Application Of Deep Brain Stimulation Research Articles

Stimulation of an entorhinal-hippocampal extinction circuit facilitates fear extinction in a post-traumatic stress disorder model.

Effective psychotherapy of post-traumatic stress disorder (PTSD) remains challenging due to the fragile nature of fear extinction, for which ventral hippocampal CA1 (vCA1) region is considered as a central hub. However, neither the core pathway nor the cellular mechanisms involved in implementing extinction are known. Here, we unveil a direct pathway, where layer 2a fan cells in the lateral entorhinal cortex (LEC) target parvalbumin-expressing interneurons (PV-INs) in the vCA1 region to propel low gamma-band synchronization of the LEC-vCA1 activity during extinction learning. Bidirectional manipulations of either hippocampal PV-INs or LEC fan cells sufficed fear extinction. Gamma entrainment of vCA1 by deep brain stimulation (DBS) or noninvasive transcranial alternating current stimulation (tACS) of LEC persistently enhanced the PV-IN activity in vCA1, thereby promoting fear extinction. These results demonstrate that the LEC-vCA1 pathway forms a top-down motif to empower low gamma-band oscillations that facilitate fear extinction. Finally, application of low gamma DBS and tACS to a mouse model with persistent PTSD showed potent efficacy, suggesting that the dedicated LEC-vCA1 pathway can be stimulated for therapy to remove traumatic memory trace.

Carry-Over Effect of Deep Cerebellar Stimulation-Mediated Motor Recovery in a Rodent Model of Traumatic Brain Injury

Background We previously demonstrated that deep brain stimulation (DBS) of lateral cerebellar nucleus (LCN) can enhance motor recovery and functional reorganization of perilesional cortex in rodent models of stroke or TBI. Objective Considering the treatment-related neuroplasticity observed at the perilesional cortex, we hypothesize that chronic LCN DBS-enhanced motor recovery observed will carry-over even after DBS has been deactivated. Methods Here, we directly tested the enduring effects of LCN DBS in male Long Evans rats that underwent controlled cortical impact (CCI) injury targeting sensorimotor cortex opposite their dominant forepaw followed by unilateral implantation of a macroelectrode into the LCN opposite the lesion. Animals were randomized to DBS or sham treatment for 4 weeks during which the motor performance were characterize by behavioral metrics. After 4 weeks, stimulation was turned off, with assessments continuing for an additional 2 weeks. Afterward, all animals were euthanized, and tissue was harvested for further analyses. Results Treated animals showed significantly greater motor improvement across all behavioral metrics relative to untreated animals during the 4-week treatment, with functional gains persisting across 2-week post-treatment. This motor recovery was associated with the increase in CaMKIIα and BDNF positive cell density across perilesional cortex in treated animals. Conclusions LCN DBS enhanced post-TBI motor recovery, the effect of which was persisted up to 2 weeks beyond stimulation offset. Such evidence should be considered in relation to future translational efforts as, unlike typical DBS applications, treatment may only need to be provided until such time as a new function plateau is achieved.

Deep brain stimulation targeted at lateral hypothalamus-medial forebrain bundle reverses depressive-like symptoms and related cognitive deficits in rat: Role of serotoninergic system

