Validation and application of computer vision algorithms for video-based tremor analysis.

Tremor is one of the most common neurological symptoms. Its clinical and neurobiological complexity necessitates novel approaches for granular phenotyping. Instrumented neurophysiological analyses have proven useful, but are highly resource-intensive and lack broad accessibility. In contrast, bedside scores are simple to administer, but lack the granularity to capture subtle but relevant tremor features. We utilise the open-source computer vision pose tracking algorithm Mediapipe to track hands in clinical video recordings and use the resulting time series to compute canonical tremor features. This approach is compared to marker-based 3D motion capture, wrist-worn accelerometry, clinical scoring and a second, specifically trained tremor-specific algorithm in two independent clinical cohorts. These cohorts consisted of 66 patients diagnosed with essential tremor, assessed in different task conditions and states of deep brain stimulation therapy. We find that Mediapipe-derived tremor metrics exhibit high convergent clinical validity to scores (Spearman's ρ = 0.55-0.86, p≤ .01) as well as an accuracy of up to 2.60 mm (95% CI [-3.13, 8.23]) and ≤0.21 Hz (95% CI [-0.05, 0.46]) for tremor amplitude and frequency measurements, matching gold-standard equipment. Mediapipe, but not the disease-specific algorithm, was capable of analysing videos involving complex configurational changes of the hands. Moreover, it enabled the extraction of tremor features with diagnostic and prognostic relevance, a dimension which conventional tremor scores were unable to provide. Collectively, this demonstrates that current computer vision algorithms can be transformed into an accurate and highly accessible tool for video-based tremor analysis, yielding comparable results to gold standard tremor recordings.

Head movement dynamics in dystonia: a multi-centre retrospective study using visual perceptive deep learning.

Dystonia is a neurological movement disorder characterised by abnormal involuntary movements and postures, particularly affecting the head and neck. However, current clinical assessment methods for dystonia rely on simplified rating scales which lack the ability to capture the intricate spatiotemporal features of dystonic phenomena, hindering clinical management and limiting understanding of the underlying neurobiology. To address this, we developed a visual perceptive deep learning framework that utilizes standard clinical videos to comprehensively evaluate and quantify disease states and the impact of therapeutic interventions, specifically deep brain stimulation. This framework overcomes the limitations of traditional rating scales and offers an efficient and accurate method that is rater-independent for evaluating and monitoring dystonia patients. To evaluate the framework, we leveraged semi-standardized clinical video data collected in three retrospective, longitudinal cohort studies across seven academic centres. We extracted static head angle excursions for clinical validation and derived kinematic variables reflecting naturalistic head dynamics to predict dystonia severity, subtype, and neuromodulation effects. The framework was also applied to a fully independent cohort of generalised dystonia patients for comparison between dystonia sub-types. Computer vision-derived measurements of head angle excursions showed a strong correlation with clinically assigned scores. Across comparisons, we identified consistent kinematic features from full video assessments encoding information critical to disease severity, subtype, and effects of neural circuit interventions, independent of static head angle deviations used in scoring. Our visual perceptive machine learning framework reveals kinematic pathosignatures of dystonia, potentially augmenting clinical management, facilitating scientific translation, and informing personalized precision neurology approaches.

Deep brain stimulation of symptom-specific networks in Parkinson's disease.

Deep Brain Stimulation can improve tremor, bradykinesia, rigidity, and axial symptoms in patients with Parkinson's disease. Potentially, improving each symptom may require stimulation of different white matter tracts. Here, we study a large cohort of patients (N = 237 from five centers) to identify tracts associated with improvements in each of the four symptom domains. Tremor improvements were associated with stimulation of tracts connected to primary motor cortex and cerebellum. In contrast, axial symptoms are associated with stimulation of tracts connected to the supplementary motor cortex and brainstem. Bradykinesia and rigidity improvements are associated with the stimulation of tracts connected to the supplementary motor and premotor cortices, respectively. We introduce an algorithm that uses these symptom-response tracts to suggest optimal stimulation parameters for DBS based on individual patient's symptom profiles. Application of the algorithm illustrates that our symptom-tract library may bear potential in personalizing stimulation treatment based on the symptoms that are most burdensome in an individual patient.

Mapping dysfunctional circuits in the frontal cortex using deep brain stimulation.

Frontal circuits play a critical role in motor, cognitive and affective processing, and their dysfunction may result in a variety of brain disorders. However, exactly which frontal domains mediate which (dys)functions remains largely elusive. We studied 534 deep brain stimulation electrodes implanted to treat four different brain disorders. By analyzing which connections were modulated for optimal therapeutic response across these disorders, we segregated the frontal cortex into circuits that had become dysfunctional in each of them. Dysfunctional circuits were topographically arranged from occipital to frontal, ranging from interconnections with sensorimotor cortices in dystonia, the primary motor cortex in Tourette's syndrome, the supplementary motor area in Parkinson's disease, to ventromedial prefrontal and anterior cingulate cortices in obsessive-compulsive disorder. Our findings highlight the integration of deep brain stimulation with brain connectomics as a powerful tool to explore couplings between brain structure and functional impairments in the human brain.

GPi-DBS-induced brain metabolic activation in cervical dystonia.

BACKGROUND: Deep brain stimulation (DBS) of the globus pallidus interna (GPi) is a highly efficacious treatment for cervical dystonia, but its mechanism of action is not fully understood. Here, we investigate the brain metabolic effects of GPi-DBS in cervical dystonia. METHODS: Eleven patients with GPi-DBS underwent brain 18F-fluorodeoxyglucose positron emission tomography imaging during stimulation on and off. Changes in regional brain glucose metabolism were investigated at the active contact location and across the whole brain. Changes in motor symptom severity were quantified using the Toronto Western Spasmodic Torticollis Rating Scale (TWSTRS), executive function using trail making test (TMT) and parkinsonism using Unified Parkinson's Disease Rating Scale (UPDRS). RESULTS: The mean (SD) best therapeutic response to DBS during the treatment was 81 (22)%. The TWSTRS score was 3.2 (3.9) points lower DBS on compared with off (p=0.02). At the stimulation site, stimulation was associated with increased metabolism, which correlated with DBS stimulation amplitude (r=0.70, p=0.03) but not with changes in motor symptom severity (p>0.9). In the whole brain analysis, stimulation increased metabolism in the GPi, subthalamic nucleus, putamen, primary sensorimotor cortex (PFDR<0.05). Acute improvement in TWSTRS correlated with metabolic activation in the sensorimotor cortex and overall treatment response in the supplementary motor area. Worsening of TMT-B score was associated with activation of the anterior cingulate cortex and parkinsonism with activation in the putamen. CONCLUSIONS: GPi-DBS increases metabolic activity at the stimulation site and sensorimotor network. The clinical benefit and adverse effects are mediated by modulation of specific networks.

Wavelet-Based Bracketing, Time-Frequency Beta Burst Detection: New Insights in Parkinson's Disease.

Studies have shown that beta band activity is not tonically elevated but comprises exaggerated phasic bursts of varying durations and magnitudes, for Parkinson's disease (PD) patients. Current methods for detecting beta bursts target a single frequency peak in beta band, potentially ignoring bursts in the wider beta band. In this study, we propose a new robust framework for beta burst identification across wide frequency ranges. Chronic local field potential at-rest recordings were obtained from seven PD patients implanted with Medtronic SenSight™ deep brain stimulation (DBS) electrodes. The proposed method uses wavelet decomposition to compute the time-frequency spectrum and identifies bursts spanning multiple frequency bins by thresholding, offering an additional burst measure, ∆f, that captures the width of a burst in the frequency domain. Analysis included calculating burst duration, magnitude, and ∆f and evaluating the distribution and likelihood of bursts between the low beta (13-20 Hz) and high beta (21-35 Hz). Finally, the results of the analysis were correlated to motor impairment (MDS-UPDRS III) med off scores. We found that low beta bursts with longer durations and larger width in the frequency domain (∆f) were positively correlated, while high beta bursts with longer durations and larger ∆f were negatively correlated with motor impairment. The proposed method, finding clear differences between bursting behavior in high and low beta bands, has clearly demonstrated the importance of considering wide frequency bands for beta burst behavior with implications for closed-loop DBS paradigms.

Machine versus physician-based programming of deep brain stimulation in isolated dystonia: A feasibility study.

BACKGROUND: Deep brain stimulation of the internal globus pallidus effectively alleviates dystonia motor symptoms. However, delayed symptom control and a lack of therapeutic biomarkers and a single pallidal sweetspot region complicates optimal programming. Postoperative management is complex, typically requiring multiple, lengthy follow-ups with an experienced physician - an important barrier to widespread adoption in medication-refractory dystonia patients. OBJECTIVE: Here we prospectively tested the best machine-predicted programming settings in a dystonia cohort treated with GPi-DBS against the settings derived from clinical long-term care in a specialised DBS centre. METHODS: Previously, we reconstructed an anatomical map of motor improvement probability across the pallidal region using individual stimulation volumes and clinical outcomes in dystonia patients. We used this to develop an algorithm that tests in silico thousands of putative stimulation settings in de novo patients after reconstructing an individual, image-based anatomical model of electrode positions, and suggests stimulation parameters with the highest likelihood of optimal symptom control. To test real-life application, our prospective study compared results in 10 patients against programming settings derived from long-term care. RESULTS: In this cohort, dystonia symptom reduction was observed at 74.9 ± 15.3% with C-SURF programming as compared to 66.3 ± 16.3% with clinical programming (p < 0.012). The average total electrical energy delivered (TEED) was similar for both the clinical and C-SURF programming (262.0 µJ/s vs. 306.1 µJ/s respectively). CONCLUSION: Our findings highlight the clinical potential of machine-based programming in dystonia, which could markedly reduce the programming burden in postoperative management.

Formation of giant iron oxide-copper-gold deposits by superimposed episodic hydrothermal pulses.

Iron oxide-copper-gold (IOCG) deposits are a globally important source of copper, gold and critical commodities. Despite their relevance, IOCG deposits remain an ill-defined clan, with a range of characteristics that has complicated development of the general genetic model. Here we focus on the Candelaria IOCG deposit in Chile and reveal that by using micro-textural and compositional variations in actinolite, a common alteration mineral found in many IOCG deposits, we can constrain the evolution of these systems. We demonstrate that Candelaria formed by the superposition of at least two pulses of mineralization with a late Cu-rich event overprinting and superimposed over an early, and probably higher temperature, iron oxide-apatite (IOA) mineralization event. These distinct pulses were likely caused by episodic injections of magmatic-hydrothermal fluids from crystallizing magmas at depth. Our data provide empirical evidence of grain-to-deposit scale compositional and potentially temperature changes in an IOCG system. The results support the use of actinolite chemistry as a novel approach to understand the formation of IOCG deposits and a potential tool for vectoring in exploration.

Quantifying the Variability Associated with Postoperative Localization of Deep Brain Stimulation Electrodes.

INTRODUCTION: Computational models of deep brain stimulation (DBS) have become common tools in clinical research studies that attempt to establish correlations between stimulation locations in the brain and behavioral outcome measures. However, the accuracy of any patient-specific DBS model depends heavily upon accurate localization of the DBS electrodes within the anatomy, which is typically defined via co-registration of clinical CT and MRI datasets. Several different approaches exist for this challenging registration problem, and each approach will result in a slightly different electrode localization. The goal of this study was to better understand how different processing steps (e.g., cost-function masking, brain extraction, intensity remapping) affect the estimate of the DBS electrode location in the brain. METHODS: No "gold standard" exists for this kind of analysis, as the exact location of the electrode in the living human brain cannot be determined with existing clinical imaging approaches. However, we can estimate the uncertainty associated with the electrode position, which can be used to guide statistical analyses in DBS mapping studies. Therefore, we used high-quality clinical datasets from 10 subthalamic DBS subjects and co-registered their long-term postoperative CT with their preoperative surgical targeting MRI using 9 different approaches. The distances separating all of the electrode location estimates were calculated for each subject. RESULTS: On average, electrodes were located within a median distance of 0.57 mm (0.49-0.74) of one another across the different registration approaches. However, when considering electrode location estimates from short-term postoperative CTs, the median distance increased to 2.01 mm (1.55-2.78). CONCLUSIONS: The results of this study suggest that electrode location uncertainty needs to be factored into statistical analyses that attempt to define correlations between stimulation locations and clinical outcomes.

Imaging the spin: Disentangling the core processes underlying mental rotation by network mapping of data from meta-analysis.

Research on the mental rotation task has sparked debate regarding the specific processes that underly the capability of humans to mentally rotate objects. The spread of reported brain activations suggests that mental rotation is subserved by a neural network circle. However, no common network has yet been found that uncovers the crucial processes underlying this ability. We aimed to identify the common network crucial for mental rotation by coordinate-based network mapping of previous neuroimaging findings in mental rotation. A meta-analysis revealed 710 peak activation coordinates from 42 fMRI studies in mental rotation, which include a total 844 participants. The coordinates were mapped to a normative functional connectome (n = 1000) to identify a network of connected regions. To account for experimental factors, we examined this network against two control tasks, action imitation and symbolic number processing. A common and crucial network for mental rotation, centring on dorsal premotor, superior parietal and inferior temporal lobes was revealed. This network, separated from other experimental aspects, suggests that the crucial processes underlying mental rotation are motor rotation, visuospatial processing, and higher order visual object recognition.

Distinct phenotypes of stimulation-induced dysarthria represent different cortical networks in STN-DBS.

BACKGROUND: Deep brain stimulation of the subthalamic nucleus is an effective treatment of Parkinson's disease, yet it is often associated with a general deterioration of speech intelligibility. Clustering the phenotypes of dysarthria has been proposed as a strategy to tackle these stimulation-induced speech problems. METHODS: In this study, we examine a cohort of 24 patients to test the real-life application of the proposed clustering and attempt to attribute the clusters to specific brain networks with two different approaches of connectivity analysis. RESULTS: Both our data-driven and hypothesis-driven approaches revealed strong connections of variants of stimulation-induced dysarthria to brain regions that are known actors of motor speech control. We showed a strong connection between the spastic dysarthria type and the precentral gyrus and supplementary motor area, prompting a possible disruption of corticobulbar fibers. The connection between the strained voice dysarthria and more frontal areas hints toward a deeper disruption of the motor programming of speech production. CONCLUSIONS: These results provide insights into the mechanism of stimulation-induced dysarthria in deep brain stimulation of the subthalamic nucleus and may guide reprogramming attempts for individual Parkinson's patients based on pathophysiological understanding of the affected networks.

Mapping Dysfunctional Circuits in the Frontal Cortex Using Deep Brain Stimulation.

Frontal circuits play a critical role in motor, cognitive, and affective processing - and their dysfunction may result in a variety of brain disorders. However, exactly which frontal domains mediate which (dys)function remains largely elusive. Here, we study 534 deep brain stimulation electrodes implanted to treat four different brain disorders. By analyzing which connections were modulated for optimal therapeutic response across these disorders, we segregate the frontal cortex into circuits that became dysfunctional in each of them. Dysfunctional circuits were topographically arranged from occipital to rostral, ranging from interconnections with sensorimotor cortices in dystonia, with the primary motor cortex in Tourette's syndrome, the supplementary motor area in Parkinson's disease, to ventromedial prefrontal and anterior cingulate cortices in obsessive-compulsive disorder. Our findings highlight the integration of deep brain stimulation with brain connectomics as a powerful tool to explore couplings between brain structure and functional impairment in the human brain.

Lead location as a determinant of motor benefit in subthalamic nucleus deep brain stimulation for Parkinson's disease.

Background: Subthalamic nucleus (STN) deep brain stimulation (DBS) is regarded as an effective treatment for patients with advanced Parkinson's disease (PD). Clinical benefit, however, varies significantly across patients. Lead location has been hypothesized to play a critical role in determining motor outcome and may account for much of the observed variability reported among patients. Objective: To retrospectively evaluate the relationship of lead location to motor outcomes in patients who had been implanted previously at another center by employing a novel visualization technology that more precisely determines the location of the DBS lead and its contacts with respect to each patient's individually defined STN. Methods: Anatomical models were generated using novel imaging in 40 PD patients who had undergone bilateral STN DBS (80 electrodes) at another center. Patient-specific models of each STN were evaluated to determine DBS electrode contact locations with respect to anterior to posterior and medial to lateral regions of the individualized STNs and compared to the change in the contralateral hemi-body Unified Parkinson's Disease Rating Scale Part III (UPDRS-III) motor score. Results: The greatest improvement in hemi-body motor function was found when active contacts were located within the posterolateral portion of the STN (71.5%). Motor benefit was 52 and 36% for central and anterior segments, respectively. Active contacts within the posterolateral portion also demonstrated the greatest reduction in levodopa dosage (77%). Conclusion: The degree of motor benefit was dependent on the location of the stimulating contact within the STN. Although other factors may play a role, we provide further evidence in support of the hypothesis that lead location is a critical factor in determining clinical outcomes in STN DBS.

Linking profiles of pathway activation with clinical motor improvements - A retrospective computational study.

