Using normative modelling to detect disease progression in mild cognitive impairment and Alzheimer’s disease in a cross-sectional multi-cohort study

Abstract Normative modelling is an emerging method for quantifying how individuals deviate from the healthy populational pattern. Several machine learning models have been implemented to develop normative models to investigate brain disorders, including regression, support vector machines and Gaussi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Walter H. L. Pinaya, Cristina Scarpazza, Rafael Garcia-Dias, Sandra Vieira, Lea Baecker, Pedro F da Costa, Alberto Redolfi, Giovanni B. Frisoni, Michela Pievani, Vince D. Calhoun, João R. Sato, Andrea Mechelli
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/232c67a78bc8428fb037c3b63039cf5c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:232c67a78bc8428fb037c3b63039cf5c
record_format	dspace
spelling	oai:doaj.org-article:232c67a78bc8428fb037c3b63039cf5c2021-12-02T18:49:16ZUsing normative modelling to detect disease progression in mild cognitive impairment and Alzheimer’s disease in a cross-sectional multi-cohort study10.1038/s41598-021-95098-02045-2322https://doaj.org/article/232c67a78bc8428fb037c3b63039cf5c2021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-95098-0https://doaj.org/toc/2045-2322Abstract Normative modelling is an emerging method for quantifying how individuals deviate from the healthy populational pattern. Several machine learning models have been implemented to develop normative models to investigate brain disorders, including regression, support vector machines and Gaussian process models. With the advance of deep learning technology, the use of deep neural networks has also been proposed. In this study, we assessed normative models based on deep autoencoders using structural neuroimaging data from patients with Alzheimer’s disease (n = 206) and mild cognitive impairment (n = 354). We first trained the autoencoder on an independent dataset (UK Biobank dataset) with 11,034 healthy controls. Then, we estimated how each patient deviated from this norm and established which brain regions were associated to this deviation. Finally, we compared the performance of our normative model against traditional classifiers. As expected, we found that patients exhibited deviations according to the severity of their clinical condition. The model identified medial temporal regions, including the hippocampus, and the ventricular system as critical regions for the calculation of the deviation score. Overall, the normative model had comparable cross-cohort generalizability to traditional classifiers. To promote open science, we are making all scripts and the trained models available to the wider research community.Walter H. L. PinayaCristina ScarpazzaRafael Garcia-DiasSandra VieiraLea BaeckerPedro F da CostaAlberto RedolfiGiovanni B. FrisoniMichela PievaniVince D. CalhounJoão R. SatoAndrea MechelliNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Walter H. L. Pinaya Cristina Scarpazza Rafael Garcia-Dias Sandra Vieira Lea Baecker Pedro F da Costa Alberto Redolfi Giovanni B. Frisoni Michela Pievani Vince D. Calhoun João R. Sato Andrea Mechelli Using normative modelling to detect disease progression in mild cognitive impairment and Alzheimer’s disease in a cross-sectional multi-cohort study
description	Abstract Normative modelling is an emerging method for quantifying how individuals deviate from the healthy populational pattern. Several machine learning models have been implemented to develop normative models to investigate brain disorders, including regression, support vector machines and Gaussian process models. With the advance of deep learning technology, the use of deep neural networks has also been proposed. In this study, we assessed normative models based on deep autoencoders using structural neuroimaging data from patients with Alzheimer’s disease (n = 206) and mild cognitive impairment (n = 354). We first trained the autoencoder on an independent dataset (UK Biobank dataset) with 11,034 healthy controls. Then, we estimated how each patient deviated from this