The aim of the study is to understand the rationale behind the application of deep brain stimulation (DBS) in the treatment of depression. Male Wistar rats, rendered depressive with chronic unpredictable mild stress (CUMS) were implanted with electrode in the lateral hypothalamus-medial forebrain bundle (LH-MFB) and subjected to deep brain stimulation (DBS) for 4 h each day for 14 days. DBS rats, as well as controls, were screened for a range of parameters indicative of depressive state. Symptomatic features noticed in CUMS rats like the memory deficit, anhedonia, reduction in body weight and 5-hydroxytryptamine (5-HT) and 5-hydroxyindoleacetic acid (5-HIAA) levels in mPFC and elevated plasma corticosterone were reversed in rats subjected to DBS. DBS arrested CUMS induced degeneration of 5-HT cells in interfascicular region of dorsal raphe nucleus (DRif) and fibers in LH-MFB and induced dendritic proliferation in mPFC neurons. MFB is known to serve as a major conduit for the DRif-mPFC serotoninergic pathway. While the density of serotonin fibers in the LH-MFB circuit was reduced in CUMS, it was upregulated in DBS-treated rats. Furthermore, microinjection of 5-HT1A receptor antagonist, WAY100635 into mPFC countered the positive effects of DBS like the antidepressant and memory-enhancing action. In this background, we suggest that DBS at LH-MFB may exercise positive effect in depressive rats via upregulation of the serotoninergic system. While these data drawn from the experiments on rat provide meaningful clues, we suggest that further studies aimed at understanding the usefulness of DBS at LH-MFB in humans may be rewarding.

SAFE-OPT: a Bayesian optimization algorithm for learning optimal deep brain stimulation parameters with safety constraints

Objective.To treat neurological and psychiatric diseases with deep brain stimulation (DBS), a trained clinician must select parameters for each patient by monitoring their symptoms and side-effects in a months-long trial-and-error process, delaying optimal clinical outcomes. Bayesian optimization has been proposed as an efficient method to quickly and automatically search for optimal parameters. However, conventional Bayesian optimization does not account for patient safety and could trigger unwanted or dangerous side-effects.Approach.In this study we develop SAFE-OPT, a Bayesian optimization algorithm designed to learn subject-specific safety constraints to avoid potentially harmful stimulation settings during optimization. We prototype and validate SAFE-OPT using a rodent multielectrode stimulation paradigm which causes subject-specific performance deficits in a spatial memory task. We first use data from an initial cohort of subjects to build a simulation where we design the best SAFE-OPT configuration for safe and accurate searchingin silico. Main results.We then deploy both SAFE-OPT and conventional Bayesian optimization without safety constraints in new subjectsin vivo, showing that SAFE-OPT can find an optimally high stimulation amplitude that does not harm task performance with comparable sample efficiency to Bayesian optimization and without selecting amplitude values that exceed the subject's safety threshold.Significance.The incorporation of safety constraints will provide a key step for adopting Bayesian optimization in real-world applications of DBS.

No Consistent Antidepressant Effects of Deep Brain Stimulation of the Bed Nucleus of the Stria Terminalis.

Applying deep brain stimulation (DBS) to several brain regions has been investigated in attempts to treat highly treatment-resistant depression, with variable results. Our initial pilot data suggested that the bed nucleus of the stria terminalis (BNST) could be a promising therapeutic target. The aim of this study was to gather blinded data exploring the efficacy of applying DBS to the BNST in patients with highly refractory depression. Eight patients with chronic severe treatment-resistant depression underwent DBS to the BNST. A randomised, double-blind crossover study design with fixed stimulation parameters was followed and followed by a period of open-label stimulation. During the double-blind crossover phase, no consistent antidepressant effects were seen with any of the four stimulation parameters applied, and no patients achieved response or remission criteria during the blinded crossover phase or during a subsequent period of three months of blinded stimulation. Stimulation-related side effects, especially agitation, were reported by a number of patients and were reversible with adjustment of the stimulation parameters. The results of this study do not support the application of DBS to the BNST in patients with highly resistant depression or ongoing research utilising stimulation at this brain site. The blocked randomised study design utilising fixed stimulation parameters was poorly tolerated by the participants and does not appear suitable for assessing the efficacy of DBS at this location.

Adverse Effects of Deep Brain Stimulation for Treatment-Resistant Depression: A Scoping Review.

