Pairwise Correlation Analysis of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) Dataset Reveals Significant Feature Correlation

The Alzheimer’s Disease Neuroimaging Initiative (ADNI) contains extensive patient measurements (e.g., magnetic resonance imaging [MRI], biometrics, RNA expression, etc.) from Alzheimer’s disease (AD) cases and controls that have recently been used by machine learning algorithms to evaluate AD onset...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Erik D. Huckvale, Matthew W. Hodgman, Brianna B. Greenwood, Devorah O. Stucki, Katrisa M. Ward, Mark T. W. Ebbert, John S. K. Kauwe, The Alzheimer’s Disease Neuroimaging Initiative, The Alzheimer’s Disease Metabolomics Consortium, Justin B. Miller
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	ADNI pairwise feature correlation feature reduction machine learning Alzheimer’s disease Genetics QH426-470
Acceso en línea:	https://doaj.org/article/05cfb758642e4e2b8035bed340482946
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:05cfb758642e4e2b8035bed340482946
record_format	dspace
spelling	oai:doaj.org-article:05cfb758642e4e2b8035bed3404829462021-11-25T17:40:23ZPairwise Correlation Analysis of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) Dataset Reveals Significant Feature Correlation10.3390/genes121116612073-4425https://doaj.org/article/05cfb758642e4e2b8035bed3404829462021-10-01T00:00:00Zhttps://www.mdpi.com/2073-4425/12/11/1661https://doaj.org/toc/2073-4425The Alzheimer’s Disease Neuroimaging Initiative (ADNI) contains extensive patient measurements (e.g., magnetic resonance imaging [MRI], biometrics, RNA expression, etc.) from Alzheimer’s disease (AD) cases and controls that have recently been used by machine learning algorithms to evaluate AD onset and progression. While using a variety of biomarkers is essential to AD research, highly correlated input features can significantly decrease machine learning model generalizability and performance. Additionally, redundant features unnecessarily increase computational time and resources necessary to train predictive models. Therefore, we used 49,288 biomarkers and 793,600 extracted MRI features to assess feature correlation within the ADNI dataset to determine the extent to which this issue might impact large scale analyses using these data. We found that 93.457% of biomarkers, 92.549% of the gene expression values, and 100% of MRI features were strongly correlated with at least one other feature in ADNI based on our Bonferroni corrected α (<i>p</i>-value ≤ 1.40754 × 10<sup>−13</sup>). We provide a comprehensive mapping of all ADNI biomarkers to highly correlated features within the dataset. Additionally, we show that significant correlation within the ADNI dataset should be resolved before performing bulk data analyses, and we provide recommendations to address these issues. We anticipate that these recommendations and resources will help guide researchers utilizing the ADNI dataset to increase model performance and reduce the cost and complexity of their analyses.Erik D. HuckvaleMatthew W. HodgmanBrianna B. GreenwoodDevorah O. StuckiKatrisa M. WardMark T. W. EbbertJohn S. K. KauweThe Alzheimer’s Disease Neuroimaging InitiativeThe Alzheimer’s Disease Metabolomics ConsortiumJustin B. MillerMDPI AGarticleADNIpairwise feature correlationfeature reductionmachine learningAlzheimer’s diseaseGeneticsQH426-470ENGenes, Vol 12, Iss 1661, p 1661 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	ADNI pairwise feature correlation feature reduction machine learning Alzheimer’s disease Genetics QH426-470
spellingShingle	ADNI pairwise feature correlation feature reduction machine learning Alzheimer’s disease Genetics QH426-470 Erik D. Huckvale Matthew W. Hodgman Brianna B. Greenwood Devorah O. Stucki Katrisa M. Ward Mark T. W. Ebbert John S. K. Kauwe The Alzheimer’s Disease Neuroimaging Initiative The Alzheimer’s Disease Metabolomics Consortium Justin B. Miller Pairwise Correlation Analysis of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) Dataset Reveals Significant Feature Correlation
