1
|
Ahmadipour P, Sani OG, Pesaran B, Shanechi MM. Multimodal subspace identification for modeling discrete-continuous spiking and field potential population activity. J Neural Eng 2024; 21:026001. [PMID: 38016450 PMCID: PMC10913727 DOI: 10.1088/1741-2552/ad1053] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Revised: 10/23/2023] [Accepted: 11/28/2023] [Indexed: 11/30/2023]
Abstract
Objective.Learning dynamical latent state models for multimodal spiking and field potential activity can reveal their collective low-dimensional dynamics and enable better decoding of behavior through multimodal fusion. Toward this goal, developing unsupervised learning methods that are computationally efficient is important, especially for real-time learning applications such as brain-machine interfaces (BMIs). However, efficient learning remains elusive for multimodal spike-field data due to their heterogeneous discrete-continuous distributions and different timescales.Approach.Here, we develop a multiscale subspace identification (multiscale SID) algorithm that enables computationally efficient learning for modeling and dimensionality reduction for multimodal discrete-continuous spike-field data. We describe the spike-field activity as combined Poisson and Gaussian observations, for which we derive a new analytical SID method. Importantly, we also introduce a novel constrained optimization approach to learn valid noise statistics, which is critical for multimodal statistical inference of the latent state, neural activity, and behavior. We validate the method using numerical simulations and with spiking and local field potential population activity recorded during a naturalistic reach and grasp behavior.Main results.We find that multiscale SID accurately learned dynamical models of spike-field signals and extracted low-dimensional dynamics from these multimodal signals. Further, it fused multimodal information, thus better identifying the dynamical modes and predicting behavior compared to using a single modality. Finally, compared to existing multiscale expectation-maximization learning for Poisson-Gaussian observations, multiscale SID had a much lower training time while being better in identifying the dynamical modes and having a better or similar accuracy in predicting neural activity and behavior.Significance.Overall, multiscale SID is an accurate learning method that is particularly beneficial when efficient learning is of interest, such as for online adaptive BMIs to track non-stationary dynamics or for reducing offline training time in neuroscience investigations.
Collapse
Affiliation(s)
- Parima Ahmadipour
- Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America
| | - Omid G Sani
- Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America
| | - Bijan Pesaran
- Department of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States of America
| | - Maryam M Shanechi
- Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America
- Thomas Lord Department of Computer Science, Alfred E. Mann Department of Biomedical Engineering, and the Neuroscience Graduate Program, University of Southern California, Los Angeles, CA, United States of America
| |
Collapse
|
2
|
Sadras N, Sani OG, Ahmadipour P, Shanechi MM. Post-stimulus encoding of decision confidence in EEG: toward a brain-computer interface for decision making. J Neural Eng 2023; 20:056012. [PMID: 37524073 DOI: 10.1088/1741-2552/acec14] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/21/2022] [Accepted: 07/31/2023] [Indexed: 08/02/2023]
Abstract
Objective.When making decisions, humans can evaluate how likely they are to be correct. If this subjective confidence could be reliably decoded from brain activity, it would be possible to build a brain-computer interface (BCI) that improves decision performance by automatically providing more information to the user if needed based on their confidence. But this possibility depends on whether confidence can be decoded right after stimulus presentation and before the response so that a corrective action can be taken in time. Although prior work has shown that decision confidence is represented in brain signals, it is unclear if the representation is stimulus-locked or response-locked, and whether stimulus-locked pre-response decoding is sufficiently accurate for enabling such a BCI.Approach.We investigate the neural correlates of confidence by collecting high-density electroencephalography (EEG) during a perceptual decision task with realistic stimuli. Importantly, we design our task to include a post-stimulus gap that prevents the confounding of stimulus-locked activity by response-locked activity and vice versa, and then compare with a task without this gap.Main results.We perform event-related potential and source-localization analyses. Our analyses suggest that the neural correlates of confidence are stimulus-locked, and that an absence of a post-stimulus gap could cause these correlates to incorrectly appear as response-locked. By preventing response-locked activity from confounding stimulus-locked activity, we then show that confidence can be reliably decoded from single-trial stimulus-locked pre-response EEG alone. We also identify a high-performance classification algorithm by comparing a battery of algorithms. Lastly, we design a simulated BCI framework to show that the EEG classification is accurate enough to build a BCI and that the decoded confidence could be used to improve decision making performance particularly when the task difficulty and cost of errors are high.Significance.Our results show feasibility of non-invasive EEG-based BCIs to improve human decision making.