Deep brain stimulation (DBS) is an emerging therapy for treatment-resistant depression (TRD). Although adverse effects have been reported in early-phase and a few randomized clinical trials, little is known about its overall safety profile, which has been assumed to be similar to that of DBS for movement disorders. The objective of this study was to pool existing safety data on DBS for TRD. Following PRISMA guidelines, PubMed was searched for English articles describing adverse outcomes after DBS for TRD. Studies were included if they reported at least 5 patients with a minimal follow-up of 6 months. After abstract (n = 607) and full-article review (n = 127), 28 articles reporting on 353 patients met criteria for final inclusion. Follow-up of the studies retrieved ranged from 12 to 96 months. Hemorrhages occurred in 0.8% of patients and infections in 10.2%. The rate of completed suicide was 2.5%. Development or worsening of depressive symptoms, anxiety, and mania occurred in 18.4%, 9.1%, and 5.1%, respectively. There were some differences between targets, but between-study heterogeneity precluded statistical comparisons. In conclusion, DBS for TRD is associated with surgical and psychiatric adverse events. Hemorrhage and infection occur at rates within an accepted range for other DBS applications. The risk of suicide after DBS for TRD is 2.5% but may not represent a significant deviation from the natural history of TRD. Finally, risks of worsening depression, anxiety, and the incidence of mania should be acknowledged when considering DBS for TRD.

Application of deep brain stimulation for the treatment of childhood-onset dystonia in patients with MEPAN syndrome.

Mitochondrial Enoyl CoA Reductase Protein-Associated Neurodegeneration (MEPAN) syndrome is a rare inherited metabolic condition caused by MECR gene mutations. This gene encodes a protein essential for fatty acid synthesis, and defects cause progressively worsening childhood-onset dystonia, optic atrophy, and basal ganglia abnormalities. Deep brain stimulation (DBS) has shown mixed improvement in other childhood-onset dystonia conditions. To the best of our knowledge, DBS has not been investigated as a treatment for dystonia in patients with MEPAN syndrome. Two children with MEPAN were identified as possible DBS candidates due to severe generalized dystonia unresponsive to pharmacotherapy. Temporary depth electrodes were placed in six locations bilaterally and tested during a 6-day hospitalization to determine the best locations for permanent electrode placement. The Burke-Fahn-Marsden Dystonia Rating Scale (BFMDRS) and Barry-Albright Dystonia Scale (BADS) were used for preoperative and postoperative testing to quantitatively assess dystonia severity changes. Patient 1 had permanent electrodes placed at the globus pallidus internus (GPi) and pedunculopontine nucleus (PPN). Patient 2 had permanent electrodes placed at the GPi and ventralis intermedius nucleus of the thalamus (VIM). Both patients successfully underwent DBS placement with no perioperative complications and significant improvement in their BFMDRS score. Patient 2 also demonstrated improvement in the BADS. We demonstrated a novel application of DBS in MEPAN syndrome patients with childhood-onset dystonia. These patients showed clinically significant improvements in dystonia following DBS, indicating that DBS can be considered for dystonia in patients with rare metabolic disorders that currently have no other proven treatment options.

A Comprehensive study on the application of deep brain stimulation in PTSD

Nowadays, with the rapid development of society, stress from all aspects promotes increasing rates of getting mental health issues or illness. Among them, Post Traumatic Stress Disorder (PTSD) is one of the famous mental problems that is noticed by people heavily in recent years. At the same time, great progress in the field of medical-surgical technology has also been made. Deep Brain Stimulation (DBS), a neurosurgical process that requires implanting electrodes in specific brain regions, can be used to treat PTSD to some extent. This reviewed the previous research and study conducted using DBS targeting PTSD, synthesized results and found that DBS treatment is currently mainly at the preclinical stage; Amygdala is the most common brain region that being targeted by DBS; The combination of several treatments is more effective than only DBS treatment; and most studies about the effects of DBS on PTSD were conducted on animal models. Whats more, the future study direction of this related topic including the Nonhuman Primate Research and DBS treatment with other disorders such as Parkinsons Disorder, and Obsessive-Compulsive Disorder(OCD) is also included.

