Format

Send to

Choose Destination
Neural Comput. 2019 Sep;31(9):1751-1788. doi: 10.1162/neco_a_01196. Epub 2019 Jul 23.

Decoding Hidden Cognitive States From Behavior and Physiology Using a Bayesian Approach.

Author information

1
Department of Computer Science, Worcester Polytechnic Institute, 100 Institute Road, Worcester, MA 01609, U.S.A. ayousefi@wpi.edu.
2
Department of Psychiatry, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, U.S.A. ibasu@mgh.harvard.edu.
3
Department of Neurology, Massachusetts General Hospital, Boston, MA 02114, U.S.A. apaulk@mgh.harvard.edu.
4
Department of Radiology, MBGH/HST Martinos Center for Biomedical Imaging and Harvard Medical School, Boston, MA 02114, U.S.A. npeled@mgh.harvard.edu.
5
Department of Neurological Surgery, Albert Einstein College of Medicine, Bronx, NY 10461, U.S.A. emad.eskandar@einstein.yu.edu.
6
Department of Psychiatry, Massachusetts General Hospital and Harvard Medical School, Charlestown, MA 02129, U.S.A. ddougherty@partners.org.
7
Department of Neurology, Massachusetts General Hospital, Boston, MA 02114, U.S.A. scash@mgh.harvard.edu.
8
Department of Psychiatry, University of Minnesota, Minneapolis, MN 55454, U.S.A. awidge@umn.edu.
9
Department of Mathematics and Statistics, Boston University, Boston, MA 02215, U.S.A. tzvi@bu.edu.

Abstract

Cognitive processes, such as learning and cognitive flexibility, are both difficult to measure and to sample continuously using objective tools because cognitive processes arise from distributed, high-dimensional neural activity. For both research and clinical applications, that dimensionality must be reduced. To reduce dimensionality and measure underlying cognitive processes, we propose a modeling framework in which a cognitive process is defined as a low-dimensional dynamical latent variable-called a cognitive state, which links high-dimensional neural recordings and multidimensional behavioral readouts. This framework allows us to decompose the hard problem of modeling the relationship between neural and behavioral data into separable encoding-decoding approaches. We first use a state-space modeling framework, the behavioral decoder, to articulate the relationship between an objective behavioral readout (e.g., response times) and cognitive state. The second step, the neural encoder, involves using a generalized linear model (GLM) to identify the relationship between the cognitive state and neural signals, such as local field potential (LFP). We then use the neural encoder model and a Bayesian filter to estimate cognitive state using neural data (LFP power) to generate the neural decoder. We provide goodness-of-fit analysis and model selection criteria in support of the encoding-decoding result. We apply this framework to estimate an underlying cognitive state from neural data in human participants (N=8) performing a cognitive conflict task. We successfully estimated the cognitive state within the 95% confidence intervals of that estimated using behavior readout for an average of 90% of task trials across participants. In contrast to previous encoder-decoder models, our proposed modeling framework incorporates LFP spectral power to encode and decode a cognitive state. The framework allowed us to capture the temporal evolution of the underlying cognitive processes, which could be key to the development of closed-loop experiments and treatments.

PMID:
31335292
DOI:
10.1162/neco_a_01196

Supplemental Content

Full text links

Icon for Atypon
Loading ...
Support Center