Collapse
Affiliation(s)
- Nitin Sadras
- Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America
| | - Omid G Sani
- Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America
| | - Parima Ahmadipour
- Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America
| | - Maryam M Shanechi
- Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America
- Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America
- Department of Computer Science, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America
- Neuroscience Graduate Program University of Southern California, Los Angeles, CA, United States of America
| |
Collapse
|
3
|
Shirvalkar P, Prosky J, Chin G, Ahmadipour P, Sani OG, Desai M, Schmitgen A, Dawes H, Shanechi MM, Starr PA, Chang EF. First-in-human prediction of chronic pain state using intracranial neural biomarkers. Nat Neurosci 2023; 26:1090-1099. [PMID: 37217725 PMCID: PMC10330878 DOI: 10.1038/s41593-023-01338-z] [Citation(s) in RCA: 12] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2021] [Accepted: 04/18/2023] [Indexed: 05/24/2023]
Abstract
Chronic pain syndromes are often refractory to treatment and cause substantial suffering and disability. Pain severity is often measured through subjective report, while objective biomarkers that may guide diagnosis and treatment are lacking. Also, which brain activity underlies chronic pain on clinically relevant timescales, or how this relates to acute pain, remains unclear. Here four individuals with refractory neuropathic pain were implanted with chronic intracranial electrodes in the anterior cingulate cortex and orbitofrontal cortex (OFC). Participants reported pain metrics coincident with ambulatory, direct neural recordings obtained multiple times daily over months. We successfully predicted intraindividual chronic pain severity scores from neural activity with high sensitivity using machine learning methods. Chronic pain decoding relied on sustained power changes from the OFC, which tended to differ from transient patterns of activity associated with acute, evoked pain states during a task. Thus, intracranial OFC signals can be used to predict spontaneous, chronic pain state in patients.
Collapse
Affiliation(s)
- Prasad Shirvalkar
- UCSF Department of Anesthesiology and Perioperative Care, Division of Pain Medicine, University of California San Francisco, San Francisco, CA, USA.
- UCSF Department of Neurology, University of California San Francisco, San Francisco, CA, USA.
- UCSF Department of Neurological Surgery, University of California San Francisco, San Francisco, CA, USA.
- UCSF Weill Institute for Neurosciences, University of California San Francisco, San Francisco, CA, USA.
| | - Jordan Prosky
- UCSF Department of Neurological Surgery, University of California San Francisco, San Francisco, CA, USA
- UCSF Weill Institute for Neurosciences, University of California San Francisco, San Francisco, CA, USA
| | - Gregory Chin
- UCSF Department of Neurological Surgery, University of California San Francisco, San Francisco, CA, USA
| | - Parima Ahmadipour
- Departments of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA
| | - Omid G Sani
- Departments of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA
| | - Maansi Desai
- Department of Speech, Language, and Hearing Sciences, The University of Texas at Austin, Austin, TX, USA
| | - Ashlyn Schmitgen
- UCSF Department of Neurological Surgery, University of California San Francisco, San Francisco, CA, USA
- UCSF Weill Institute for Neurosciences, University of California San Francisco, San Francisco, CA, USA
| | - Heather Dawes
- UCSF Department of Neurological Surgery, University of California San Francisco, San Francisco, CA, USA
- UCSF Weill Institute for Neurosciences, University of California San Francisco, San Francisco, CA, USA
| | - Maryam M Shanechi
- Departments of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA
| | - Philip A Starr
- UCSF Department of Neurological Surgery, University of California San Francisco, San Francisco, CA, USA
- UCSF Weill Institute for Neurosciences, University of California San Francisco, San Francisco, CA, USA
- UCSF Department of Physiology, University of California San Francisco, San Francisco, CA, USA
| | - Edward F Chang
- UCSF Department of Neurological Surgery, University of California San Francisco, San Francisco, CA, USA
- UCSF Weill Institute for Neurosciences, University of California San Francisco, San Francisco, CA, USA
- UCSF Department of Physiology, University of California San Francisco, San Francisco, CA, USA
| |
Collapse
|
4
|
Ahmadipour P, Sani OG, Pesaran B, Shanechi MM. Multimodal subspace identification for modeling discrete-continuous spiking and field potential population activity. bioRxiv 2023:2023.05.26.542509. [PMID: 37398400 PMCID: PMC10312539 DOI: 10.1101/2023.05.26.542509] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/04/2023]
Abstract
Learning dynamical latent state models for multimodal spiking and field potential activity can reveal their collective low-dimensional dynamics and enable better decoding of behavior through multimodal fusion. Toward this goal, developing unsupervised learning methods that are computationally efficient is important, especially for real-time learning applications such as brain-machine interfaces (BMIs). However, efficient learning remains elusive for multimodal spike-field data due to their heterogeneous discrete-continuous distributions and different timescales. Here, we develop a multiscale subspace identification (multiscale SID) algorithm that enables computationally efficient modeling and dimensionality reduction for multimodal discrete-continuous spike-field data. We describe the spike-field activity as combined Poisson and Gaussian observations, for which we derive a new analytical subspace identification method. Importantly, we also introduce a novel constrained optimization approach to learn valid noise statistics, which is critical for multimodal statistical inference of the latent state, neural activity, and behavior. We validate the method using numerical simulations and spike-LFP population activity recorded during a naturalistic reach and grasp behavior. We find that multiscale SID accurately learned dynamical models of spike-field signals and extracted low-dimensional dynamics from these multimodal signals. Further, it fused multimodal information, thus better identifying the dynamical modes and predicting behavior compared to using a single modality. Finally, compared to existing multiscale expectation-maximization learning for Poisson-Gaussian observations, multiscale SID had a much lower computational cost while being better in identifying the dynamical modes and having a better or similar accuracy in predicting neural activity. Overall, multiscale SID is an accurate learning method that is particularly beneficial when efficient learning is of interest.
