Rapid motor fluctuations reveal short-timescale neurophysiological biomarkers of Parkinson's disease

The potential of convolutional neural networks for identifying neural states based on electrophysiological signals: experiments on synthetic and real patient data

Processing incoming neural oscillatory signals in real-time and decoding from them relevant behavioral or pathological states is often required for adaptive Deep Brain Stimulation (aDBS) and other brain-computer interface (BCI) applications. Most current approaches rely on first extracting a set of predefined features, such as the power in canonical frequency bands or various time-domain features, and then training machine learning systems that use those predefined features as inputs and infer what the underlying brain state is at each given time point. However, whether this algorithmic approach is best suited to extract all available information contained within the neural waveforms remains an open question. Here, we aim to explore different algorithmic approaches in terms of their potential to yield improvements in decoding performance based on neural activity such as measured through local field potentials (LFPs) recordings or electroencephalography (EEG). In particular, we aim to explore the potential of end-to-end convolutional neural networks, and compare this approach with other machine learning methods that are based on extracting predefined feature sets. To this end, we implement and train a number of machine learning models, based either on manually constructed features or, in the case of deep learning-based models, on features directly learnt from the data. We benchmark these models on the task of identifying neural states using simulated data, which incorporates waveform features previously linked to physiological and pathological functions. We then assess the performance of these models in decoding movements based on local field potentials recorded from the motor thalamus of patients with essential tremor. Our findings, derived from both simulated and real patient data, suggest that end-to-end deep learning-based methods may surpass feature-based approaches, particularly when the relevant patterns within the waveform data are either unknown, difficult to quantify, or when there may be, from the point of view of the predefined feature extraction pipeline, unidentified features that could contribute to decoding performance. The methodologies proposed in this study might hold potential for application in adaptive deep brain stimulation (aDBS) and other brain-computer interface systems.

Concurrent decoding of distinct neurophysiological fingerprints of tremor and bradykinesia in Parkinson's disease

Parkinson's disease (PD) is characterized by distinct motor phenomena that are expressed asynchronously. Understanding the neurophysiological correlates of these motor states could facilitate monitoring of disease progression and allow improved assessments of therapeutic efficacy, as well as enable optimal closed-loop neuromodulation. We examined neural activity in the basal ganglia and cortex of 31 subjects with PD during a quantitative motor task to decode tremor and bradykinesia - two cardinal motor signs of PD - and relatively asymptomatic periods of behavior. Support vector regression analysis of microelectrode and electrocorticography recordings revealed that tremor and bradykinesia had nearly opposite neural signatures, while effective motor control displayed unique, differentiating features. The neurophysiological signatures of these motor states depended on the signal type and location. Cortical decoding generally outperformed subcortical decoding. Within the subthalamic nucleus (STN), tremor and bradykinesia were better decoded from distinct subregions. These results demonstrate how to leverage neurophysiology to more precisely treat PD.

Landscape and future directions of machine learning applications in closed-loop brain stimulation

Brain stimulation (BStim) encompasses multiple modalities (e.g., deep brain stimulation, responsive neurostimulation) that utilize electrodes implanted in deep brain structures to treat neurological disorders. Currently, BStim is primarily used to treat movement disorders such as Parkinson's, though indications are expanding to include neuropsychiatric disorders like depression and schizophrenia. Traditional BStim systems are "open-loop" and deliver constant electrical stimulation based on manually-determined parameters. Advancements in BStim have enabled development of "closed-loop" systems that analyze neural biomarkers (e.g., local field potentials in the sub-thalamic nucleus) and adjust electrical modulation in a dynamic, patient-specific, and energy efficient manner. These closed-loop systems enable real-time, context-specific stimulation adjustment to reduce symptom burden. Machine learning (ML) has emerged as a vital component in designing these closed-loop systems as ML models can predict / identify presence of disease symptoms based on neural activity and adaptively learn to modulate stimulation. We queried the US National Library of Medicine PubMed database to understand the role of ML in developing closed-loop BStim systems to treat epilepsy, movement disorders, and neuropsychiatric disorders. Both neural and non-neural network ML algorithms have successfully been leveraged to create closed-loop systems that perform comparably to open-loop systems. For disorders in which the underlying neural pathophysiology is relatively well understood (e.g., Parkinson's, essential tremor), most work has involved refining ML models that can classify neural signals as aberrant or normal. The same is seen for epilepsy, where most current research has focused on identifying optimal ML model design and integrating closed-loop systems into existing devices. For neuropsychiatric disorders, where the underlying pathologic neural circuitry is still being investigated, research is focused on identifying biomarkers (e.g., local field potentials from brain nuclei) that ML models can use to identify onset of symptoms and stratify severity of disease.

Thalamic neuromodulation in epilepsy: A primer for emerging circuit-based therapies

INTRODUCTION

Epilepsy is a common, often debilitating disease of hyperexcitable neural networks. While medically intractable cases may benefit from surgery, there may be no single, well-localized focus for resection or ablation. In such cases, approaching the disease from a network-based perspective may be beneficial.

