Depression diagnosis using machine intelligence based on spatiospectrotemporal analysis of multi-channel EEG.
Depression diagnosis is a challenging clinical task currently conducted mostly using subjective criteria. It is well known that depression alters the neural activity in the brain, so that the corresponding neurophysiological signature may be measured using non-invasive electroencephalography (EEG) s...
| Publicado en: | Medical & Biological Engineering & Computing Vol. 60; no. 11; pp. 3187 - 3203 |
|---|---|
| Autores principales: | , , |
| Formato: | Journal Article |
| Publicado: |
Springer Nature
Nov2022
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=159531214&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 159531214 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 01400118 PO0 jtl: Medical & Biological Engineering & Computing issn: 01400118 maglogo: N pubinfo: dt: Nov2022 vid: 60 iid: 11 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 159531214 159136962 159531214 NLM36115006 10.1007/s11517-022-02647-4 NLM36115006 159531214 ppf: 3187 ppct: 16 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Depression diagnosis using machine intelligence based on spatiospectrotemporal analysis of multi-channel EEG. aug: au: Nassibi, Amir Papavassiliou, Christos Atashzar, S. Farokh affil: Department of Electrical and Electronic Engineering, Imperial College London, London, UK sug: subj: Depression Diagnosis Electroencephalography Methods Algorithms Electrodes Scales ab: Depression diagnosis is a challenging clinical task currently conducted mostly using subjective criteria. It is well known that depression alters the neural activity in the brain, so that the corresponding neurophysiological signature may be measured using non-invasive electroencephalography (EEG) signals. These, in turn, may be possible to decode using machine learning algorithms. Despite the extensive literature, the existing techniques rely on several channels and obtrusive systems. In this paper, and for the first time, the diagnostic power of each EEG channel for depression detection is analyzed using Neighborhood Component Analysis (NCA). Our results indicate that a mere two features collected from one EEG channel suffice for reliable diagnosis. To evaluate the performance of the proposed method, a dataset comprising seven minutes of EEG recording from 84 subjects is used. The data was divided into two separate sets, one for feature selection and one for diagnostic classification. We delineate brain regions that have the strongest discriminative power linked to depression diagnosis. Thus, we identified one electrode (i.e., AF4) located on the frontal lobe, which can be used to diagnose depression with high accuracy. After evaluation of a series of shallow machine learning methods, we achieved the classification accuracy of 80.8%, sensitivity of 60% and specificity of 99.7% with two features from one electrode. We also achieved the highest classification accuracy of 91.8%, the specificity of 93.5%, and sensitivity of 90% with two electrodes and three features. Our findings show that it is possible to significantly reduce the complexity of algorithms to diagnose depression with the motivation of use in highly accessible wearable devices. pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|