Healthcare Informatics Research",
issn = "2093-3681",
publisher = "Korean Society of Medical Informatics",
number = "1",

}

TY - JOUR

T1 - Online learning for classification of Alzheimer disease based on cortical thickness and hippocampal shape analysis

AU - Lee, Ga Young

AU - Kim, Jeonghun

AU - Kim, Ju Han

AU - Kim, Kiwoong

AU - Seong, Jun Kyung

PY - 2014/2/13

Y1 - 2014/2/13

N2 - Objectives: Mobile healthcare applications are becoming a growing trend. Also, the prevalence of dementia in modern society is showing a steady growing trend. Among degenerative brain diseases that cause dementia, Alzheimer disease (AD) is the most common. The purpose of this study was to identify AD patients using magnetic resonance imaging in the mobile environment. Methods: We propose an incremental classification for mobile healthcare systems. Our classification method is based on incremental learning for AD diagnosis and AD prediction using the cortical thickness data and hippocampus shape. We constructed a classifier based on principal component analysis and linear discriminant analysis. We performed initial learning and mobile subject classification. Initial learning is the group learning part in our server. Our smartphone agent implements the mobile classification and shows various results. Results: With use of cortical thickness data analysis alone, the discrimination accuracy was 87.33% (sensitivity 96.49% and specificity 64.33%). When cortical thickness data and hippocampal shape were analyzed together, the achieved accuracy was 87.52% (sensitivity 96.79% and specificity 63.24%). Conclusions: In this paper, we presented a classification method based on online learning for AD diagnosis by employing both cortical thickness data and hippocampal shape analysis data. Our method was implemented on smartphone devices and discriminated AD patients for normal group.

AB - Objectives: Mobile healthcare applications are becoming a growing trend. Also, the prevalence of dementia in modern society is showing a steady growing trend. Among degenerative brain diseases that cause dementia, Alzheimer disease (AD) is the most common. The purpose of this study was to identify AD patients using magnetic resonance imaging in the mobile environment. Methods: We propose an incremental classification for mobile healthcare systems. Our classification method is based on incremental learning for AD diagnosis and AD prediction using the cortical thickness data and hippocampus shape. We constructed a classifier based on principal component analysis and linear discriminant analysis. We performed initial learning and mobile subject classification. Initial learning is the group learning part in our server. Our smartphone agent implements the mobile classification and shows various results. Results: With use of cortical thickness data analysis alone, the discrimination accuracy was 87.33% (sensitivity 96.49% and specificity 64.33%). When cortical thickness data and hippocampal shape were analyzed together, the achieved accuracy was 87.52% (sensitivity 96.79% and specificity 63.24%). Conclusions: In this paper, we presented a classification method based on online learning for AD diagnosis by employing both cortical thickness data and hippocampal shape analysis data. Our method was implemented on smartphone devices and discriminated AD patients for normal group.

KW - Alzheimer disease

KW - Artificial intelligence

KW - Classification

KW - Delivery of health care

KW - Mobile health units

UR - http://www.scopus.com/inward/record.url?scp=84893605524&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893605524&partnerID=8YFLogxK

U2 - 10.4258/hir.2014.20.1.61

DO - 10.4258/hir.2014.20.1.61

M3 - Article

AN - SCOPUS:84893605524

VL - 20

SP - 61

EP - 68

JO - Healthcare Informatics Research

JF - Healthcare Informatics Research

SN - 2093-3681

IS - 1

ER -