Elman neural network for the early identification of cognitive impairment in Alzheimer�s disease

Bertè, Francesco; Lamponi, Giuseppe; Calabrò, Rocco Salvatore; Bramantı, Placido

doi:10.11138/fneur/2014.29.1.057

Cited by 12 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to previous studies which demonstrated the utility of machine learning models for predicting outcomes closely related to the risk of disability in the older people as fall risk [33,34] or dementia [35,36], these results demonstrate a fairly high level of accuracy (exceeding 80% case classification accuracy) for predicting functional status one year ahead using individual features and information available from a standardized CGA which are available, for example, at the time of admission to rehabilitation program. The performance of models generated by SVMs exceeded the performance of models analysed using LR model constrained by the same independent variables.…”

Section: Discussionsupporting

confidence: 84%

A new tool for the evaluation of the rehabilitation outcomes in older persons: a machine learning model to predict functional status 1 year ahead

Verrusio

Renzi

Dellepiane³

et al. 2018

Eur Geriatr Med

View full text Add to dashboard Cite

To date, the assessment of disability in older people is obtained utilizing a Comprehensive Geriatric Assessment (CGA). However, it is often difficult to understand which areas of CGA are most predictive of the disability. The aim of this study is to evaluate the possibility to early predictone year ahead-the disability level of a patient using Machine Leaning models. Methods Community-dwelling older people were enrolled in this study. CGA was made at baseline and at 1 year follow-up. After collecting input/independent variables (i.e. age, gender, schooling followed, Body Mass Index, information on smoking, polypharmacy, functional status, cognitive performance, depression, nutritional status), we performed two distinct Support Vector Machine models (SVMs) able to predict functional status one year ahead. In order to validate the choice of the model the results achieved with the SVMs were compared with the output produced by simple Linear Regression (LR) models. Results 218 patients (mean age =78.01; sd=7.85; Male= 39%) were recruited. The combination of the two SVMs is able to achieve a higher prediction accuracy (exceeding 80% instances correctly classified vs 67% instances correctly classified by the combination of the two linear regression models). Furthermore, SVMs are able to classify both the three categories, Self Sufficienty, Disability Risk and Disability, while linear regression model separates the population only in two groups (Self Sufficiency and Disability) without identifying the intermediate category (Disability Risk) which turns out to be the most critical one. Conclusions The development of such a model can contribute to the early detection of patients at risk of self-sufficiency loss.

show abstract

Section: Discussionsupporting

confidence: 84%

A new tool for the evaluation of the rehabilitation outcomes in older persons: a machine learning model to predict functional status 1 year ahead

Verrusio

Renzi

Dellepiane³

et al. 2018

Eur Geriatr Med

View full text Add to dashboard Cite

show abstract

“…Previous studies explored several EEG features for AD and MCI discrimination from HC, focusing on binary discrimination problems (AD vs. HC, MCI vs. HC and AD vs. MCI) [ 16 , 17 , 18 , 19 , 20 ]. To the best of our knowledge, only one study performed a three-way classification, although via binary classifiers [ 21 ].…”

Section: Discussionmentioning

confidence: 99%

Automated Multiclass Classification of Spontaneous EEG Activity in Alzheimer’s Disease and Mild Cognitive Impairment