Machine learning: a new direction for assisting the application of deep brain stimulation

In recent years, deep brain stimulation has been widely used in the treatment of various difficult diseases of the nervous system. The rapid development of machine learning algorithms has greatly promoted the application and development of deep brain stimulation. Machine learning can help in preoperative screening of surgical candidates, outcome prediction and surgical planning. It can assist target localization during operation. More importantly, the local field potential signals recorded by macroscopic electrodes can be analyzed in real time after surgery, which provides a basis for the development of a closed-loop stimulation system. Of course, the application of machine learning also has its limitations and challenges, such as dimensionality reduction of high-dimensional data, development and validation of new models and etc, which need to be further explored and improved.

Clinical neuromodulatory effects of deep brain stimulation in disorder of consciousness: A literature review.

The management of patients with disorders of consciousness (DOC) presents substantial challenges in clinical practice. Deep brain stimulation (DBS) has emerged as a potential therapeutic approach, but the lack of standardized regulatory parameters for DBS in DOC hinders definitive conclusions. This comprehensive review aims to provide a detailed summary of the current issues concerning patient selection, target setting, and modulation parameters in clinical studies investigating the application of DBS for DOC patients. A meticulous systematic analysis of the literatures was conducted, encompassing articles published from 1968 to April 2023, retrieved from reputable databases (PubMed, Embase, Medline, and Web of Science). The systematic analysis of 21 eligible articles, involving 146 patients with DOC resulting from acquired brain injury or other disorders, revealed significant insights. The most frequently targeted regions were the Centromedian-parafascicular complex (CM-pf) nuclei and central thalamus (CT), both recognized for their role in regulating consciousness. However, other targets have also been explored in different studies. The stimulation frequency was predominantly set at 25 or 100 Hz, with pulse width of 120 μs, and voltages ranged from 0 to 4 V. These parameters were customized based on individual patient responses and evaluations. The overall clinical efficacy rate in all included studies was 39.7%, indicating a positive effect of DBS in a subset of DOC patients. Nonetheless, the assessment methods, follow-up durations, and outcome measures varied across studies, potentially contributing to the variability in reported efficacy rates. Despite the challenges arising from the lack of standardized parameters, DBS shows promising potential as a therapeutic option for patients with DOC. However, there still remains the need for standardized protocols and assessment methods, which are crucial to deepen the understanding and optimizing the therapeutic potential of DBS in this specific patient population.

Postoperative infection problems in DBS applications

Deep brain stimulation (DBS) is a significant neuromodulation method for treating neurological and psychiatric disorders. Despite its efficacy, complications, particularly infections, are a concern. This article reviews the prevalence, risk factors, pathogens, infection locations, timing, surgical approaches, prevention strategies, and treatment methods associated with infections following DBS procedures. DBS surgeries have gained popularity due to their adjustability, but infections pose challenges. Surgical site infections (SSIs) are common (0% to 24% cases) and extensively studied regarding patient groups, locations, timing, and pathogens. Expanding patient groups, including conditions like Tourette syndrome and epilepsy, have varying infection risks. Infections occur at burr-hole, extension, and implantable pulse generator (IPG) sites. Staphylococcus aureus is a primary pathogen, yet bacterial DNA on IPGs and colonization complicate understanding. Surgical approaches, staged or non-staged, show comparable infection rates. The influence of repetitive pulse generator replacements on infection rates is debated. Lead externalization, topical vancomycin powder, and other factors impact infection risk. Treating DBS-related infections often requires hardware extraction and antibiotic treatment. Innovations like ethylene oxide sterilization and hydrogen peroxide show potential. Algorithms suggest partial explantation for localized infections. Cost analyses favor starting with antibiotics. Infections persist despite progress; understanding risks, pathogens, and strategies is vital for optimal outcomes in DBS.

Surgical treatment methods in the course of psychiatric disorders: Deep brain stimulation-Novel insights and indications.

