A novel multi-modal machine learning based approach for automatic classification of EEG recordings in dementia

@article{Ieracitano2020ANM,
  title={A novel multi-modal machine learning based approach for automatic classification of EEG recordings in dementia},
  author={Cosimo Ieracitano and Nadia Mammone and Amir Hussain and Francesco Carlo Morabito},
  journal={Neural networks : the official journal of the International Neural Network Society},
  year={2020},
  volume={123},
  pages={
          176-190
        }
}
  • C. Ieracitano, N. Mammone, F. Morabito
  • Published 14 December 2019
  • Computer Science
  • Neural networks : the official journal of the International Neural Network Society
A Convolutional Neural Network based self-learning approach for classifying neurodegenerative states from EEG signals in dementia
TLDR
The proposed architecture, termed EEG-CNN, is shown to exhibit remarkable abilities to self-learn relevant features directly from the EEG traces, avoiding the need for hand-crafted feature extraction engineering.
Deep learning of resting-state electroencephalogram signals for three-class classification of Alzheimer’s disease, mild cognitive impairment and healthy ageing
TLDR
These results provide significant improvement for this classification task compared to previous studies in this field and suggest that DL could contribute to the diagnosis of AD from EEG recordings.
Depression Diagnosis Modeling With Advanced Computational Methods: Frequency-Domain eMVAR and Deep Learning
TLDR
A novel methodology for EEG-based depression diagnosis utilizing 2 advanced computational techniques: frequency-domain extended multivariate autoregressive (eMVAR) and deep learning (DL), which demonstrates that the DL methodology is a competitive alternative to the strong feature extraction-based ML methods in depression classification.
Diagnosis and prognosis of mental disorders by means of EEG and deep learning: a systematic mapping study
TLDR
Processing EEG with DL to detect mental disorders is a promising research field and to objectively compare performance between studies: public datasets, intra-subject validation, and standard metrics should be used.
Classification of normal and depressed EEG signals based on centered correntropy of rhythms in empirical wavelet transform domain
TLDR
A new method based on centered correntropy (CC) and empirical wavelet transform (EWT) for the classification of normal and depressed EEG signals can be used as a fast and accurate computer-aided detection system for the diagnosis of patients with depression in clinics and hospitals.
Identification of Major Psychiatric Disorders From Resting-State Electroencephalography Using a Machine Learning Approach
TLDR
It is suggested that ML in EEG may predict major psychiatric disorders and provide an objective index of psychiatric disorders.
...
...

References

SHOWING 1-10 OF 45 REFERENCES
A Time-Frequency based Machine Learning System for Brain States Classification via EEG Signal Processing
TLDR
Experimental results reported that the 1-hidden layer MLP (MLP1) outperformed all the other developed learning systems as well as recently proposed state-of-the-art methods, achieving accuracy rate up to 95.76 % ±0.0045 and 86.84% ± 0.0098 in AD vs HC and AD vs MCI classification, respectively.
Combining EEG signal processing with supervised methods for Alzheimer’s patients classification
TLDR
A procedure that exploits feature extraction and classification techniques to EEG signals is applied, whose aim is to distinguish patient affected by AD from the ones affected by Mild Cognitive Impairment and healthy control samples, and it is found that Wavelets analysis outperforms Fourier.
Automated Multiclass Classification of Spontaneous EEG Activity in Alzheimer’s Disease and Mild Cognitive Impairment
TLDR
The methodology can help physicians to discriminate AD, MCI and HC, and MLP showed the highest diagnostic performance in determining whether a subject is not healthy and whether asubject does not suffer from AD.
Extracting Salient Features for EEG-based Diagnosis of Alzheimer's Disease Using Support Vector Machine Classifier
TLDR
Different features for the diagnosis of AD are analyzed to serve as a possible biomarker to distinguish between AD subject and normal subject and increased performance in terms of sensitivity and specificity are shown.
Multiple feature extraction and classification of electroencephalograph signal for Alzheimers' with spectrum and bispectrum.
TLDR
Spectrum and bispectral analyses are proposed to extract multiple effective features of electroencephalograph (EEG) signals from Alzheimer's disease patients and further applied to distinguish AD patients from the normal controls and indicate that all these features could differentiate AD patients with a maximum accuracy of 90.2%.
Automatic Diagnosis of Mild Cognitive Impairment Using Electroencephalogram Spectral Features
TLDR
An accurate, mobile, and nonexpensive diagnostic approach based on electroencephalogram (EEG) signal is proposed to be used as an MCI diagnostic tool, especially for screening a large population.
Deep convolutional neural networks for classification of mild cognitive impaired and Alzheimer's disease patients from scalp EEG recordings
  • F. Morabito, M. Campolo, P. Bramanti
  • Computer Science
    2016 IEEE 2nd International Forum on Research and Technologies for Society and Industry Leveraging a better tomorrow (RTSI)
  • 2016
TLDR
The representational power of Deep Learning on Convolutional Neural Networks (CNN) is exploited to generate suitable sets of features that are then able to classify EEG patterns of AD from a prodromal version of dementia and from age-matched Healthy Controls.
...
...