Collapse
|
5
|
Yang Y, Ahmadipour P, Shanechi MM. Adaptive latent state modeling of brain network dynamics with real-time learning rate optimization. J Neural Eng 2021; 18. [PMID: 33254159 DOI: 10.1088/1741-2552/abcefd] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2020] [Accepted: 11/30/2020] [Indexed: 12/29/2022]
Abstract
Objective. Dynamic latent state models are widely used to characterize the dynamics of brain network activity for various neural signal types. To date, dynamic latent state models have largely been developed for stationary brain network dynamics. However, brain network dynamics can be non-stationary for example due to learning, plasticity or recording instability. To enable modeling these non-stationarities, two problems need to be resolved. First, novel methods should be developed that can adaptively update the parameters of latent state models, which is difficult due to the state being latent. Second, new methods are needed to optimize the adaptation learning rate, which specifies how fast new neural observations update the model parameters and can significantly influence adaptation accuracy.Approach. We develop a Rate Optimized-adaptive Linear State-Space Modeling (RO-adaptive LSSM) algorithm that solves these two problems. First, to enable adaptation, we derive a computation- and memory-efficient adaptive LSSM fitting algorithm that updates the LSSM parameters recursively and in real time in the presence of the latent state. Second, we develop a real-time learning rate optimization algorithm. We use comprehensive simulations of a broad range of non-stationary brain network dynamics to validate both algorithms, which together constitute the RO-adaptive LSSM.Main results. We show that the adaptive LSSM fitting algorithm can accurately track the broad simulated non-stationary brain network dynamics. We also find that the learning rate significantly affects the LSSM fitting accuracy. Finally, we show that the real-time learning rate optimization algorithm can run in parallel with the adaptive LSSM fitting algorithm. Doing so, the combined RO-adaptive LSSM algorithm rapidly converges to the optimal learning rate and accurately tracks non-stationarities.Significance. These algorithms can be used to study time-varying neural dynamics underlying various brain functions and enhance future neurotechnologies such as brain-machine interfaces and closed-loop brain stimulation systems.
Collapse
Affiliation(s)
- Yuxiao Yang
- Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America.,These authors contributed equally to this work
| | - Parima Ahmadipour
- Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America.,These authors contributed equally to this work
| | - Maryam M Shanechi
- Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America.,Neuroscience Graduate Program, University of Southern California, Los Angeles, CA, United States of America
| |
Collapse
|
6
|
Abstract
OBJECTIVE Extracting and modeling the low-dimensional dynamics of multi-site electrocorticogram (ECoG) network activity is important in studying brain functions and dysfunctions and for developing translational neurotechnologies. Dynamic latent state models can be used to describe the ECoG network dynamics with low-dimensional latent states. But so far, non-stationarity of ECoG network dynamics has largely not been addressed in these latent state models. Such non-stationarity can happen due to a change in brain state or recording instability over time. A critical question is whether adaptive tracking of ECoG network dynamics can lead to further dimensionality reduction and more parsimonious and precise modeling. This question is largely unaddressed. APPROACH We investigate this question by employing an adaptive linear state-space model for ECoG network activity constructed from ECoG power feature time-series over tens of hours from 10 human subjects with epilepsy. We study how adaptive modeling affects the prediction and dimensionality reduction for ECoG network dynamics compared with prior non-adaptive models, which do not track non-stationarity. MAIN RESULTS Across the 10 subjects, adaptive modeling significantly improved the prediction of ECoG network dynamics compared with non-adaptive modeling, especially for lower latent state dimensions. Also, compared with non-adaptive modeling, adaptive modeling allowed for additional dimensionality reduction without degrading prediction performance. Finally, these results suggested that ECoG network dynamics over our recording periods exhibit non-stationarity, which can be tracked with adaptive modeling. SIGNIFICANCE These results have important implications for studying low-dimensional neural representations using ECoG, and for developing future adaptive neurotechnologies for more precise decoding and modulation of brain states in neurological and neuropsychiatric disorders.
Collapse
Affiliation(s)
- Parima Ahmadipour
- Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States of America. Equal contribution
| | | | | | | |
Collapse
|