Stacked autoencoders as new models for an accurate Alzheimer’s disease classification support using resting-state EEG and MRI measurements

•Artificial neural networks with stacked autoencoders detected Alzheimer’s dementia patients based on EEG and structural MRI variables.•Classification accuracies over control participants reached 80% (EEG), 85% (MRI), and 89% (both).•These results motivate future multi-centric, harmonized prospectiv...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Clinical neurophysiology Ročník 132; číslo 1; s. 232 - 245
Hlavní autoři:	Ferri, Raffaele, Babiloni, Claudio, Karami, Vania, Triggiani, Antonio Ivano, Carducci, Filippo, Noce, Giuseppe, Lizio, Roberta, Pascarelli, Maria T., Soricelli, Andrea, Amenta, Francesco, Bozzao, Alessandro, Romano, Andrea, Giubilei, Franco, Del Percio, Claudio, Stocchi, Fabrizio, Frisoni, Giovanni B., Nobili, Flavio, Patanè, Luca, Arena, Paolo
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Netherlands Elsevier B.V 01.01.2021
Témata:	Alzheimer’s Disease (AD) Low-resolution brain electromagnetic tomography (LORETA) Neurology Resting State Electroencephalography (rsEEG) Stacked Artificial Neural Networks (ANNs) with Autoencoders Alzheimer’s Disease (AD) Resting State Electroencephalography (rsEEG) Low-resolution brain electromagnetic tomography (LORETA) Stacked Artificial Neural Networks (ANNs) with Autoencoders
ISSN:	1388-2457, 1872-8952, 1872-8952
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	•Artificial neural networks with stacked autoencoders detected Alzheimer’s dementia patients based on EEG and structural MRI variables.•Classification accuracies over control participants reached 80% (EEG), 85% (MRI), and 89% (both).•These results motivate future multi-centric, harmonized prospective and longitudinal cross-validation studies. This retrospective and exploratory study tested the accuracy of artificial neural networks (ANNs) at detecting Alzheimer’s disease patients with dementia (ADD) based on input variables extracted from resting-state electroencephalogram (rsEEG), structural magnetic resonance imaging (sMRI) or both. For the classification exercise, the ANNs had two architectures that included stacked (autoencoding) hidden layers recreating input data in the output. The classification was based on LORETA source estimates from rsEEG activity recorded with 10–20 montage system (19 electrodes) and standard sMRI variables in 89 ADD and 45 healthy control participants taken from a national database. The ANN with stacked autoencoders and a deep leaning model representing both ADD and control participants showed classification accuracies in discriminating them of 80%, 85%, and 89% using rsEEG, sMRI, and rsEEG + sMRI features, respectively. The two ANNs with stacked autoencoders and a deep leaning model specialized for either ADD or control participants showed classification accuracies of 77%, 83%, and 86% using the same input features. The two architectures of ANNs using stacked (autoencoding) hidden layers consistently reached moderate to high accuracy in the discrimination between ADD and healthy control participants as a function of the rsEEG and sMRI features employed. The present results encourage future multi-centric, prospective and longitudinal cross-validation studies using high resolution EEG techniques and harmonized clinical procedures towards clinical applications of the present ANNs.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	1388-2457 1872-8952 1872-8952
DOI:	10.1016/j.clinph.2020.09.015