1
|
Li Y, Frederick RA, George D, Cogan SF, Pancrazio JJ, Bleris L, Hernandez-Reynoso AG. NeurostimML: a machine learning model for predicting neurostimulation-induced tissue damage. J Neural Eng 2024; 21:036054. [PMID: 38885676 DOI: 10.1088/1741-2552/ad593e] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2023] [Accepted: 06/17/2024] [Indexed: 06/20/2024]
Abstract
Objective. The safe delivery of electrical current to neural tissue depends on many factors, yet previous methods for predicting tissue damage rely on only a few stimulation parameters. Here, we report the development of a machine learning approach that could lead to a more reliable method for predicting electrical stimulation-induced tissue damage by incorporating additional stimulation parameters.Approach. A literature search was conducted to build an initial database of tissue response information after electrical stimulation, categorized as either damaging or non-damaging. Subsequently, we used ordinal encoding and random forest for feature selection, and investigated four machine learning models for classification: Logistic Regression, K-nearest Neighbor, Random Forest, and Multilayer Perceptron. Finally, we compared the results of these models against the accuracy of the Shannon equation.Main Results. We compiled a database with 387 unique stimulation parameter combinations collected from 58 independent studies conducted over a period of 47 years, with 195 (51%) categorized as non-damaging and 190 (49%) categorized as damaging. The features selected for building our model with a Random Forest algorithm were: waveform shape, geometric surface area, pulse width, frequency, pulse amplitude, charge per phase, charge density, current density, duty cycle, daily stimulation duration, daily number of pulses delivered, and daily accumulated charge. The Shannon equation yielded an accuracy of 63.9% using akvalue of 1.79. In contrast, the Random Forest algorithm was able to robustly predict whether a set of stimulation parameters was classified as damaging or non-damaging with an accuracy of 88.3%.Significance. This novel Random Forest model can facilitate more informed decision making in the selection of neuromodulation parameters for both research studies and clinical practice. This study represents the first approach to use machine learning in the prediction of stimulation-induced neural tissue damage, and lays the groundwork for neurostimulation driven by machine learning models.
Collapse
Affiliation(s)
- Yi Li
- Department of Bioengineering, The University of Texas at Dallas, Richardson, TX, United States of America
- Center for Systems Biology, The University of Texas at Dallas, Richardson, TX, United States of America
| | - Rebecca A Frederick
- Phil and Penny Knight Campus for Accelerating Scientific Impact, University of Oregon, Eugene, OR, United States of America
| | - Daniel George
- Department of Computer Science, The University of Texas at Dallas, Richardson, TX, United States of America
| | - Stuart F Cogan
- Department of Bioengineering, The University of Texas at Dallas, Richardson, TX, United States of America
| | - Joseph J Pancrazio
- Department of Bioengineering, The University of Texas at Dallas, Richardson, TX, United States of America
| | - Leonidas Bleris
- Department of Bioengineering, The University of Texas at Dallas, Richardson, TX, United States of America
- Center for Systems Biology, The University of Texas at Dallas, Richardson, TX, United States of America
- Department of Biological Sciences, The University of Texas at Dallas, Richardson, TX, United States of America
| | - Ana G Hernandez-Reynoso
- Department of Bioengineering, The University of Texas at Dallas, Richardson, TX, United States of America
| |
Collapse
|
2
|
Fortunato C, Bennasar-Vázquez J, Park J, Chang JC, Miller LE, Dudman JT, Perich MG, Gallego JA. Nonlinear manifolds underlie neural population activity during behaviour. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2023.07.18.549575. [PMID: 37503015 PMCID: PMC10370078 DOI: 10.1101/2023.07.18.549575] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/29/2023]
Abstract
There is rich variety in the activity of single neurons recorded during behaviour. Yet, these diverse single neuron responses can be well described by relatively few patterns of neural co-modulation. The study of such low-dimensional structure of neural population activity has provided important insights into how the brain generates behaviour. Virtually all of these studies have used linear dimensionality reduction techniques to estimate these population-wide co-modulation patterns, constraining them to a flat "neural manifold". Here, we hypothesised that since neurons have nonlinear responses and make thousands of distributed and recurrent connections that likely amplify such nonlinearities, neural manifolds should be intrinsically nonlinear. Combining neural population recordings from monkey, mouse, and human motor cortex, and mouse striatum, we show that: 1) neural manifolds are intrinsically nonlinear; 2) their nonlinearity becomes more evident during complex tasks that require more varied activity patterns; and 3) manifold nonlinearity varies across architecturally distinct brain regions. Simulations using recurrent neural network models confirmed the proposed relationship between circuit connectivity and manifold nonlinearity, including the differences across architecturally distinct regions. Thus, neural manifolds underlying the generation of behaviour are inherently nonlinear, and properly accounting for such nonlinearities will be critical as neuroscientists move towards studying numerous brain regions involved in increasingly complex and naturalistic behaviours.
