Decoding naturalistic affective behaviour from spectro-spatial features in multiday human iEEG

Maryam Bijanzadeh, Ankit N. Khambhati, Maansi Desai, Deanna L. Wallace, Alia Shafi, Heather E. Dawes, Virginia E. Sturm and Edward F. Chang ()
Additional contact information
Maryam Bijanzadeh: University of California San Francisco
Ankit N. Khambhati: University of California San Francisco
Maansi Desai: University of Texas at Austin
Deanna L. Wallace: University of Texas at Austin
Alia Shafi: University of California San Francisco
Heather E. Dawes: University of California San Francisco
Virginia E. Sturm: University of California San Francisco
Edward F. Chang: University of California San Francisco

Nature Human Behaviour, 2022, vol. 6, issue 6, 823-836

Abstract: Abstract The neurological basis of affective behaviours in everyday life is not well understood. We obtained continuous intracranial electroencephalography recordings from the human mesolimbic network in 11 participants with epilepsy and hand-annotated spontaneous behaviours from 116 h of multiday video recordings. In individual participants, binary random forest models decoded affective behaviours from neutral behaviours with up to 93% accuracy. Both positive and negative affective behaviours were associated with increased high-frequency and decreased low-frequency activity across the mesolimbic network. The insula, amygdala, hippocampus and anterior cingulate cortex made stronger contributions to affective behaviours than the orbitofrontal cortex, but the insula and anterior cingulate cortex were most critical for differentiating behaviours with observable affect from those without. In a subset of participants (N = 3), multiclass decoders distinguished amongst the positive, negative and neutral behaviours. These results suggest that spectro-spatial features of brain activity in the mesolimbic network are associated with affective behaviours of everyday life.

Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41562-022-01310-0 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nathum:v:6:y:2022:i:6:d:10.1038_s41562-022-01310-0

Ordering information: This journal article can be ordered from
https://www.nature.com/nathumbehav/

DOI: 10.1038/s41562-022-01310-0

Access Statistics for this article

Nature Human Behaviour is currently edited by Stavroula Kousta

More articles in Nature Human Behaviour from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().