A Pilot Study on Data-Driven Adaptive Deep Brain Stimulation in Chronically Implanted Essential Tremor Patients

Model-based closed-loop control of thalamic deep brain stimulation

Introduction: Closed-loop control of deep brain stimulation (DBS) is beneficial for effective and automatic treatment of various neurological disorders like Parkinson's disease (PD) and essential tremor (ET). Manual (open-loop) DBS programming solely based on clinical observations relies on neurologists' expertise and patients' experience. Continuous stimulation in open-loop DBS may decrease battery life and cause side effects. On the contrary, a closed-loop DBS system uses a feedback biomarker/signal to track worsening (or improving) of patients' symptoms and offers several advantages compared to the open-loop DBS system. Existing closed-loop DBS control systems do not incorporate physiological mechanisms underlying DBS or symptoms, e.g., how DBS modulates dynamics of synaptic plasticity. Methods: In this work, we propose a computational framework for development of a model-based DBS controller where a neural model can describe the relationship between DBS and neural activity and a polynomial-based approximation can estimate the relationship between neural and behavioral activities. A controller is used in our model in a quasi-real-time manner to find DBS patterns that significantly reduce the worsening of symptoms. By using the proposed computational framework, these DBS patterns can be tested clinically by predicting the effect of DBS before delivering it to the patient. We applied this framework to the problem of finding optimal DBS frequencies for essential tremor given electromyography (EMG) recordings solely. Building on our recent network model of ventral intermediate nuclei (Vim), the main surgical target of the tremor, in response to DBS, we developed neural model simulation in which physiological mechanisms underlying Vim-DBS are linked to symptomatic changes in EMG signals. By using a proportional-integral-derivative (PID) controller, we showed that a closed-loop system can track EMG signals and adjust the stimulation frequency of Vim-DBS so that the power of EMG reaches a desired control target. Results and discussion: We demonstrated that the model-based DBS frequency aligns well with that used in clinical studies. Our model-based closed-loop system is adaptable to different control targets and can potentially be used for different diseases and personalized systems.

Alternative patterns of deep brain stimulation in neurologic and neuropsychiatric disorders

Deep brain stimulation (DBS) is a widely used clinical therapy that modulates neuronal firing in subcortical structures, eliciting downstream network effects. Its effectiveness is determined by electrode geometry and location as well as adjustable stimulation parameters including pulse width, interstimulus interval, frequency, and amplitude. These parameters are often determined empirically during clinical or intraoperative programming and can be altered to an almost unlimited number of combinations. Conventional high-frequency stimulation uses a continuous high-frequency square-wave pulse (typically 130-160 Hz), but other stimulation patterns may prove efficacious, such as continuous or bursting theta-frequencies, variable frequencies, and coordinated reset stimulation. Here we summarize the current landscape and potential clinical applications for novel stimulation patterns.

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.

Machine learning based brain signal decoding for intelligent adaptive deep brain stimulation

Sensing enabled implantable devices and next-generation neurotechnology allow real-time adjustments of invasive neuromodulation. The identification of symptom and disease-specific biomarkers in invasive brain signal recordings has inspired the idea of demand dependent adaptive deep brain stimulation (aDBS). Expanding the clinical utility of aDBS with machine learning may hold the potential for the next breakthrough in the therapeutic success of clinical brain computer interfaces. To this end, sophisticated machine learning algorithms optimized for decoding of brain states from neural time-series must be developed. To support this venture, this review summarizes the current state of machine learning studies for invasive neurophysiology. After a brief introduction to the machine learning terminology, the transformation of brain recordings into meaningful features for decoding of symptoms and behavior is described. Commonly used machine learning models are explained and analyzed from the perspective of utility for aDBS. This is followed by a critical review on good practices for training and testing to ensure conceptual and practical generalizability for real-time adaptation in clinical settings. Finally, first studies combining machine learning with aDBS are highlighted. This review takes a glimpse into the promising future of intelligent adaptive DBS (iDBS) and concludes by identifying four key ingredients on the road for successful clinical adoption: i) multidisciplinary research teams, ii) publicly available datasets, iii) open-source algorithmic solutions and iv) strong world-wide research collaborations.

Diving into the Subcortex: The Potential of Chronic Subcortical Sensing for Unravelling Basal Ganglia Function and Optimization of Deep Brain STIMULATION

Subcortical structures are a relative neurophysiological 'terra incognita' owing to their location within the skull. While perioperative subcortical sensing has been performed for more than 20 years, the neurophysiology of the basal ganglia in the home setting has remained almost unexplored. However, with the recent advent of implantable pulse generators (IPG) that are able to record neural activity, the opportunity to chronically record local field potentials (LFPs) directly from electrodes implanted for deep brain stimulation opens up. This allows for a breakthrough of chronic subcortical sensing into fundamental research and clinical practice. In this review an extensive overview of the current state of subcortical sensing is provided. The widespread potential of chronic subcortical sensing for investigational and clinical use is discussed. Finally, status and future perspectives of the most promising application of chronic subcortical sensing -i.e., adaptive deep brain stimulation (aDBS)- are discussed in the context of movement disorders. The development of aDBS based on both chronic subcortical and cortical sensing has the potential to dramatically change clinical practice and the life of patients with movement disorders. However, several barriers still stand in the way of clinical implementation. Advancements regarding IPG and lead technology, physiomarkers, and aDBS algorithms as well as harnessing artificial intelligence, multimodality and sensing in the naturalistic setting are needed to bring aDBS to clinical practice.