Gómez

Poza

et al. 2018

Entropy

101

View full text Add to dashboard Cite

Abstract:The discrimination of early Alzheimer's disease (AD) and its prodromal form (i.e., mild cognitive impairment, MCI) from cognitively healthy control (HC) subjects is crucial since the treatment is more effective in the first stages of the dementia. The aim of our study is to evaluate the usefulness of a methodology based on electroencephalography (EEG) to detect AD and MCI. EEG rhythms were recorded from 37 AD patients, 37 MCI subjects and 37 HC subjects. Artifact-free trials were analyzed by means of several spectral and nonlinear features: relative power in the conventional frequency bands, median frequency, individual alpha frequency, spectral entropy, Lempel-Ziv complexity, central tendency measure, sample entropy, fuzzy entropy, and auto-mutual information. Relevance and redundancy analyses were also conducted through the fast correlation-based filter (FCBF) to derive an optimal set of them. The selected features were used to train three different models aimed at classifying the trials: linear discriminant analysis (LDA), quadratic discriminant analysis (QDA) and multi-layer perceptron artificial neural network (MLP). Afterwards, each subject was automatically allocated in a particular group by applying a trial-based majority vote procedure. After feature extraction, the FCBF method selected the optimal set of features: individual alpha frequency, relative power at delta frequency band, and sample entropy. Using the aforementioned set of features, MLP showed the highest diagnostic performance in determining whether a subject is not healthy (sensitivity of 82.35% and positive predictive value of 84.85% for HC vs. all classification task) and whether a subject does not suffer from AD (specificity of 79.41% and negative predictive value of 84.38% for AD vs. all comparison). Our findings suggest that our methodology can help physicians to discriminate AD, MCI and HC.

show abstract

“…This study had multiple positive aspects, including extensive clinical and neuropsychological profiling of participants, matched groups (for age, sex and education) and a good sample size relative to earlier studies (e.g. Ahmadlou, Adeli, & Adeli, 2010;Bertè, Lamponi, Calabrò, & Bramanti, 2014;Kashefpoor, Rabbani, Barekatain, 2016;McBride et al, 2015;Musaeus et al, 2018). Additionally, our MCI group included only participants with amnestic MCI sub-type, which is more closely linked with AD than non-amnestic MCI (Csukly et al, 2016).…”

Section: Discussionmentioning

confidence: 99%

A comparison of resting state EEG and structural MRI for classifying Alzheimer’s disease and mild cognitive impairment

Farina

Emek‐Savaş

Rueda‐Delgado

et al. 2019

Preprint

View full text Add to dashboard Cite

AbstractAlzheimer’s disease (AD) is a neurodegenerative disorder characterised by severe cognitive decline and loss of autonomy. AD is the leading cause of dementia. AD is preceded by mild cognitive impairment (MCI). By 2050, 68% of new dementia cases will occur in low- and middle-income countries. In the absence of objective biomarkers, psychological assessments are typically used to diagnose MCI and AD. However, these require specialist training and rely on subjective judgements. The need for low-cost, accessible and objective tools to aid AD and MCI diagnosis is therefore crucial. Electroencephalography (EEG) has potential as one such tool: it is relatively inexpensive (cf. magnetic resonance imaging; MRI) and is portable. In this study, we collected resting state EEG, structural MRI and rich neuropsychological data from older adults (55+ years) with AD, with MCI and from healthy controls (n~60 per group). Our goal was to evaluate the utility of EEG, relative to MRI, for the classification of MCI and AD. We also assessed the performance of combined EEG and behavioural (Mini-Mental State Examination; MMSE) and structural MRI classification models. Resting state EEG classified AD and HC participants with moderate accuracy (AROC=0.76), with lower accuracy when distinguishing MCI from HC participants (AROC=0.67). The addition of EEG data to MMSE scores had no additional value compared to MMSE alone. Structural MRI out-performed EEG (AD vs HC, AD vs MCI: AROCs=1.00; HC vs MCI: AROC=0.73). Resting state EEG does not appear to be a suitable tool for classifying AD. However, EEG classification accuracy was comparable to structural MRI when distinguishing MCI from healthy aging, although neither were sufficiently accurate to have clinical utility. This is the first direct comparison of EEG and MRI as classification tools in AD and MCI participants.

show abstract

Elman neural network for the early identification of cognitive impairment in Alzheimer�s disease

Cited by 12 publications

References 25 publications

A new tool for the evaluation of the rehabilitation outcomes in older persons: a machine learning model to predict functional status 1 year ahead

A new tool for the evaluation of the rehabilitation outcomes in older persons: a machine learning model to predict functional status 1 year ahead

Automated Multiclass Classification of Spontaneous EEG Activity in Alzheimer’s Disease and Mild Cognitive Impairment

A comparison of resting state EEG and structural MRI for classifying Alzheimer’s disease and mild cognitive impairment

Contact Info

Product

Resources

About