Deep brain stimulation (DBS) is a relatively dated treatment procedure that emerged in the late 1980s. Nonetheless, numerous studies are being carried out to examine its influence on the human brain and develop new treatment indications. This systematic review aims to summarize the current state of knowledge referring to DBS, investigate novel insights into its indications, and discuss the technical aspects and rationale behind DBS application. In particular, we sought to subject to scrutiny the application of DBS specifically in anorexia nervosa (AN), various addiction types, depression, and obsessive-compulsive disorders (OCDs). The method is supposed to offer promising results, especially in pharmacologically resistant forms of the upper-mentioned psychiatric disorders. Moreover, further insight has been provided into the historical notions of the method and differences in the surgical approach in specific disease entities. Furthermore, we mark the possible influence of comorbidities on treatment results. Our review consists of articles and studies found on PubMed, Google Scholar, Cochrane, and Scopus, which were then analyzed with scrutiny in the identification process, including the most resourceful ones. After methodological quality and risk of bias assessment, a total of 53 studies were included. To this date, DBS's usefulness in the treatment of AN, OCDs, depression, and addictions has been proven, despite an ongoing debate concerning the technical aspects and parameters when applying DBS. To the best of our knowledge, we have not found any paper that would recapitulate the current state of DBS in the context of psychiatric disorders with an addition of technical insights.

Technical note: System uncertainty on four- and eight-channel parallel RF transmission for safe MRI of deep brain stimulation devices.

Parallel radiofrequency transmission (pTx) remains a promising technology for addressing high-field magnetic resonance imaging (MRI) challenges, particularly regarding the safety of patients with implanted deep brain stimulation (DBS) devices. Radiofrequency (RF) shim optimization methods utilizing pTx technology have shown the potential to minimize induced RF heating effects at the electrode tips of DBS devices at 3 T. Research pTx system implementations often involve the combination of custom and commercial hardware that are integrated onto an existing MRI system. As a result, system characterization is important to ensure implant-friendly safe imaging conditions are satisfied for the operating range of the hardware. Utilizing electromagnetic and thermal simulations, the impact of system uncertainty is studied for the proposed 4- and 8-channel pTx system setupand its associated "safe mode" for DBS applications. Electromagnetic simulations indicated that instrumentation errors can affect the overall electric field strength experienced at the DBS lead tip, and a worst-case system uncertainty analysis predicted temperature elevations of +1.5°C in the 4-channel setup and +0.9°C in the 8-channel setup. In conclusion, system uncertainty can impact the precision of pTx RF inputs which in the worst-case, may lead to an unsafe imaging scenario and the proposed 8-channel setup may provide more robustness and thus, safer conditions for MRI of DBS patients.

A protocol of a systematic review on deep brain stimulation surgery and its efficacy in addressing substance abuse addiction.

Pharmacotherapy and psychotherapeutic approaches are still the mainstay first line of treatment for substance use disorder. However, the path to rehabilitation and cessation of dependence often proves uncertain and laborious, with risks of relapse being considerable despite exposure to current therapeutic modalities. For cases of treatment-refractory addiction, deep brain stimulation (DBS) interventions can prove a more effective long term therapeutic solution for the patient. The aim of the study will be to systematically assess whether attempts at correcting substance use disorder via DBS neurosurgical interventions have been successful in inducing remission or ameliorating relapse rates. The current study will analyze available literature from database inception up to 15th April 2023, reviewing all publications documenting results achieved with human patients undergoing DBS for substance use disorder in PubMed, Ovid, Cochrane, and Web of Science. The electronic database search will exclude animal studies in the field and focus solely on the application of DBS for the purposes of addressing addiction disorders. The expectation is for a reduced number of trial results to have been reported, namely due to the relatively recent application of DBS to address severe addiction. Nonetheless, numbers should be in sufficient amount to inform about the efficacy of the intervention. This study will attempt to demonstrate the viability of DBS as a solution for tackling treatment-refractory substance use disorder, proposing it as a valid therapeutic option that can deliver robust results and help combat an expanding societal plague that is drug dependence.