Practical Closed-Loop Strategies for Deep Brain Stimulation: Lessons From Chronic Pain

Deep brain stimulation (DBS) is a plausible therapy for various neuropsychiatric disorders, though continuous tonic stimulation without regard to underlying physiology (open-loop) has had variable success. Recently available DBS devices can sense neural signals which, in turn, can be used to control stimulation in a closed-loop mode. Closed-loop DBS strategies may mitigate many drawbacks of open-loop stimulation and provide more personalized therapy. These devices contain many adjustable parameters that control how the closed-loop system operates, which need to be optimized using a combination of empirically and clinically informed decision making. We offer a practical guide for the implementation of a closed-loop DBS system, using examples from patients with chronic pain. Focusing on two research devices from Medtronic, the Activa PC+S and Summit RC+S, we provide pragmatic details on implementing closed- loop programming from a clinician’s perspective. Specifically, by combining our understanding of chronic pain with data-driven heuristics, we describe how to tune key parameters to handle feature selection, state thresholding, and stimulation artifacts. Finally, we discuss logistical and practical considerations that clinicians must be aware of when programming closed-loop devices.

Closing the Loop With Cortical Sensing: The Development of Adaptive Deep Brain Stimulation for Essential Tremor Using the Activa PC+S

Deep Brain Stimulation (DBS) is an important tool in the treatment of pharmacologically resistant neurological movement disorders such as essential tremor (ET) and Parkinson's disease (PD). However, the open-loop design of current systems may be holding back the true potential of invasive neuromodulation. In the last decade we have seen an explosion of activity in the use of feedback to "close the loop" on neuromodulation in the form of adaptive DBS (aDBS) systems that can respond to the patient's therapeutic needs. In this paper we summarize the accomplishments of a 5-year study at the University of Washington in the use of neural feedback from an electrocorticography strip placed over the sensorimotor cortex. We document our progress from an initial proof of hardware all the way to a fully implanted adaptive stimulation system that leverages machine-learning approaches to simplify the programming process. In certain cases, our systems out-performed current open-loop approaches in both power consumption and symptom suppression. Throughout this effort, we collaborated with neuroethicists to capture patient experiences and take them into account whilst developing ethical aDBS approaches. Based on our results we identify several key areas for future work. "Graded" aDBS will allow the system to smoothly tune the stimulation level to symptom severity, and frequent automatic calibration of the algorithm will allow aDBS to adapt to the time-varying dynamics of the disease without additional input from a clinician. Additionally, robust computational models of the pathophysiology of ET will allow stimulation to be optimized to the nuances of an individual patient's symptoms. We also outline the unique advantages of using cortical electrodes for control and the remaining hardware limitations that need to be overcome to facilitate further development in this field. Over the course of this study we have verified the potential of fully-implanted, cortically driven aDBS as a feasibly translatable treatment for pharmacologically resistant ET.

Rapid Dynamic Naturalistic Monitoring of Bradykinesia in Parkinson's Disease Using a Wrist-Worn Accelerometer

Motor fluctuations in Parkinson’s disease are characterized by unpredictability in the timing and duration of dopaminergic therapeutic benefits on symptoms, including bradykinesia and rigidity. These fluctuations significantly impair the quality of life of many Parkinson’s patients. However, current clinical evaluation tools are not designed for the continuous, naturalistic (real-world) symptom monitoring needed to optimize clinical therapy to treat fluctuations. Although commercially available wearable motor monitoring, used over multiple days, can augment neurological decision making, the feasibility of rapid and dynamic detection of motor fluctuations is unclear. So far, applied wearable monitoring algorithms are trained on group data. In this study, we investigated the influence of individual model training on short timescale classification of naturalistic bradykinesia fluctuations in Parkinson’s patients using a single-wrist accelerometer. As part of the Parkinson@Home study protocol, 20 Parkinson patients were recorded with bilateral wrist accelerometers for a one hour OFF medication session and a one hour ON medication session during unconstrained activities in their own homes. Kinematic metrics were extracted from the accelerometer data from the bodyside with the largest unilateral bradykinesia fluctuations across medication states. The kinematic accelerometer features were compared over the 1 h duration of recording, and medication-state classification analyses were performed on 1 min segments of data. Then, we analyzed the influence of individual versus group model training, data window length, and total number of training patients included in group model training, on classification. Statistically significant areas under the curves (AUCs) for medication induced bradykinesia fluctuation classification were seen in 85% of the Parkinson patients at the single minute timescale using the group models. Individually trained models performed at the same level as the group trained models (mean AUC both 0.70, standard deviation respectively 0.18 and 0.10) despite the small individual training dataset. AUCs of the group models improved as the length of the feature windows was increased to 300 s, and with additional training patient datasets. We were able to show that medication-induced fluctuations in bradykinesia can be classified using wrist-worn accelerometry at the time scale of a single minute. Rapid, naturalistic Parkinson motor monitoring has the clinical potential to evaluate dynamic symptomatic and therapeutic fluctuations and help tailor treatments on a fast timescale.