description	The Alzheimer’s Disease Neuroimaging Initiative (ADNI) contains extensive patient measurements (e.g., magnetic resonance imaging [MRI], biometrics, RNA expression, etc.) from Alzheimer’s disease (AD) cases and controls that have recently been used by machine learning algorithms to evaluate AD onset and progression. While using a variety of biomarkers is essential to AD research, highly correlated input features can significantly decrease machine learning model generalizability and performance. Additionally, redundant features unnecessarily increase computational time and resources necessary to train predictive models. Therefore, we used 49,288 biomarkers and 793,600 extracted MRI features to assess feature correlation within the ADNI dataset to determine the extent to which this issue might impact large scale analyses using these data. We found that 93.457% of biomarkers, 92.549% of the gene expression values, and 100% of MRI features were strongly correlated with at least one other feature in ADNI based on our Bonferroni corrected α (<i>p</i>-value ≤ 1.40754 × 10<sup>−13</sup>). We provide a comprehensive mapping of all ADNI biomarkers to highly correlated features within the dataset. Additionally, we show that significant correlation within the ADNI dataset should be resolved before performing bulk data analyses, and we provide recommendations to address these issues. We anticipate that these recommendations and resources will help guide researchers utilizing the ADNI dataset to increase model performance and reduce the cost and complexity of their analyses.
format	article
author	Erik D. Huckvale Matthew W. Hodgman Brianna B. Greenwood Devorah O. Stucki Katrisa M. Ward Mark T. W. Ebbert John S. K. Kauwe The Alzheimer’s Disease Neuroimaging Initiative The Alzheimer’s Disease Metabolomics Consortium Justin B. Miller
author_facet	Erik D. Huckvale Matthew W. Hodgman Brianna B. Greenwood Devorah O. Stucki Katrisa M. Ward Mark T. W. Ebbert John S. K. Kauwe The Alzheimer’s Disease Neuroimaging Initiative The Alzheimer’s Disease Metabolomics Consortium Justin B. Miller
author_sort	Erik D. Huckvale
title	Pairwise Correlation Analysis of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) Dataset Reveals Significant Feature Correlation
title_short	Pairwise Correlation Analysis of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) Dataset Reveals Significant Feature Correlation
title_full	Pairwise Correlation Analysis of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) Dataset Reveals Significant Feature Correlation
title_fullStr	Pairwise Correlation Analysis of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) Dataset Reveals Significant Feature Correlation
title_full_unstemmed	Pairwise Correlation Analysis of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) Dataset Reveals Significant Feature Correlation
title_sort	pairwise correlation analysis of the alzheimer’s disease neuroimaging initiative (adni) dataset reveals significant feature correlation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/05cfb758642e4e2b8035bed340482946
work_keys_str_mv	AT erikdhuckvale pairwisecorrelationanalysisofthealzheimersdiseaseneuroimaginginitiativeadnidatasetrevealssignificantfeaturecorrelation AT matthewwhodgman pairwisecorrelationanalysisofthealzheimersdiseaseneuroimaginginitiativeadnidatasetrevealssignificantfeaturecorrelation AT briannabgreenwood pairwisecorrelationanalysisofthealzheimersdiseaseneuroimaginginitiativeadnidatasetrevealssignificantfeaturecorrelation AT devorahostucki pairwisecorrelationanalysisofthealzheimersdiseaseneuroimaginginitiativeadnidatasetrevealssignificantfeaturecorrelation AT katrisamward pairwisecorrelationanalysisofthealzheimersdiseaseneuroimaginginitiativeadnidatasetrevealssignificantfeaturecorrelation AT marktwebbert pairwisecorrelationanalysisofthealzheimersdiseaseneuroimaginginitiativeadnidatasetrevealssignificantfeaturecorrelation AT johnskkauwe pairwisecorrelationanalysisofthealzheimersdiseaseneuroimaginginitiativeadnidatasetrevealssignificantfeaturecorrelation AT thealzheimersdiseaseneuroimaginginitiative pairwisecorrelationanalysisofthealzheimersdiseaseneuroimaginginitiativeadnidatasetrevealssignificantfeaturecorrelation AT thealzheimersdiseasemetabolomicsconsortium pairwisecorrelationanalysisofthealzheimersdiseaseneuroimaginginitiativeadnidatasetrevealssignificantfeaturecorrelation AT justinbmiller pairwisecorrelationanalysisofthealzheimersdiseaseneuroimaginginitiativeadnidatasetrevealssignificantfeaturecorrelation
_version_	1718412086044786688

Pairwise Correlation Analysis of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) Dataset Reveals Significant Feature Correlation

Ejemplares similares