Dense attention network identifies EEG abnormalities during working memory performance of patients with schizophrenia
ID Perellón Alfonso, Ruben (Author), ID Oblak, Aleš (Author), ID Kuclar, Matija (Author), ID Škrlj, Blaž (Author), ID Škodlar, Borut (Author), ID Pregelj, Peter (Author), ID Repovš, Grega (Author), ID Bon, Jurij (Author)

.pdfPDF - Presentation file, Download (3,26 MB)
MD5: 4C376F9C3E79B8D8AD14DDD6F5CE1994
URLURL - Source URL, Visit https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1205119/full This link opens in a new window

Introduction: Patients with schizophrenia typically exhibit deficits in working memory (WM) associated with abnormalities in brain activity. Alterations in the encoding, maintenance and retrieval phases of sequential WM tasks are well established. However, due to the heterogeneity of symptoms and complexity of its neurophysiological underpinnings, differential diagnosis remains a challenge. We conducted an electroencephalographic (EEG) study during a visual WM task in fifteen schizophrenia patients and fifteen healthy controls. We hypothesized that EEG abnormalities during the task could be identified, and patients successfully classified by an interpretable machine learning algorithm. Methods: We tested a custom dense attention network (DAN) machine learning model to discriminate patients from control subjects and compared its performance with simpler and more commonly used machine learning models. Additionally, we analyzed behavioral performance, event-related EEG potentials, and time-frequency representations of the evoked responses to further characterize abnormalities in patients during WM. Results: The DAN model was significantly accurate in discriminating patients from healthy controls, ACC = 0.69, SD = 0.05. There were no significant differences between groups, conditions, or their interaction in behavioral performance or event-related potentials. However, patients showed significantly lower alpha suppression in the task preparation, memory encoding, maintenance, and retrieval phases F(1,28) = 5.93, p = 0.022, η2 = 0.149. Further analysis revealed that the two highest peaks in the attention value vector of the DAN model overlapped in time with the preparation and memory retrieval phases, as well as with two of the four significant time-frequency ROIs. Discussion: These results highlight the potential utility of interpretable machine learning algorithms as an aid in diagnosis of schizophrenia and other psychiatric disorders presenting oscillatory abnormalities.

Keywords:schizophrenia, working memory, contralateral delay negativity, electroencephalography EEG, dense attention network DAN
Work type:Article
Typology:1.01 - Original Scientific Article
Organization:FF - Faculty of Arts
MF - Faculty of Medicine
Publication status:Published
Publication version:Version of Record
Number of pages:12 str.
Numbering:Vol. 14, art. 1205119
PID:20.500.12556/RUL-153575 This link opens in a new window
ISSN on article:1664-0640
DOI:10.3389/fpsyt.2023.1205119 This link opens in a new window
COBISS.SI-ID:166182915 This link opens in a new window
Publication date in RUL:16.01.2024
Copy citation
Share:Bookmark and Share

Record is a part of a journal

Title:Frontiers in psychiatry
Shortened title:Front. psychiatry
Publisher:Frontiers Research Foundation
COBISS.SI-ID:54153314 This link opens in a new window


License:CC BY 4.0, Creative Commons Attribution 4.0 International
Description:This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

Keywords:shizofrenija, delovni spomin, elektroencefalografija EEG, kontralateralna negativnost, gosto pozornostno omrežje


Funder:Other - Other funder or multiple funders
Funding programme:"la Caixa” Foundation
Project number:100010434, LCF/BQ/DI19/11730050
Name:“la Caixa” Foundation

Funder:Other - Other funder or multiple funders
Funding programme:Spanish Ministry of Science and Innovation
Project number:FJC2021-047380- I
Name:Juan de la Cierva-Formacion research grant

Funder:Other - Other funder or multiple funders
Funding programme:"la Caixa” Foundation
Project number:100010434, LCF/BQ/DI18/11660026
Name:“la Caixa” Foundation

Funder:Other - Other funder or multiple funders
Funding programme:European Union’s Horizon 2020
Project number:713673
Name:Marie Skłodowska-Curie grant

Funder:ARRS - Slovenian Research Agency
Project number:P5-0110
Name:Psihološki in nevroznanstveni vidiki kognicije

Funder:ARRS - Slovenian Research Agency
Project number:P3-0338
Name:Fiziološki mehanizmi nevroloških motenj in bolezni

Funder:ARRS - Slovenian Research Agency
Project number:J3-1763
Name:Vpliv individualizacije stimulacijske frekvence v realnem času na učinkovitost zdravljenja depresije s transkranialno magnetno stimulacijo

Funder:ARRS - Slovenian Research Agency
Project number:J3-9264
Name:Razstavljanje kognicije: Mehanizmi in reprezentacije delovnega spomina

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections: