Impacts of Deep Brain Stimulation of the Globus Pallidus Internus on Swallowing: A Retrospective, Cross-Sectional Study.

Deep brain stimulation (DBS) is a common treatment for motor symptoms of Parkinson disease (PD), a condition associated with increased risk of dysphagia. The effect of DBS on swallowing function has not been comprehensively evaluated using gold-standard imaging techniques, particularly for globus pallidus internus (GPi) DBS. The objective of this retrospective, cross-sectional study was to identify differences in swallowing safety and timing kinematics among PD subjects with and without GPi DBS. We investigated the effects of unilateral and bilateral GPi DBS as well as the relationship between swallowing safety and DBS stimulation parameters, using retrospective analysis of videofluoroscopy recordings (71 recordings from 36 subjects) from electronic medical records. Outcomes were analyzed by surgical status (pre-surgical, unilateral DBS, bilateral DBS). The primary outcome was percent of thin-liquid bolus trials rated as unsafe, with Penetration-Aspiration Scale scores of 3 or higher. Secondary analyses included swallowing timing measures, relationships between swallowing safety and DBS stimulation parameters, and Dynamic Imaging Grade of Swallowing Toxicity ratings. Most subjects swallowed all boluses safely (19/29 in the pre-surgical, 16/26 in the unilateral DBS, and 10/16 in the bilateral DBS conditions). Swallowing safety impairment did not differ among stimulation groups. There was no main effect of stimulation condition on timing metrics, though main effects were found for sex and bolus type. Stimulation parameters were not correlated with swallowing safety. Swallowing efficiency and overall impairment did not differ among conditions. These results provide evidence that GPi DBS does not affect pharyngeal swallowing function. Further, prospective, investigations are needed.

Comparative connectivity correlates of dystonic and essential tremor deep brain stimulation.

The pathophysiology of dystonic tremor and essential tremor remains partially understood. In patients with medication-refractory dystonic tremor or essential tremor, deep brain stimulation (DBS) targeting the thalamus or posterior subthalamic area has evolved into a promising treatment option. However, the optimal DBS targets for these disorders remains unknown. This retrospective study explored the optimal targets for DBS in essential tremor and dystonic tremor using a combination of volumes of tissue activated estimation and functional and structural connectivity analyses. We included 20 patients with dystonic tremor who underwent unilateral thalamic DBS, along with a matched cohort of 20 patients with essential tremor DBS. Tremor severity was assessed preoperatively and approximately 6 months after DBS implantation using the Fahn-Tolosa-Marin Tremor Rating Scale. The tremor-suppressing effects of DBS were estimated using the percentage improvement in the unilateral tremor-rating scale score contralateral to the side of implantation. The optimal stimulation region, based on the cluster centre of gravity for peak contralateral motor score improvement, for essential tremor was located in the ventral intermediate nucleus region and for dystonic tremor in the ventralis oralis posterior nucleus region along the ventral intermediate nucleus/ventralis oralis posterior nucleus border (4 mm anterior and 3 mm superior to that for essential tremor). Both disorders showed similar functional connectivity patterns: a positive correlation between tremor improvement and involvement of the primary sensorimotor, secondary motor and associative prefrontal regions. Tremor improvement, however, was tightly correlated with the primary sensorimotor regions in essential tremor, whereas in dystonic tremor, the correlation was tighter with the premotor and prefrontal regions. The dentato-rubro-thalamic tract, comprising the decussating and non-decussating fibres, significantly correlated with tremor improvement in both dystonic and essential tremor. In contrast, the pallidothalamic tracts, which primarily project to the ventralis oralis posterior nucleus region, significantly correlated with tremor improvement only in dystonic tremor. Our findings support the hypothesis that the pathophysiology underpinning dystonic tremor involves both the cerebello-thalamo-cortical network and the basal ganglia-thalamo-cortical network. Further our data suggest that the pathophysiology of essential tremor is primarily attributable to the abnormalities within the cerebello-thalamo-cortical network. We conclude that the ventral intermediate nucleus/ventralis oralis posterior nucleus border and ventral intermediate nucleus region may be a reasonable DBS target for patients with medication-refractory dystonic tremor and essential tremor, respectively. Uncovering the pathophysiology of these disorders may in the future aid in further improving DBS outcomes.

Therapeutic Advances in the Treatment of Holmes Tremor: Systematic Review.

OBJECTIVE: We aimed to formulate a practical clinical treatment algorithm for Holmes tremor (HT) by reviewing currently published clinical data. MATERIALS AND METHODS: We performed a systematic review of articles discussing the management of HT published between January 1990 and December 2018. We examined data from 89 patients published across 58 studies detailing the effects of pharmacological or surgical interventions on HT severity. Clinical outcomes were measured by a continuous 1-10 ranked scale. The majority of studies addressing treatment response were case series or case reports. No randomized control studies were identified. RESULTS: Our review included 24 studies focusing on pharmacologic treatments of 25 HT patients and 34 studies focusing on the effect of deep brain stimulation (DBS) in 64 patients. In the medical intervention group, the most commonly used drugs were levetiracetam, trihexyphenidyl, and levodopa. In the surgically treated group, the thalamic ventralis intermedius nucleus (VIM) and globus pallidus internus (GPi) were the most common brain targets for neuromodulation. The two targets accounted for 57.8% and 32.8% of total cases, respectively. Overall, compared to the medically treated group, DBS provided greater tremor suppression (p = 0.025) and was more effective for the management of postural tremor in HT. Moreover, GPi DBS displayed greater benefit in the resting tremor component (p = 0.042) and overall tremor reduction (p = 0.022). CONCLUSIONS: There is a highly variable response to different medical treatments in HT without randomized clinical trials available to dictate treatment decisions. A variety of medical and surgical treatment options can be considered for the management of HT. Collaborative research between different institutions and researchers are warranted and needed to improve our understanding of the pathophysiology and management of this condition. In this review, we propose a practical treatment algorithm for HT based on currently available evidence.

Quality of life outcomes after globus pallidus internus deep brain stimulation in idiopathic or inherited isolated dystonia: a meta-analysis.

BACKGROUND: Several studies reported the beneficial effects of globus pallidus internus deep brain stimulation (GPi DBS) on health-related quality of life (HRQoL) in patients with inherited or idiopathic isolated dystonia. However, the impact of this intervention on physical and mental/psychological domains and the effects over time remain unclear. METHODS: We conducted a systematic literature review from January 2000 to May 2019 and performed a meta-analysis of HRQoL outcomes based on the Short Form Health Survey-36 (SF-36) after GPi DBS in patients with inherited or idiopathic isolated dystonia to evaluate the effects of DBS on physical and mental QoL. RESULTS: Seven studies comprising 144 patients with dystonia (78, generalised; 34, segmental; and 32, focal cervical) were included in this comprehensive analysis. The mean (SD) age at DBS implantation was 41.0 (11.4) years, and the follow-up period after implantation was 3.2 (3.8) years. The random effects model meta-analysis revealed that both physical and mental domains of SF-36 improved following DBS with a significantly larger effect size for the physical domains (effect size=0.781; p<0.0001) compared with the mental domains (effect size=0.533; p<0.0001). A moderator variable analysis demonstrated that effect sizes for HRQoL improvement were maintained over time. CONCLUSIONS: This is the first meta-analysis that demonstrates significant benefits in HRQoL following DBS in patients with inherited or idiopathic isolated dystonia. The benefits are greater for physical QoL domains compared with mental/psychological QoL. These findings highlight the importance of a comprehensive multidisciplinary approach to improve mental/psychological QoL.

A Comprehensive Review of Brain Connectomics and Imaging to Improve Deep Brain Stimulation Outcomes.

DBS is an effective neuromodulatory therapy that has been applied in various conditions, including PD, essential tremor, dystonia, Tourette syndrome, and other movement disorders. There have also been recent examples of applications in epilepsy, chronic pain, and neuropsychiatric conditions. Innovations in neuroimaging technology have been driving connectomics, an emerging whole-brain network approach to neuroscience. Two rising techniques are functional connectivity profiling and structural connectivity profiling. Functional connectivity profiling explores the operational relationships between multiple regions of the brain with respect to time and stimuli. Structural connectivity profiling approximates physical connections between different brain regions through reconstruction of axonal fibers. Through these techniques, complex relationships can be described in various disease states, such as PD, as well as in response to therapy, such as DBS. These advances have expanded our understanding of human brain function and have provided a partial in vivo glimpse into the underlying brain circuits underpinning movement and other disorders. This comprehensive review will highlight the contemporary concepts in brain connectivity as applied to DBS, as well as introduce emerging considerations in movement disorders. © 2020 International Parkinson and Movement Disorder Society.

Cannulation-Related Complications on Veno-Arterial Extracorporeal Membrane Oxygenation: Prevalence and Effect on Mortality.

Cannulation-related complications are a known source of morbidity in patients supported on veno-arterial extracorporeal membrane oxygenation (VA-ECMO). Despite its prevalence, little is known regarding the outcomes of patients who suffer such complications. This is a single institution review of cannulation-related complications and its effect on mortality in patients supported on VA-ECMO from January 2010-2015 using three cannulation strategies: axillary, femoral, and central. Complications were defined as advanced if they required major interventions (fasciotomy, amputation, site conversion). Patients were divided into two groups (complication present vs. not present) and Kaplan-Meier analysis was performed to determine any differences in their survival distributions. There were 103 patients supported on VA-ECMO: 41 (40%), 36 (35%), and 26 (25%) were cannulated via axillary, femoral, and central access, respectively. Cannulation-related complications occurred in 33 (32%) patients and this did not differ significantly between either axillary (34%), femoral (36%), or central (23%) strategies (P = 0.52). The most common complications encountered were hemorrhage and limb ischemia in 19 (18%) and 11 (11%) patients. Hemorrhagic complications did not differ between groups (P = 0.37), while limb ischemia and hyperperfusion were significantly associated with femoral and axillary cannulation, at a rate of 25% (P < 0.01) and 15% (P = 0.01), respectively. There was no difference in the incidence of advanced complications between cannulation groups: axillary (12%) vs. femoral (14%) vs. central (8%; P = 0.75). In addition, no increase in mortality was noted in patients who developed a cannulation-related complication by Kaplan-Meier estimates (P = 0.37). Cannulation-related complications affect a significant proportion of patients supported on VA-ECMO but do not differ in incidence between different cannulation strategies and do not affect patient mortality. Improved efforts at preventing these complications need to be developed to avoid the additional morbidity in an already critical patient population.

An Eye on the First Surgical Side: Appreciating the Potential Impacts of a Second DBS Lead on Ipsilateral Symptoms.

Clinical Vignette: A 63-year-old man with severe essential tremor underwent staged bilateral ventralis intermedius (Vim) deep brain stimulation (DBS). Left Vim DBS resulted in improved right upper extremity tremor control. Months later, the addition of right Vim DBS to the other brain hemisphere was associated with acute worsening of the right upper extremity tremor. Clinical Dilemma: In staged bilateral Vim DBS, second lead implantation may possibly alter ipsilateral tremor control. While ipsilateral improvement is common, rarely, it can disrupt previously achieved benefit. Clinical Solution: DBS programming, including an increase in left Vim DBS amplitude, re-established and enhanced bilateral tremor control. Gap in Knowledge: The mechanisms underlying changes in ipsilateral tremor control following a second lead implantation are unknown. In this case, worsening and subsequent improvement after optimization highlight the potential impact of DBS implantation on the ipsilateral side. Expert Commentary: After staged bilateral Vim DBS, clinicians should keep an eye on the first or original DBS side and carefully monitor for emergent side effects or worsening in tremor. Ipsilateral effects resulting from DBS implantation present a reprogramming opportunity with a potential to further optimize clinical outcomes. Highlights: This case report highlights the potential for ipsilateral tremor worsening following staged bilateral DBS and provides valuable insights into troubleshooting and reprogramming strategies. The report emphasizes the importance of vigilant monitoring and individualized management in optimizing clinical outcomes for patients undergoing staged bilateral DBS for essential tremor.

Characterizing Disease Progression in Parkinson's Disease from Videos of the Finger Tapping Test.

INTRODUCTION: Parkinson's disease (PD) is characterized by motor symptoms whose progression is typically assessed using clinical scales, namely the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Despite its reliability, the scale is bounded by a 5-point scale that limits its ability to track subtle changes in disease progression and is prone to subjective interpretations. We aimed to develop an automated system to objectively quantify motor symptoms in PD using Machine Learning (ML) algorithms to analyze videos and capture nuanced features of disease progression. METHODS: We analyzed videos of the Finger Tapping test, a component of the MDS-UPDRS, from 24 healthy controls and 66 PD patients using ML algorithms for hand pose estimation. We computed multiple movement features related to bradykinesia from videos and employed a novel tiered classification approach to predict disease severity that employed different features according to severity. We compared our video-based disease severity prediction approach against other approaches recently introduced in the literature. RESULTS: Traditional kinematics features such as amplitude and velocity changed linearly with disease severity, while other non-traditional features displayed non-linear trends. The proposed disease severity prediction approach demonstrated superior accuracy in detecting PD and distinguishing between different levels of disease severity when compared to existing approaches.

Current perspectives on tractography-guided deep brain stimulation for the treatment of mood disorders.

INTRODUCTION: Deep brain stimulation (DBS) is an emerging therapy for mood disorders, particularly treatment-resistant depression (TRD). Different brain areas implicated in depression-related brain networks have been investigated as DBS targets and variable clinical outcomes highlight the importance of target identification. Tractography has provided insight into how DBS modulates disorder-related brain networks and is being increasingly used to guide DBS for psychiatric disorders. AREAS COVERED: In this perspective, an overview of the current state of DBS for TRD and the principles of tractography is provided. Next, a comprehensive review of DBS targets is presented with a focus on tractography. Finally, the challenges and future directions of tractography-guided DBS are discussed. EXPERT OPINION: Tractography-guided DBS is a promising tool for improving DBS outcomes for mood disorders. Tractography is particularly useful for targeting patient-specific white matter tracts that are not visible using conventional structural MRI. Developments in tractography methods will help refine DBS targeting for TRD and may facilitate symptom-specific precision neuromodulation. Ultimately, the standardization of tractography methods will be essential to transforming DBS into an established therapy for mood disorders.

Preventing Shift from Pneumocephalus During Deep Brain Stimulation Surgery: Don't Give Up the 'Fork in the Brain'.

Clinical vignette: We present the case of a patient who developed intra-operative pneumocephalus during left globus pallidus internus deep brain stimulation (DBS) placement for Parkinson's disease (PD). Microelectrode recording (MER) revealed that we were anterior and lateral to the intended target. Clinical dilemma: Clinically, we suspected brain shift from pneumocephalus. Removal of the guide-tube for readjustment of the brain target would have resulted in the introduction of movement resulting from brain shift and from displacement from the planned trajectory. Clinical solution: We elected to leave the guide-tube cannula in place and to pass the final DBS lead into a channel that was located posterior-medially from the center microelectrode pass. Gap in knowledge: Surgical techniques which can be employed to minimize brain shift in the operating room setting are critical for reduction in variation of the final DBS lead placement. Pneumocephalus after dural opening is one potential cause of brain shift. The recognition that the removal of a guide-tube cannula could worsen brain shift creates an opportunity for an intraoperative team to maintain the advantage of the 'fork' in the brain provided by the initial procedure's requirement of guide-tube placement.

Active recharge biphasic stimulation for the intraoperative monopolar review in deep brain stimulation.

Introduction: Charge balancing is used in deep brain stimulation (DBS) to avoid net charge accumulation at the tissue-electrode interface that can result in neural damage. Charge balancing paradigms include passive recharge and active recharge. In passive recharge, each cathodic pulse is accompanied by a waiting period before the next stimulation, whereas active recharge uses energy to deliver symmetric anodic and cathodic stimulation pulses sequentially, producing a net zero charge. We sought to determine differences in stimulation induced side effect thresholds between active vs. passive recharge during the intraoperative monopolar review. Methods: Sixty-five consecutive patients undergoing DBS from 2021 to 2022 were retrospectively reviewed. Intraoperative monopolar review was performed with both active recharge and passive recharge for all included patients to determine side effect stimulation thresholds. Sixteen patients with 64 total DBS contacts met inclusion criteria for further analysis. Intraoperative monopolar review results were compared with the monopolar review from the first DBS programming visit. Results: The mean intraoperative active recharge stimulation threshold was 4.1 mA, while the mean intraoperative passive recharge stimulation threshold was 3.9 mA, though this difference was not statistically significant on t-test (p = 0.442). Mean stimulation threshold at clinic follow-up was 3.2 mA. In Pearson correlation, intraoperative passive recharge thresholds had stronger correlation with follow-up stimulation thresholds (Pearson r = 0.5281, p < 0.001) than intraoperative active recharge (Pearson r = 0.340, p = 0.018), however the difference between these correlations was not statistically significant on Fisher Z correlation test (p = 0.294). The mean difference between intraoperative passive recharge stimulation threshold and follow-up stimulation threshold was 0.8 mA, while the mean difference between intraoperative active recharge threshold and follow-up threshold was 1.2 mA. This difference was not statistically significant on a t-test (p = 0.134). Conclusions: Both intraoperative active recharge and passive recharge stimulation were well-correlated with the monopolar review at the first programming visit. No statistically significant differences were observed suggesting that either passive or active recharge may be utilized intraoperatively.

Corrigendum: Modeling the volume of tissue activated in deep brain stimulation and its clinical influence: a review.

[This corrects the article DOI: 10.3389/fnhum.2024.1333183.].

Modeling the volume of tissue activated in deep brain stimulation and its clinical influence: a review.

Deep brain stimulation (DBS) is a neuromodulatory therapy that has been FDA approved for the treatment of various disorders, including but not limited to, movement disorders (e.g., Parkinson's disease and essential tremor), epilepsy, and obsessive-compulsive disorder. Computational methods for estimating the volume of tissue activated (VTA), coupled with brain imaging techniques, form the basis of models that are being generated from retrospective clinical studies for predicting DBS patient outcomes. For instance, VTA models are used to generate target-and network-based probabilistic stimulation maps that play a crucial role in predicting DBS treatment outcomes. This review defines the methods for calculation of tissue activation (or modulation) including ones that use heuristic and clinically derived estimates and more computationally involved ones that rely on finite-element methods and biophysical axon models. We define model parameters and provide a comparison of commercial, open-source, and academic simulation platforms available for integrated neuroimaging and neural activation prediction. In addition, we review clinical studies that use these modeling methods as a function of disease. By describing the tissue-activation modeling methods and highlighting their application in clinical studies, we provide the neural engineering and clinical neuromodulation communities with perspectives that may influence the adoption of modeling methods for future DBS studies.

Management of essential tremor deep brain stimulation-induced side effects.

Deep brain stimulation (DBS) is an effective surgical therapy for carefully selected patients with medication refractory essential tremor (ET). The most popular anatomical targets for ET DBS are the ventral intermedius nucleus (VIM) of the thalamus, the caudal zona incerta (cZI) and the posterior subthalamic area (PSA). Despite extensive knowledge in DBS programming for tremor suppression, it is not uncommon to experience stimulation induced side effects related to DBS therapy. Dysarthria, dysphagia, ataxia, and gait impairment are common stimulation induced side effects from modulation of brain tissue that surround the target of interest. In this review, we explore current evidence about the etiology of stimulation induced side effects in ET DBS and provide several evidence-based strategies to troubleshoot, reprogram and retain tremor suppression.

TGF-ß signalling limits effector function capacity of NK cell anti-tumour immunity in human bladder cancer.

BACKGROUND: Natural killer (NK) cells are important innate immunity players and have unique abilities to recognize and eliminate cancer cells, particularly in settings of antibody-opsonization and antibody-dependant cellular cytotoxicity (ADCC). However, NK cell-based responses in bladder cancers to therapeutic antibodies are typically immunosuppressed, and these immunosuppressive mechanisms are largely unknown. METHODS: Single cell RNA sequencing (scRNA-seq) and high-dimensional flow cytometry were used to investigate the phenotype of tumour-infiltrating NK cells in patients with bladder cancer. Further, in vitro, and in vivo models of this disease were used to validate these findings. FINDINGS: NK cells within bladder tumours displayed reduced expression of FcγRIIIa/CD16, the critical Fc receptor involved in ADCC-mediated cytotoxicity, on both transcriptional and protein levels. Transcriptional signatures of transforming growth factor (TGF)-ß-signalling, a pleiotropic cytokine known for its immunosuppressive and tissue residency-inducing effects, were upregulated in tumour-infiltrating NK cells. TGF-ß mediated CD16 downregulation on NK cells, was further validated in vitro, which was accompanied by a transition into a tissue residency phenotype. This CD16 downregulation was also abrogated by TGF-ßR signalling inhibition, which could also restore the ADCC ability of NK cells subject to TGF-ß effects. In a humanized mouse model of bladder cancer, mice treated with a TGF-ß inhibitor exhibited increased ADCC activity compared to mice treated only with antibodies. INTERPRETATION: This study highlights how TGF-ß-rich bladder cancers inhibit NK cell-mediated ADCC by downregulating CD16. TGF-ß inhibition represents new avenues to reverse immunosuppression and enhance the tumoricidal capacity of NK cells in bladder cancer. FUNDING: The Guimaraes Laboratory is funded by a US Department of Defense-Breast Cancer Research Program-Breakthrough Award Level 1 (#BC200025), a grant (#2019485) awarded through the Medical Research Future Fund (MRFF, with the support of the Queensland Children's Hospital Foundation, Microba Life Sciences, Richie's Rainbow Foundation, Translational Research Institute (TRI) and UQ), and a grant (#RSS_2023_085) funded by a Metro South Health Research Support Scheme. J.K.M.W. is funded by a UQ Research Training Program PhD Scholarship and N.O. is funded by a NHMRC Postgraduate Scholarship (#2021932).

Chronic intracranial recordings in the globus pallidus reveal circadian rhythms in Parkinson's disease.

Circadian rhythms have been shown in the subthalamic nucleus (STN) in Parkinson's disease (PD), but only a few studies have focused on the globus pallidus internus (GPi). This retrospective study investigates GPi circadian rhythms in a large cohort of subjects with PD (130 recordings from 93 subjects) with GPi activity chronically recorded in their home environment. We found a significant change in GPi activity between daytime and nighttime in most subjects (82.4%), with a reduction in GPi activity at nighttime in 56.2% of recordings and an increase in activity in 26.2%. GPi activity in higher frequency bands ( > 20 Hz) was more likely to decrease at night and in patients taking extended-release levodopa medication. Our results suggest that circadian fluctuations in the GPi vary across individuals and that increased power at night might be due to the reemergence of pathological neural activity. These findings should be considered to ensure successful implementation of adaptive neurostimulation paradigms in the real-world.

Proceedings of the 11th Annual Deep Brain Stimulation Think Tank: pushing the forefront of neuromodulation with functional network mapping, biomarkers for adaptive DBS, bioethical dilemmas, AI-guided neuromodulation, and translational advancements.

The Deep Brain Stimulation (DBS) Think Tank XI was held on August 9-11, 2023 in Gainesville, Florida with the theme of "Pushing the Forefront of Neuromodulation". The keynote speaker was Dr. Nico Dosenbach from Washington University in St. Louis, Missouri. He presented his research recently published in Nature inn a collaboration with Dr. Evan Gordon to identify and characterize the somato-cognitive action network (SCAN), which has redefined the motor homunculus and has led to new hypotheses about the integrative networks underpinning therapeutic DBS. The DBS Think Tank was founded in 2012 and provides an open platform where clinicians, engineers, and researchers (from industry and academia) can freely discuss current and emerging DBS technologies, as well as logistical and ethical issues facing the field. The group estimated that globally more than 263,000 DBS devices have been implanted for neurological and neuropsychiatric disorders. This year's meeting was focused on advances in the following areas: cutting-edge translational neuromodulation, cutting-edge physiology, advances in neuromodulation from Europe and Asia, neuroethical dilemmas, artificial intelligence and computational modeling, time scales in DBS for mood disorders, and advances in future neuromodulation devices.

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.