Sparse learning and stability selection for predicting MCI to AD conversion using baseline ADNI data

Jieping Ye, Michael Farnum, Eric Yang, Rudi Verbeeck, Victor Lobanov, Nandini Raghavan, Gerald Novak, Allitia DiBernardo, Vaibhav A. Narayan

Research output: Contribution to journalArticle

80 Citations (Scopus)

Abstract

Background: Patients with Mild Cognitive Impairment (MCI) are at high risk of progression to Alzheimer's dementia. Identifying MCI individuals with high likelihood of conversion to dementia and the associated biosignatures has recently received increasing attention in AD research. Different biosignatures for AD (neuroimaging, demographic, genetic and cognitive measures) may contain complementary information for diagnosis and prognosis of AD.Methods: We have conducted a comprehensive study using a large number of samples from the Alzheimer's Disease Neuroimaging Initiative (ADNI) to test the power of integrating various baseline data for predicting the conversion from MCI to probable AD and identifying a small subset of biosignatures for the prediction and assess the relative importance of different modalities in predicting MCI to AD conversion. We have employed sparse logistic regression with stability selection for the integration and selection of potential predictors. Our study differs from many of the other ones in three important respects: (1) we use a large cohort of MCI samples that are unbiased with respect to age or education status between case and controls (2) we integrate and test various types of baseline data available in ADNI including MRI, demographic, genetic and cognitive measures and (3) we apply sparse logistic regression with stability selection to ADNI data for robust feature selection.Results: We have used 319 MCI subjects from ADNI that had MRI measurements at the baseline and passed quality control, including 177 MCI Non-converters and 142 MCI Converters. Conversion was considered over the course of a 4-year follow-up period. A combination of 15 features (predictors) including those from MRI scans, APOE genotyping, and cognitive measures achieves the best prediction with an AUC score of 0.8587.Conclusions: Our results demonstrate the power of integrating various baseline data for prediction of the conversion from MCI to probable AD. Our results also demonstrate the effectiveness of stability selection for feature selection in the context of sparse logistic regression.

Original languageEnglish (US)
Article number46
JournalBMC Neurology
Volume12
DOIs
StatePublished - Jun 25 2012

Fingerprint

Neuroimaging
Alzheimer Disease
Learning
Logistic Models
Demography
Cognitive Dysfunction
Quality Control
Area Under Curve
Dementia
Magnetic Resonance Imaging
Education
Research

ASJC Scopus subject areas

  • Clinical Neurology

Cite this

Ye, J., Farnum, M., Yang, E., Verbeeck, R., Lobanov, V., Raghavan, N., ... Narayan, V. A. (2012). Sparse learning and stability selection for predicting MCI to AD conversion using baseline ADNI data. BMC Neurology, 12, [46]. https://doi.org/10.1186/1471-2377-12-46

Sparse learning and stability selection for predicting MCI to AD conversion using baseline ADNI data. / Ye, Jieping; Farnum, Michael; Yang, Eric; Verbeeck, Rudi; Lobanov, Victor; Raghavan, Nandini; Novak, Gerald; DiBernardo, Allitia; Narayan, Vaibhav A.

In: BMC Neurology, Vol. 12, 46, 25.06.2012.

Research output: Contribution to journalArticle

Ye, J, Farnum, M, Yang, E, Verbeeck, R, Lobanov, V, Raghavan, N, Novak, G, DiBernardo, A & Narayan, VA 2012, 'Sparse learning and stability selection for predicting MCI to AD conversion using baseline ADNI data', BMC Neurology, vol. 12, 46. https://doi.org/10.1186/1471-2377-12-46
Ye, Jieping ; Farnum, Michael ; Yang, Eric ; Verbeeck, Rudi ; Lobanov, Victor ; Raghavan, Nandini ; Novak, Gerald ; DiBernardo, Allitia ; Narayan, Vaibhav A. / Sparse learning and stability selection for predicting MCI to AD conversion using baseline ADNI data. In: BMC Neurology. 2012 ; Vol. 12.
@article{ac3593c239574ac68184657e6092e640,
title = "Sparse learning and stability selection for predicting MCI to AD conversion using baseline ADNI data",
abstract = "Background: Patients with Mild Cognitive Impairment (MCI) are at high risk of progression to Alzheimer's dementia. Identifying MCI individuals with high likelihood of conversion to dementia and the associated biosignatures has recently received increasing attention in AD research. Different biosignatures for AD (neuroimaging, demographic, genetic and cognitive measures) may contain complementary information for diagnosis and prognosis of AD.Methods: We have conducted a comprehensive study using a large number of samples from the Alzheimer's Disease Neuroimaging Initiative (ADNI) to test the power of integrating various baseline data for predicting the conversion from MCI to probable AD and identifying a small subset of biosignatures for the prediction and assess the relative importance of different modalities in predicting MCI to AD conversion. We have employed sparse logistic regression with stability selection for the integration and selection of potential predictors. Our study differs from many of the other ones in three important respects: (1) we use a large cohort of MCI samples that are unbiased with respect to age or education status between case and controls (2) we integrate and test various types of baseline data available in ADNI including MRI, demographic, genetic and cognitive measures and (3) we apply sparse logistic regression with stability selection to ADNI data for robust feature selection.Results: We have used 319 MCI subjects from ADNI that had MRI measurements at the baseline and passed quality control, including 177 MCI Non-converters and 142 MCI Converters. Conversion was considered over the course of a 4-year follow-up period. A combination of 15 features (predictors) including those from MRI scans, APOE genotyping, and cognitive measures achieves the best prediction with an AUC score of 0.8587.Conclusions: Our results demonstrate the power of integrating various baseline data for prediction of the conversion from MCI to probable AD. Our results also demonstrate the effectiveness of stability selection for feature selection in the context of sparse logistic regression.",
author = "Jieping Ye and Michael Farnum and Eric Yang and Rudi Verbeeck and Victor Lobanov and Nandini Raghavan and Gerald Novak and Allitia DiBernardo and Narayan, {Vaibhav A.}",
year = "2012",
month = "6",
day = "25",
doi = "10.1186/1471-2377-12-46",
language = "English (US)",
volume = "12",
journal = "BMC Neurology",
issn = "1471-2377",
publisher = "BioMed Central",

