SDA: a data-driven algorithm that detects functional states applied to the EEG of Guhyasamaja meditation

被引:1
|
作者
Mikhaylets, Ekaterina [1 ]
Razorenova, Alexandra M. [1 ,2 ]
Chernyshev, Vsevolod [1 ]
Syrov, Nikolay [3 ]
Yakovlev, Lev [3 ]
Boytsova, Julia [4 ]
Kokurina, Elena [4 ]
Zhironkina, Yulia [5 ]
Medvedev, Svyatoslav [4 ]
Kaplan, Alexander [3 ,6 ]
机构
[1] HSE Univ, Fac Comp Sci, Fac Econ Sci, Moscow, Russia
[2] Moscow State Univ Psychol & Educ, Ctr Neurocognit Res, MEG Ctr, Moscow, Russia
[3] Immanuel Kant Balt Fed Univ, Balt Ctr Neurotechnol & Artificial Intelligence, Kaliningrad, Russia
[4] Academician Natalya Bekhtereva Fdn, St Petersburg, Russia
[5] Save Tibet Fdn, Moscow, Russia
[6] Lomonosov Moscow State Univ, Lab Neurophysiol & Neurocomp Interfaces, Moscow, Russia
关键词
EEG; clustering; unsupervised data annotation; information value; meditation practice; Ward's method; functional states; change point detection; DYNAMICS;
D O I
10.3389/fninf.2023.1301718
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
The study presents a novel approach designed to detect time-continuous states in time-series data, called the State-Detecting Algorithm (SDA). The SDA operates on unlabeled data and detects optimal change-points among intrinsic functional states in time-series data based on an ensemble of Ward's hierarchical clustering with time-connectivity constraint. The algorithm chooses the best number of states and optimal state boundaries, maximizing clustering quality metrics. We also introduce a series of methods to estimate the performance and confidence of the SDA when the ground truth annotation is unavailable. These include information value analysis, paired statistical tests, and predictive modeling analysis. The SDA was validated on EEG recordings of Guhyasamaja meditation practice with a strict staged protocol performed by three experienced Buddhist practitioners in an ecological setup. The SDA used neurophysiological descriptors as inputs, including PSD, power indices, coherence, and PLV. Post-hoc analysis of the obtained EEG states revealed significant differences compared to the baseline and neighboring states. The SDA was found to be stable with respect to state order organization and showed poor clustering quality metrics and no statistical significance between states when applied to randomly shuffled epochs (i.e., surrogate subject data used as controls). The SDA can be considered a general data-driven approach that detects hidden functional states associated with the mental processes evolving during meditation or other ongoing mental and cognitive processes.
引用
收藏
页数:21
相关论文
共 50 条
  • [1] Data-driven unsupervised EEG clustering on tantric meditation data
    Mikhaylets, E.
    Razorenova, A.
    Chernyshev, V.
    Boytsova, J.
    Syrov, N.
    Yakovlev, L.
    Kokurina, E.
    Zhironkina, Y.
    Kaplan, A.
    Medvedev, S.
    INTERNATIONAL JOURNAL OF PSYCHOPHYSIOLOGY, 2023, 188 : 78 - 78
  • [2] Data-Driven Modeling of Sleep States from EEG
    Van Esbroeck, Alexander
    Westover, Brandon
    2012 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2012, : 5090 - 5093
  • [3] Identification of preseizure states in epilepsy: a data-driven approach for multichannel EEG recordings
    Feldwisch-Drentrup, Hinnerk
    Staniek, Matthaeus
    Schulze-Bonhage, Andreas
    Timmer, Jens
    Dickten, Henning
    Elger, Christian E.
    Schelter, Bjoern
    Lehnertz, Klaus
    FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2011, 5
  • [4] Data-driven visualization and group analysis of multichannel EEG coherence with functional units
    ten Caat, Michael
    Maurits, Natasha M.
    Roerdink, Jos B. T. M.
    IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2008, 14 (04) : 756 - 771
  • [5] DATA-DRIVEN FUSION OF EEG, FUNCTIONAL AND STRUCTURAL MRI: A COMPARISON OF TWO MODELS
    Levin-Schwartz, Yuri
    Calhoun, Vince D.
    Adali, Tuelay
    2014 48TH ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS (CISS), 2014,
  • [6] Data-Driven Algorithm Design
    Gupta, Rishi
    Roughgarden, Tim
    COMMUNICATIONS OF THE ACM, 2020, 63 (06) : 87 - 94
  • [7] A Data-Driven Accelerated Sampling Method for Searching Functional States of Proteins
    Zhu, Qiang
    Yuan, Yigao
    Ma, Jing
    Dong, Hao
    ADVANCED THEORY AND SIMULATIONS, 2019, 2 (04)
  • [8] Data-Driven Approach Detects, Classifies Screenout in Horizontal Wells
    Carpenter, Chris
    JPT, Journal of Petroleum Technology, 2022, 74 (05): : 85 - 87
  • [9] A federated data-driven evolutionary algorithm
    Xu, Jinjin
    Jin, Yaochu
    Du, Wenli
    Gu, Sai
    KNOWLEDGE-BASED SYSTEMS, 2021, 233 (233)
  • [10] An algorithm for data-driven bandwidth selection
    Comaniciu, D
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (02) : 281 - 288