Collapse
Affiliation(s)
- Cátia Fortunato
- Department of Bioengineering, Imperial College London, London UK
| | | | - Junchol Park
- Janelia Research Campus, Howard Hughes Medical Institute, Ashburn VA, USA
| | - Joanna C. Chang
- Department of Bioengineering, Imperial College London, London UK
| | - Lee E. Miller
- Department of Neurosciences, Northwestern University, Chicago IL, USA
- Department of Biomedical Engineering, Northwestern University, Chicago IL, USA
- Department of Physical Medicine and Rehabilitation, Northwestern University, Chicago IL, USA, and Shirley Ryan Ability Lab, Chicago, IL, USA
| | - Joshua T. Dudman
- Janelia Research Campus, Howard Hughes Medical Institute, Ashburn VA, USA
| | - Matthew G. Perich
- Department of Neurosciences, Faculté de médecine, Université de Montréal, Montréal, Québec, Canada
- Québec Artificial Intelligence Institute (MILA), Montréal, Québec, Canada
| | - Juan A. Gallego
- Department of Bioengineering, Imperial College London, London UK
| |
Collapse
|
3
|
Talpir I, Livneh Y. Stereotyped goal-directed manifold dynamics in the insular cortex. Cell Rep 2024; 43:114027. [PMID: 38568813 PMCID: PMC11063631 DOI: 10.1016/j.celrep.2024.114027] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2023] [Revised: 02/12/2024] [Accepted: 03/15/2024] [Indexed: 04/05/2024] Open
Abstract
The insular cortex is involved in diverse processes, including bodily homeostasis, emotions, and cognition. However, we lack a comprehensive understanding of how it processes information at the level of neuronal populations. We leveraged recent advances in unsupervised machine learning to study insular cortex population activity patterns (i.e., neuronal manifold) in mice performing goal-directed behaviors. We find that the insular cortex activity manifold is remarkably consistent across different animals and under different motivational states. Activity dynamics within the neuronal manifold are highly stereotyped during rewarded trials, enabling robust prediction of single-trial outcomes across different mice and across various natural and artificial motivational states. Comparing goal-directed behavior with self-paced free consumption, we find that the stereotyped activity patterns reflect task-dependent goal-directed reward anticipation, and not licking, taste, or positive valence. These findings reveal a core computation in insular cortex that could explain its involvement in pathologies involving aberrant motivations.
Collapse
Affiliation(s)
- Itay Talpir
- Department of Brain Sciences, Weizmann Institute of Science, Rehovot 76100, Israel
| | - Yoav Livneh
- Department of Brain Sciences, Weizmann Institute of Science, Rehovot 76100, Israel.
| |
Collapse
|
4
|
Osuna-Orozco R, Zhao Y, Stealey HM, Lu HY, Contreras-Hernandez E, Santacruz SR. Adaptation and learning as strategies to maximize reward in neurofeedback tasks. Front Hum Neurosci 2024; 18:1368115. [PMID: 38590363 PMCID: PMC11000125 DOI: 10.3389/fnhum.2024.1368115] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2024] [Accepted: 03/04/2024] [Indexed: 04/10/2024] Open
Abstract
Introduction Adaptation and learning have been observed to contribute to the acquisition of new motor skills and are used as strategies to cope with changing environments. However, it is hard to determine the relative contribution of each when executing goal directed motor tasks. This study explores the dynamics of neural activity during a center-out reaching task with continuous visual feedback under the influence of rotational perturbations. Methods Results for a brain-computer interface (BCI) task performed by two non-human primate (NHP) subjects are compared to simulations from a reinforcement learning agent performing an analogous task. We characterized baseline activity and compared it to the activity after rotational perturbations of different magnitudes were introduced. We employed principal component analysis (PCA) to analyze the spiking activity driving the cursor in the NHP BCI task as well as the activation of the neural network of the reinforcement learning agent. Results and discussion Our analyses reveal that both for the NHPs and the reinforcement learning agent, the task-relevant neural manifold is isomorphic with the task. However, for the NHPs the manifold is largely preserved for all rotational perturbations explored and adaptation of neural activity occurs within this manifold as rotations are compensated by reassignment of regions of the neural space in an angular pattern that cancels said rotations. In contrast, retraining the reinforcement learning agent to reach the targets after rotation results in substantial modifications of the underlying neural manifold. Our findings demonstrate that NHPs adapt their existing neural dynamic repertoire in a quantitatively precise manner to account for perturbations of different magnitudes and they do so in a way that obviates the need for extensive learning.