Patient feedback and psychosocial outcomes of deep brain stimulation in people with obsessive–compulsive disorder

Severe and refractory psychiatric patients can experience complex and profound changes in symptomology, functioning and well-being from deep brain stimulation (DBS) therapy. Currently, the efficacy of DBS is assessed by clinician rated scales of primary symptoms, yet this does not capture the multitude of DBS mediated changes or represent the patient perspective. We aimed to elucidate the patient perspective in psychiatric DBS application by investigating 1) symptomatic, and 2) psychosocial changes, 3) therapeutic expectations and satisfaction, 4) decision-making capacity, and 5) clinical care recommendations from treatment refractory obsessive–compulsive disorder (OCD) DBS patients. Participants enrolled in an open label clinical trial of DBS therapy for OCD who had reached clinical response were invited to participate in a follow up survey. Participants completed a 1) feedback survey relating to goals, expectations, and satisfaction of therapy, and 2) self-report questionnaires on psychosocial functioning including quality of life, cognitive insight, locus of control, rumination, cognitive flexibility, impulsivity, affect, and well-being. Greatest change was reported for quality of life, rumination, affect and cognitive flexibility. Participants reported realistic expectations, high satisfaction, adequate pre-operative education and decision-making capacity; and advocated for greater access to DBS care and more widespread support services. This is the first identified investigation on psychiatric patient perspectives of functioning and therapeutic outcomes following DBS. Insights from the study have implications for informing psychoeducation, clinical practices, and neuroethical debates. We encourage a greater patient-centred and biopsychosocial approach in evaluating and managing OCD DBS patients, by considering personally meaningful goals and addressing symptomatic and psychosocial recovery.

Restoring the firing activity of ventral tegmental area neurons by lateral hypothalamic deep brain stimulation following morphine administration in rats

We have previously shown that high-frequency deep brain stimulation (DBS) of the lateral hypothalamus (LH) compromises morphine-induced addiction-like behavior in rats. The exact mechanism underlying this effect is not known. Here, we investigated the assumption that DBS in the LH influences the firing activity of neurons in the ventral tegmental area (VTA). To that end, male Wistar rats received morphine (5 mg/kg; s.c.) for three days and underwent extracellular single unit recording under general anesthesia one day later. During the recording, the rats received an intraoperative injection of morphine (5 mg/kg; s.c.) plus DBS in the LH (130 Hz pulse frequency, 150 μA amplitude, and 100 μs pulse width). One group of animals also received preoperative DBS after each morphine injection before the recording. The spiking frequency of VTA neurons was measured at three successive phases: (1) baseline (5–15 min); (2) DBS-on (morphine + DBS for 30 min); and (3) After-DBS (over 30 min after termination of DBS). Results showed that morphine suppressed the firing activity of a large population of non-DA neurons, whereas it activated most DA neurons. Intraoperative DBS reversed morphine suppression of non-DA firing, but did not alter the excitatory effect of morphine on DA neurons firing. With repeated preoperative application of DBS, non-DA neurons returned to the morphine-induced suppressive state, but DA neurons released from the excitatory effect of morphine. It is concluded that the development of morphine reward is associated with a hypoactivity of VTA non-DA neurons and a hyperactivity of DA neurons, and that DBS modulation of the spiking activity may contribute to the blockade of morphine addiction-like behavior.

