A similarity-based approach to leverage multi-cohort medical data on the diagnosis and prognosis of Alzheimer's disease

The Alzheimer's Disease Neuroimaging Initiative

Research output: Contribution to journalArticle

Abstract

Motivation: Heterogeneous diseases such as Alzheimer's disease (AD) manifest a variety of phenotypes among populations. Early diagnosis and effective treatment offer cost benefits. Many studies on biochemical and imaging markers have shown potential promise in improving diagnosis, yet establishing quantitative diagnostic criteria for ancillary tests remains challenging. Results: We have developed a similarity-based approach that matches individuals to subjects with similar conditions. We modeled the disease with a Gaussian process, and tested the method in the Alzheimer's Disease Big Data DREAM Challenge. Ranked the highest among submitted methods, our diagnostic model predicted cognitive impairment scores in an independent dataset test with a correlation score of 0.573. It differentiated AD patients from control subjects with an area under the receiver operating curve of 0.920. Without knowing longitudinal information about subjects, the model predicted patients who are vulnerable to conversion from mild-cognitive impairment to AD through the similarity network. This diagnostic framework can be applied to other diseases with clinical heterogeneity, such as Parkinson's disease.

Original languageEnglish (US)
Article numbergiy085
JournalGigaScience
Volume7
Issue number7
DOIs
StatePublished - Jul 1 2018

Fingerprint

Alzheimer Disease
Health Care Costs
Cost-Benefit Analysis
Parkinson Disease
Early Diagnosis
Biomarkers
Phenotype
Population
Imaging techniques
Cognitive Dysfunction
Costs

Keywords

  • Alzheimer's Disease
  • Gaussian Process Regression
  • Kernel method
  • Machine learning
  • Patient similarity network

ASJC Scopus subject areas

  • Health Informatics
  • Computer Science Applications

Cite this

A similarity-based approach to leverage multi-cohort medical data on the diagnosis and prognosis of Alzheimer's disease. / The Alzheimer's Disease Neuroimaging Initiative.

In: GigaScience, Vol. 7, No. 7, giy085, 01.07.2018.

Research output: Contribution to journalArticle

@article{71fc7c4a96da4ac59c0e4ef1cb18f3aa,
title = "A similarity-based approach to leverage multi-cohort medical data on the diagnosis and prognosis of Alzheimer's disease",
abstract = "Motivation: Heterogeneous diseases such as Alzheimer's disease (AD) manifest a variety of phenotypes among populations. Early diagnosis and effective treatment offer cost benefits. Many studies on biochemical and imaging markers have shown potential promise in improving diagnosis, yet establishing quantitative diagnostic criteria for ancillary tests remains challenging. Results: We have developed a similarity-based approach that matches individuals to subjects with similar conditions. We modeled the disease with a Gaussian process, and tested the method in the Alzheimer's Disease Big Data DREAM Challenge. Ranked the highest among submitted methods, our diagnostic model predicted cognitive impairment scores in an independent dataset test with a correlation score of 0.573. It differentiated AD patients from control subjects with an area under the receiver operating curve of 0.920. Without knowing longitudinal information about subjects, the model predicted patients who are vulnerable to conversion from mild-cognitive impairment to AD through the similarity network. This diagnostic framework can be applied to other diseases with clinical heterogeneity, such as Parkinson's disease.",
keywords = "Alzheimer's Disease, Gaussian Process Regression, Kernel method, Machine learning, Patient similarity network",
author = "{The Alzheimer's Disease Neuroimaging Initiative} and Hongjiu Zhang and Fan Zhu and Hiroko Dodge and Higgins, {Gerald A.} and Omenn, {Gilbert S.} and Yuanfang Guan",
year = "2018",
month = "7",
day = "1",
doi = "10.1093/gigascience/giy085",
language = "English (US)",
volume = "7",
journal = "GigaScience",
issn = "2047-217X",
publisher = "BioMed Central",
number = "7",

}

TY - JOUR

T1 - A similarity-based approach to leverage multi-cohort medical data on the diagnosis and prognosis of Alzheimer's disease

AU - The Alzheimer's Disease Neuroimaging Initiative

AU - Zhang, Hongjiu

AU - Zhu, Fan

AU - Dodge, Hiroko

AU - Higgins, Gerald A.

AU - Omenn, Gilbert S.

AU - Guan, Yuanfang

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Motivation: Heterogeneous diseases such as Alzheimer's disease (AD) manifest a variety of phenotypes among populations. Early diagnosis and effective treatment offer cost benefits. Many studies on biochemical and imaging markers have shown potential promise in improving diagnosis, yet establishing quantitative diagnostic criteria for ancillary tests remains challenging. Results: We have developed a similarity-based approach that matches individuals to subjects with similar conditions. We modeled the disease with a Gaussian process, and tested the method in the Alzheimer's Disease Big Data DREAM Challenge. Ranked the highest among submitted methods, our diagnostic model predicted cognitive impairment scores in an independent dataset test with a correlation score of 0.573. It differentiated AD patients from control subjects with an area under the receiver operating curve of 0.920. Without knowing longitudinal information about subjects, the model predicted patients who are vulnerable to conversion from mild-cognitive impairment to AD through the similarity network. This diagnostic framework can be applied to other diseases with clinical heterogeneity, such as Parkinson's disease.

AB - Motivation: Heterogeneous diseases such as Alzheimer's disease (AD) manifest a variety of phenotypes among populations. Early diagnosis and effective treatment offer cost benefits. Many studies on biochemical and imaging markers have shown potential promise in improving diagnosis, yet establishing quantitative diagnostic criteria for ancillary tests remains challenging. Results: We have developed a similarity-based approach that matches individuals to subjects with similar conditions. We modeled the disease with a Gaussian process, and tested the method in the Alzheimer's Disease Big Data DREAM Challenge. Ranked the highest among submitted methods, our diagnostic model predicted cognitive impairment scores in an independent dataset test with a correlation score of 0.573. It differentiated AD patients from control subjects with an area under the receiver operating curve of 0.920. Without knowing longitudinal information about subjects, the model predicted patients who are vulnerable to conversion from mild-cognitive impairment to AD through the similarity network. This diagnostic framework can be applied to other diseases with clinical heterogeneity, such as Parkinson's disease.

KW - Alzheimer's Disease

KW - Gaussian Process Regression

KW - Kernel method

KW - Machine learning

KW - Patient similarity network

UR - http://www.scopus.com/inward/record.url?scp=85050890511&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050890511&partnerID=8YFLogxK

U2 - 10.1093/gigascience/giy085

DO - 10.1093/gigascience/giy085

M3 - Article

VL - 7

JO - GigaScience

JF - GigaScience

SN - 2047-217X

IS - 7

M1 - giy085

ER -