norm and established which brain regions were associated to this deviation. Finally, we compared the performance of our normative model against traditional classifiers. As expected, we found that patients exhibited deviations according to the severity of their clinical condition. The model identified medial temporal regions, including the hippocampus, and the ventricular system as critical regions for the calculation of the deviation score. Overall, the normative model had comparable cross-cohort generalizability to traditional classifiers. To promote open science, we are making all scripts and the trained models available to the wider research community.
format	article
author	Walter H. L. Pinaya Cristina Scarpazza Rafael Garcia-Dias Sandra Vieira Lea Baecker Pedro F da Costa Alberto Redolfi Giovanni B. Frisoni Michela Pievani Vince D. Calhoun João R. Sato Andrea Mechelli
author_facet	Walter H. L. Pinaya Cristina Scarpazza Rafael Garcia-Dias Sandra Vieira Lea Baecker Pedro F da Costa Alberto Redolfi Giovanni B. Frisoni Michela Pievani Vince D. Calhoun João R. Sato Andrea Mechelli
author_sort	Walter H. L. Pinaya
title	Using normative modelling to detect disease progression in mild cognitive impairment and Alzheimer’s disease in a cross-sectional multi-cohort study
title_short	Using normative modelling to detect disease progression in mild cognitive impairment and Alzheimer’s disease in a cross-sectional multi-cohort study
title_full	Using normative modelling to detect disease progression in mild cognitive impairment and Alzheimer’s disease in a cross-sectional multi-cohort study
title_fullStr	Using normative modelling to detect disease progression in mild cognitive impairment and Alzheimer’s disease in a cross-sectional multi-cohort study
title_full_unstemmed	Using normative modelling to detect disease progression in mild cognitive impairment and Alzheimer’s disease in a cross-sectional multi-cohort study
title_sort	using normative modelling to detect disease progression in mild cognitive impairment and alzheimer’s disease in a cross-sectional multi-cohort study
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/232c67a78bc8428fb037c3b63039cf5c
work_keys_str_mv	AT walterhlpinaya usingnormativemodellingtodetectdiseaseprogressioninmildcognitiveimpairmentandalzheimersdiseaseinacrosssectionalmulticohortstudy AT cristinascarpazza usingnormativemodellingtodetectdiseaseprogressioninmildcognitiveimpairmentandalzheimersdiseaseinacrosssectionalmulticohortstudy AT rafaelgarciadias usingnormativemodellingtodetectdiseaseprogressioninmildcognitiveimpairmentandalzheimersdiseaseinacrosssectionalmulticohortstudy AT sandravieira usingnormativemodellingtodetectdiseaseprogressioninmildcognitiveimpairmentandalzheimersdiseaseinacrosssectionalmulticohortstudy AT leabaecker usingnormativemodellingtodetectdiseaseprogressioninmildcognitiveimpairmentandalzheimersdiseaseinacrosssectionalmulticohortstudy AT pedrofdacosta usingnormativemodellingtodetectdiseaseprogressioninmildcognitiveimpairmentandalzheimersdiseaseinacrosssectionalmulticohortstudy AT albertoredolfi usingnormativemodellingtodetectdiseaseprogressioninmildcognitiveimpairmentandalzheimersdiseaseinacrosssectionalmulticohortstudy AT giovannibfrisoni usingnormativemodellingtodetectdiseaseprogressioninmildcognitiveimpairmentandalzheimersdiseaseinacrosssectionalmulticohortstudy AT michelapievani usingnormativemodellingtodetectdiseaseprogressioninmildcognitiveimpairmentandalzheimersdiseaseinacrosssectionalmulticohortstudy AT vincedcalhoun usingnormativemodellingtodetectdiseaseprogressioninmildcognitiveimpairmentandalzheimersdiseaseinacrosssectionalmulticohortstudy AT joaorsato usingnormativemodellingtodetectdiseaseprogressioninmildcognitiveimpairmentandalzheimersdiseaseinacrosssectionalmulticohortstudy AT andreamechelli usingnormativemodellingtodetectdiseaseprogressioninmildcognitiveimpairmentandalzheimersdiseaseinacrosssectionalmulticohortstudy
_version_	1718377549195640832

Using normative modelling to detect disease progression in mild cognitive impairment and Alzheimer’s disease in a cross-sectional multi-cohort study

Ejemplares similares