AREAS COVERED

Herein, the authors provide a narrative review of normal thalamic anatomy and physiology and propose general strategies for preventing and/or aborting seizures by modulating this structure. Additionally, they make specific recommendations for targeting the thalamus within different contexts, motivated by a more detailed discussion of its distinct nuclei and their respective connectivity. By describing important principles governing thalamic function and its involvement in seizure networks, the authors aim to provide a primer for those now entering this fast-growing field of thalamic neuromodulation for epilepsy.

EXPERT OPINION

The thalamus is critically involved with the function of many cortical and subcortical areas, suggesting it may serve as a compelling node for preventing or aborting seizures, and so it has increasingly been targeted for the surgical treatment of epilepsy. As various thalamic neuromodulation strategies for seizure control are developed, there is a need to ground such interventions in a mechanistic, circuit-based framework.

Machine learning-based personalized subthalamic biomarkers predict ON-OFF levodopa states in Parkinson patients

Objective.Adaptive deep brain stimulation (aDBS) based on subthalamic nucleus (STN) electrophysiology has recently been proposed to improve clinical outcomes of DBS for Parkinson's disease (PD) patients. Many current models for aDBS are based on one or two electrophysiological features of STN activity, such as beta or gamma activity. Although these models have shown interesting results, we hypothesized that an aDBS model that includes many STN activity parameters will yield better clinical results. The objective of this study was to investigate the most appropriate STN neurophysiological biomarkers, detectable over long periods of time, that can predict OFF and ON levodopa states in PD patients.Approach.Long-term local field potentials (LFPs) were recorded from eight STNs (four PD patients) during 92 recording sessions (44 OFF and 48 ON levodopa states), over a period of 3-12 months. Electrophysiological analysis included the power of frequency bands, band power ratio and burst features. A total of 140 engineered features was extracted for 20 040 epochs (each epoch lasting 5 s). Based on these engineered features, machine learning (ML) models classified LFPs as OFF vs ON levodopa states.Main results.Beta and gamma band activity alone poorly predicts OFF vs ON levodopa states, with an accuracy of 0.66 and 0.64, respectively. Group ML analysis slightly improved prediction rates, but personalized ML analysis, based on individualized engineered electrophysiological features, were markedly better, predicting OFF vs ON levodopa states with an accuracy of 0.8 for support vector machine learning models.Significance.We showed that individual patients have unique sets of STN neurophysiological biomarkers that can be detected over long periods of time. ML models revealed that personally classified engineered features most accurately predict OFF vs ON levodopa states. Future development of aDBS for PD patients might include personalized ML algorithms.

Multi-Dimensional, Short-Timescale Quantification of Parkinson's Disease and Essential Tremor Motor Dysfunction

Introduction: Parkinson's disease (PD) is a progressive movement disorder characterized by heterogenous motor dysfunction with fluctuations in severity. Objective, short-timescale characterization of this dysfunction is necessary as therapies become increasingly adaptive.

Objectives: This study aims to characterize a novel, naturalistic, and goal-directed tablet-based task and complementary analysis protocol designed to characterize the motor features of PD.

Methods: A total of 26 patients with PD and without deep brain stimulation (DBS), 20 control subjects, and eight patients with PD and with DBS completed the task. Eight metrics, each designed to capture an aspect of motor dysfunction in PD, were calculated from 1-second, non-overlapping epochs of the raw positional and pressure data captured during task completion. These metrics were used to generate a classifier using a support vector machine (SVM) model to produce a unifying, scalar “motor error score” (MES). The data generated from these patients with PD were compared to same-day standard clinical assessments. Additionally, these data were compared to analogous data generated from a separate group of 12 patients with essential tremor (ET) to assess the task's specificity for different movement disorders. Finally, an SVM model was generated for each of the eight patients with PD and with DBS to differentiate between their motor dysfunction in the “DBS On” and “DBS Off” stimulation states.

Results: The eight metrics calculated from the raw positional and force data captured during task completion were non-redundant. MES generated by the SVM analysis protocol showed a strong correlation with MDS-UPDRS-III scores assigned by movement disorder specialists. Analysis of the relative contributions of each of the eight metrics showed a significant difference between the motor dysfunction of PD and ET. Much of this difference was attributable to the homogenous, tremor-dominant phenotype of ET motor dysfunction. Finally, in individual patients with PD with DBS, task performance and subsequent SVM classification effectively differentiated between the “DBS On” and “DBS Off” stimulation states.

Conclusion: This tablet-based task and analysis protocol correlated strongly with expert clinical assessments of PD motor dysfunction. Additionally, the task showed specificity for PD when compared to ET, another common movement disorder. This specificity was driven by the relative heterogeneity of motor dysfunction of PD compared to ET. Finally, the task was able to distinguish between the “DBS On” and “DBS Off” states within single patients with PD. This task provides temporally-precise and specific information about motor dysfunction in at least two movement disorders that could feasibly correlate to neural activity.