}

TY - JOUR

T1 - Sparse learning and stability selection for predicting MCI to AD conversion using baseline ADNI data

AU - Ye, Jieping

AU - Farnum, Michael

AU - Yang, Eric

AU - Verbeeck, Rudi

AU - Lobanov, Victor

AU - Raghavan, Nandini

AU - Novak, Gerald

AU - DiBernardo, Allitia

AU - Narayan, Vaibhav A.

PY - 2012/6/25

Y1 - 2012/6/25

N2 - Background: Patients with Mild Cognitive Impairment (MCI) are at high risk of progression to Alzheimer's dementia. Identifying MCI individuals with high likelihood of conversion to dementia and the associated biosignatures has recently received increasing attention in AD research. Different biosignatures for AD (neuroimaging, demographic, genetic and cognitive measures) may contain complementary information for diagnosis and prognosis of AD.Methods: We have conducted a comprehensive study using a large number of samples from the Alzheimer's Disease Neuroimaging Initiative (ADNI) to test the power of integrating various baseline data for predicting the conversion from MCI to probable AD and identifying a small subset of biosignatures for the prediction and assess the relative importance of different modalities in predicting MCI to AD conversion. We have employed sparse logistic regression with stability selection for the integration and selection of potential predictors. Our study differs from many of the other ones in three important respects: (1) we use a large cohort of MCI samples that are unbiased with respect to age or education status between case and controls (2) we integrate and test various types of baseline data available in ADNI including MRI, demographic, genetic and cognitive measures and (3) we apply sparse logistic regression with stability selection to ADNI data for robust feature selection.Results: We have used 319 MCI subjects from ADNI that had MRI measurements at the baseline and passed quality control, including 177 MCI Non-converters and 142 MCI Converters. Conversion was considered over the course of a 4-year follow-up period. A combination of 15 features (predictors) including those from MRI scans, APOE genotyping, and cognitive measures achieves the best prediction with an AUC score of 0.8587.Conclusions: Our results demonstrate the power of integrating various baseline data for prediction of the conversion from MCI to probable AD. Our results also demonstrate the effectiveness of stability selection for feature selection in the context of sparse logistic regression.

AB - Background: Patients with Mild Cognitive Impairment (MCI) are at high risk of progression to Alzheimer's dementia. Identifying MCI individuals with high likelihood of conversion to dementia and the associated biosignatures has recently received increasing attention in AD research. Different biosignatures for AD (neuroimaging, demographic, genetic and cognitive measures) may contain complementary information for diagnosis and prognosis of AD.Methods: We have conducted a comprehensive study using a large number of samples from the Alzheimer's Disease Neuroimaging Initiative (ADNI) to test the power of integrating various baseline data for predicting the conversion from MCI to probable AD and identifying a small subset of biosignatures for the prediction and assess the relative importance of different modalities in predicting MCI to AD conversion. We have employed sparse logistic regression with stability selection for the integration and selection of potential predictors. Our study differs from many of the other ones in three important respects: (1) we use a large cohort of MCI samples that are unbiased with respect to age or education status between case and controls (2) we integrate and test various types of baseline data available in ADNI including MRI, demographic, genetic and cognitive measures and (3) we apply sparse logistic regression with stability selection to ADNI data for robust feature selection.Results: We have used 319 MCI subjects from ADNI that had MRI measurements at the baseline and passed quality control, including 177 MCI Non-converters and 142 MCI Converters. Conversion was considered over the course of a 4-year follow-up period. A combination of 15 features (predictors) including those from MRI scans, APOE genotyping, and cognitive measures achieves the best prediction with an AUC score of 0.8587.Conclusions: Our results demonstrate the power of integrating various baseline data for prediction of the conversion from MCI to probable AD. Our results also demonstrate the effectiveness of stability selection for feature selection in the context of sparse logistic regression.

UR - http://www.scopus.com/inward/record.url?scp=84862598129&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862598129&partnerID=8YFLogxK

U2 - 10.1186/1471-2377-12-46

DO - 10.1186/1471-2377-12-46

M3 - Article

C2 - 22731740

AN - SCOPUS:84862598129

VL - 12

JO - BMC Neurology

JF - BMC Neurology

SN - 1471-2377

M1 - 46

ER -