Collapse
Affiliation(s)
- Rodrigo Osuna-Orozco
- Department of Biomedical Engineering, University of Texas at Austin, Austin, TX, United States
| | - Yi Zhao
- Department of Biomedical Engineering, University of Texas at Austin, Austin, TX, United States
| | - Hannah Marie Stealey
- Department of Biomedical Engineering, University of Texas at Austin, Austin, TX, United States
| | - Hung-Yun Lu
- Department of Biomedical Engineering, University of Texas at Austin, Austin, TX, United States
| | | | - Samantha Rose Santacruz
- Department of Biomedical Engineering, University of Texas at Austin, Austin, TX, United States
- Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, United States
- Institute for Neuroscience, University of Texas at Austin, Austin, TX, United States
| |
Collapse
|
5
|
Noda T, Aschauer DF, Chambers AR, Seiler JPH, Rumpel S. Representational maps in the brain: concepts, approaches, and applications. Front Cell Neurosci 2024; 18:1366200. [PMID: 38584779 PMCID: PMC10995314 DOI: 10.3389/fncel.2024.1366200] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/05/2024] [Accepted: 03/08/2024] [Indexed: 04/09/2024] Open
Abstract
Neural systems have evolved to process sensory stimuli in a way that allows for efficient and adaptive behavior in a complex environment. Recent technological advances enable us to investigate sensory processing in animal models by simultaneously recording the activity of large populations of neurons with single-cell resolution, yielding high-dimensional datasets. In this review, we discuss concepts and approaches for assessing the population-level representation of sensory stimuli in the form of a representational map. In such a map, not only are the identities of stimuli distinctly represented, but their relational similarity is also mapped onto the space of neuronal activity. We highlight example studies in which the structure of representational maps in the brain are estimated from recordings in humans as well as animals and compare their methodological approaches. Finally, we integrate these aspects and provide an outlook for how the concept of representational maps could be applied to various fields in basic and clinical neuroscience.
Collapse
Affiliation(s)
- Takahiro Noda
- Institute of Physiology, Focus Program Translational Neurosciences, University Medical Center, Johannes Gutenberg University-Mainz, Mainz, Germany
| | - Dominik F. Aschauer
- Institute of Physiology, Focus Program Translational Neurosciences, University Medical Center, Johannes Gutenberg University-Mainz, Mainz, Germany
| | - Anna R. Chambers
- Department of Otolaryngology – Head and Neck Surgery, Harvard Medical School, Boston, MA, United States
- Eaton Peabody Laboratories, Massachusetts Eye and Ear Infirmary, Boston, MA, United States
| | - Johannes P.-H. Seiler
- Institute of Physiology, Focus Program Translational Neurosciences, University Medical Center, Johannes Gutenberg University-Mainz, Mainz, Germany
| | - Simon Rumpel
- Institute of Physiology, Focus Program Translational Neurosciences, University Medical Center, Johannes Gutenberg University-Mainz, Mainz, Germany
| |
Collapse
|
6
|
Esparza J, Sebastián ER, de la Prida LM. From cell types to population dynamics: Making hippocampal manifolds physiologically interpretable. Curr Opin Neurobiol 2023; 83:102800. [PMID: 37898015 DOI: 10.1016/j.conb.2023.102800] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2023] [Revised: 09/27/2023] [Accepted: 09/28/2023] [Indexed: 10/30/2023]
Abstract
The study of the hippocampal code is gaining momentum. While the physiological approach targets the contribution of individual cells as determined by genetic, biophysical and circuit factors, the field pushes for a population dynamic approach that considers the representation of behavioural variables by a large number of neurons. In this alternative framework, neuronal activity is projected into low-dimensional manifolds. These manifolds can reveal the structure of population representations, but their physiological interpretation is challenging. Here, we review the recent literature and propose that integrating information regarding behavioral traits, local field potential oscillations and cell-type-specificity into neural manifolds offers strategies to make them interpretable at the physiological level.