Distinct suppressing effects of deep brain stimulation in the orbitofrontal cortex on the development, extinction, and reinstatement of methamphetamine-seeking behaviors

AimsThe orbitofrontal cortex (OFC) is implicated in compulsive drug-seeking and relapse, the characteristics that result in addiction treatment failure. Structural and functional impairments within the OFC have been detected in many substance use disorders (SUDs). Deep brain stimulation (DBS) is proposed as a promising therapeutic option in treating SUDs. Therefore, the present study aimed to investigate the potential efficacy of DBS application on the various stages of the methamphetamine-conditioned place preference (CPP) paradigm in rats. Main methodsElectrodes were implanted unilaterally in the rat's right OFC. DBS in the form of high- or low-frequency stimulation (HFS: 130 Hz, LFS: 13 Hz) was applied during the 5-day conditioning phase (a daily 30-min session) or extinction period (30-min session, daily, ten days) of methamphetamine-induced CPP in two separate sets of experiments. Following extinction, place preference was reinstated by injecting a priming dose of methamphetamine (0.25 mg/kg). Key findingsThe HFS and LFS significantly decreased the methamphetamine place preference when applied over the conditioning period. In the extinction experiment, only HFS could remarkably accelerate the extinction of reward-context associations and even reduce the methamphetamine-induced reinstatement of seeking behaviors. SignificanceConclusively, DBS administration in the OFC demonstrated some positive results, including suppressing effects on the development, maintenance, and relapse of methamphetamine-seeking behavior. These findings encourage conducting more preclinical studies to strongly suggest a wide range of DBS applications in cortical areas such as OFC as an efficient treatment modality for psychostimulant use disorder.

Identifying Relational Applications of Deep Brain Stimulation for Treatment Resistant Depression

Identifying Relational Applications of Deep Brain Stimulation for Treatment Resistant Depression

Advanced non-linear control based on artificial intelligence tuner for hand tremor suppression

One of the most common symptoms among diverse patients (e.g. Parkinson’s disease, essential tremor) is hand tremor. Deep brain stimulation (DBS) has been a popular method of controlling hand tremor in recent years. Although recent advancements in the DBS system have enabled DBS applications in the context of various neurodegenerative disorders, the deployment of such interface tactics in DBS applications is seriously threatened by un-adaptability concerns and a lack of an accurate model. In response to these issues, the current letter discusses the construction of an intelligent technique for minimizing hand tremor and self-adaptive DBS settings without requiring a proper hand tremor system modeling setup. For this purpose, the hand tremor is suppressed using an intelligent proportional–integral (iPI) as the main controller and the sliding mode (SM) as an observer. Furthermore, as an auxiliary controller, a deep reinforcement learning (DRL) method with the Actor-Critic structure is adaptively incorporated. The feedback parameters of the ultra-local model (ULM) controller will be adaptively modified utilizing the DRL method by online neural network (NN) updating in the proposed strategy. The advantages of the ULM based on DRL structure over state-of-the-art approaches are demonstrated by a complete assessment.

Artificial neural network-based rapid predictor of biological nerve fiber activation for DBS applications

Objective. Computational models are powerful tools that can enable the optimization of deep brain stimulation (DBS). To enhance the clinical practicality of these models, their computational expense and required technical expertise must be minimized. An important aspect of DBS models is the prediction of neural activation in response to electrical stimulation. Existing rapid predictors of activation simplify implementation and reduce prediction runtime, but at the expense of accuracy. We sought to address this issue by leveraging the speed and generalization abilities of artificial neural networks (ANNs) to create a novel predictor of neural fiber activation in response to DBS. Approach. We developed six variations of an ANN-based predictor to predict the response of individual, myelinated axons to extracellular electrical stimulation. ANNs were trained using datasets generated from a finite-element model of an implanted DBS system together with multi-compartment cable models of axons. We evaluated the ANN-based predictors using three white matter pathways derived from group-averaged connectome data within a patient-specific tissue conductivity field, comparing both predicted stimulus activation thresholds and pathway recruitment across a clinically relevant range of stimulus amplitudes and pulse widths. Main results. The top-performing ANN could predict the thresholds of axons with a mean absolute error (MAE) of 0.037 V, and pathway recruitment with an MAE of 0.079%, across all parameters. The ANNs reduced the time required to predict the thresholds of 288 axons by four to five orders of magnitude when compared to multi-compartment cable models. Significance. We demonstrated that ANNs can be fast, accurate, and robust predictors of neural activation in response to DBS.