Collapse
|
7
|
Woodman RJ, Mangoni AA. A comprehensive review of machine learning algorithms and their application in geriatric medicine: present and future. Aging Clin Exp Res 2023; 35:2363-2397. [PMID: 37682491 PMCID: PMC10627901 DOI: 10.1007/s40520-023-02552-2] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2023] [Accepted: 08/24/2023] [Indexed: 09/09/2023]
Abstract
The increasing access to health data worldwide is driving a resurgence in machine learning research, including data-hungry deep learning algorithms. More computationally efficient algorithms now offer unique opportunities to enhance diagnosis, risk stratification, and individualised approaches to patient management. Such opportunities are particularly relevant for the management of older patients, a group that is characterised by complex multimorbidity patterns and significant interindividual variability in homeostatic capacity, organ function, and response to treatment. Clinical tools that utilise machine learning algorithms to determine the optimal choice of treatment are slowly gaining the necessary approval from governing bodies and being implemented into healthcare, with significant implications for virtually all medical disciplines during the next phase of digital medicine. Beyond obtaining regulatory approval, a crucial element in implementing these tools is the trust and support of the people that use them. In this context, an increased understanding by clinicians of artificial intelligence and machine learning algorithms provides an appreciation of the possible benefits, risks, and uncertainties, and improves the chances for successful adoption. This review provides a broad taxonomy of machine learning algorithms, followed by a more detailed description of each algorithm class, their purpose and capabilities, and examples of their applications, particularly in geriatric medicine. Additional focus is given on the clinical implications and challenges involved in relying on devices with reduced interpretability and the progress made in counteracting the latter via the development of explainable machine learning.
Collapse
Affiliation(s)
- Richard J Woodman
- Centre of Epidemiology and Biostatistics, College of Medicine and Public Health, Flinders University, GPO Box 2100, Adelaide, SA, 5001, Australia.
| | - Arduino A Mangoni
- Discipline of Clinical Pharmacology, College of Medicine and Public Health, Flinders University, Adelaide, SA, Australia
- Department of Clinical Pharmacology, Flinders Medical Centre, Southern Adelaide Local Health Network, Adelaide, SA, Australia
| |
Collapse
|
8
|
Li Y, Frederick RA, George D, Cogan SF, Pancrazio JJ, Bleris L, Hernandez-Reynoso AG. NeurostimML: A machine learning model for predicting neurostimulation-induced tissue damage. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.10.18.562980. [PMID: 37905012 PMCID: PMC10614958 DOI: 10.1101/2023.10.18.562980] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/02/2023]
Abstract
Objective The safe delivery of electrical current to neural tissue depends on many factors, yet previous methods for predicting tissue damage rely on only a few stimulation parameters. Here, we report the development of a machine learning approach that could lead to a more reliable method for predicting electrical stimulation-induced tissue damage by incorporating additional stimulation parameters. Approach A literature search was conducted to build an initial database of tissue response information after electrical stimulation, categorized as either damaging or non-damaging. Subsequently, we used ordinal encoding and random forest for feature selection, and investigated four machine learning models for classification: Logistic Regression, K-nearest Neighbor, Random Forest, and Multilayer Perceptron. Finally, we compared the results of these models against the accuracy of the Shannon equation. Main Results We compiled a database with 387 unique stimulation parameter combinations collected from 58 independent studies conducted over a period of 47 years, with 195 (51%) categorized as non-damaging and 190 (49%) categorized as damaging. The features selected for building our model with a Random Forest algorithm were: waveform shape, geometric surface area, pulse width, frequency, pulse amplitude, charge per phase, charge density, current density, duty cycle, daily stimulation duration, daily number of pulses delivered, and daily accumulated charge. The Shannon equation yielded an accuracy of 63.9% using a k value of 1.79. In contrast, the Random Forest algorithm was able to robustly predict whether a set of stimulation parameters was classified as damaging or non-damaging with an accuracy of 88.3%. Significance This novel Random Forest model can facilitate more informed decision making in the selection of neuromodulation parameters for both research studies and clinical practice. This study represents the first approach to use machine learning in the prediction of stimulation-induced neural tissue damage, and lays the groundwork for neurostimulation driven by machine learning models.
Collapse
Affiliation(s)
- Yi Li
- Department of Bioengineering, The University of Texas at Dallas, Richardson, TX, USA
- Center for Systems Biology, The University of Texas at Dallas, Richardson, TX, USA
| | - Rebecca A. Frederick
- Phil and Penny Knight Campus for Accelerating Scientific Impact, University of Oregon, Eugene, OR, USA
| | - Daniel George
- Department of Computer Science, The University of Texas at Dallas, Richardson, TX, USA
| | - Stuart F. Cogan
- Department of Bioengineering, The University of Texas at Dallas, Richardson, TX, USA
| | - Joseph J. Pancrazio
- Department of Bioengineering, The University of Texas at Dallas, Richardson, TX, USA
| | - Leonidas Bleris
- Department of Bioengineering, The University of Texas at Dallas, Richardson, TX, USA
- Center for Systems Biology, The University of Texas at Dallas, Richardson, TX, USA
- Department of Biological Sciences, The University of Texas at Dallas, Richardson, TX, USA
| | | |
Collapse
|