BACKGROUND: Deep brain stimulation (DBS) is an established therapy for patients with Parkinson's disease. In silico computer models for DBS hold the potential to inform a selection of stimulation parameters. In recent years, the focus has shifted towards DBS-induced firing in myelinated axons, deemed particularly relevant for the external modulation of neural activity. OBJECTIVE: The aim of this project was to investigate correlations between patient-specific pathway activation profiles and clinical motor improvement. METHODS: We used the concept of pathway activation modeling, which incorporates advanced volume conductor models and anatomically authentic fiber trajectories to estimate DBS-induced action potential initiation in anatomically plausible pathways that traverse in close proximity to targeted nuclei. We applied the method on two retrospective datasets of DBS patients, whose clinical improvement had been evaluated according to the motor part of the Unified Parkinson's Disease Rating Scale. Based on differences in outcome and activation levels for intrapatient DBS protocols in a training cohort, we derived a pathway activation profile that theoretically induces a complete alleviation of symptoms described by UPDRS-III. The profile was further enhanced by analyzing the importance of matching activation levels for individual pathways. RESULTS: The obtained profile emphasized the importance of activation in pathways descending from the motor-relevant cortical regions as well as the pallidothalamic pathways. The degree of similarity of patient-specific profiles to the optimal profile significantly correlated with clinical motor improvement in a test cohort. CONCLUSION: Pathway activation modeling has a translational utility in the context of motor symptom alleviation in Parkinson's patients treated with DBS.

Troubleshooting Gait Disturbances in Parkinson's Disease With Deep Brain Stimulation.

Deep brain stimulation (DBS) of the subthalamic nucleus or the globus pallidus is an established treatment for Parkinson's disease (PD) that yields a marked and lasting improvement of motor symptoms. Yet, DBS benefit on gait disturbances in PD is still debated and can be a source of dissatisfaction and poor quality of life. Gait disturbances in PD encompass a variety of clinical manifestations and rely on different pathophysiological bases. While gait disturbances arising years after DBS surgery can be related to disease progression, early impairment of gait may be secondary to treatable causes and benefits from DBS reprogramming. In this review, we tackle the issue of gait disturbances in PD patients with DBS by discussing their neurophysiological basis, providing a detailed clinical characterization, and proposing a pragmatic programming approach to support their management.

Optimal deep brain stimulation sites and networks for cervical vs. generalized dystonia.

Dystonia is a debilitating disease with few treatment options. One effective option is deep brain stimulation (DBS) to the internal pallidum. While cervical and generalized forms of isolated dystonia have been targeted with a common approach to the posterior third of the nucleus, large-scale investigations regarding optimal stimulation sites and potential network effects have not been carried out. Here, we retrospectively studied clinical results following DBS for cervical and generalized dystonia in a multicenter cohort of 80 patients. We model DBS electrode placement based on pre- and postoperative imaging and introduce an approach to map optimal stimulation sites to anatomical space. Second, we investigate which tracts account for optimal clinical improvements, when modulated. Third, we investigate distributed stimulation effects on a whole-brain functional connectome level. Our results show marked differences of optimal stimulation sites that map to the somatotopic structure of the internal pallidum. While modulation of the striatopallidofugal axis of the basal ganglia accounted for optimal treatment of cervical dystonia, modulation of pallidothalamic bundles did so in generalized dystonia. Finally, we show a common multisynaptic network substrate for both phenotypes in the form of connectivity to the cerebellum and somatomotor cortex. Our results suggest a brief divergence of optimal stimulation networks for cervical vs. generalized dystonia within the pallidothalamic loop that merge again on a thalamo-cortical level and share a common whole-brain network.

Deep Brain Stimulation for Arm Tremor: A Randomized Trial Comparing Two Targets.

OBJECTIVE: Deep brain stimulation (DBS) of the thalamic ventral intermediate nucleus (VIM) effectively suppresses arm tremor. Uncontrolled studies suggest the posterior subthalamic area (PSA) may be superior. We compared the intra-individual efficacy of VIM- versus PSA-DBS on tremor suppression and arm function. METHODS: We performed a randomized, double-blind, crossover trial at Oslo University Hospital in patients (18-80 years) with isolated or combined action tremor affecting at least one arm. Four-contact DBS leads were implanted (bi- or unilaterally) with a trajectory to cover the VIM (upper two contacts) and PSA (lower two contacts). Patients were randomized (1:1 ratio) post-surgery to: Group 1, VIM-stimulation months 0-3 (period 1), then PSA-stimulation months 4-6 (period 2); Group 2, PSA-stimulation first, then VIM-stimulation. Primary endpoint was the difference in improvement from baseline to the end of the VIM- versus PSA-period in the sum of the dominant arm tremor scores of the Fahn-Tolosa-Marin Tremor Rating Scale (FTMTRS), items 5/6 + 10-14. RESULTS: Forty-five patients were randomized to Group 1 (n = 23) or 2 (n = 22). In the primary endpoint per-protocol analysis (mixed model, n = 40), mean difference in the sum FTMTRS score improvement for the dominant arm was -2.65 points (95% CI -4.33 to -0.97; p = 0.002). The difference in favour of PSA stimulation was highly significant in period 2, but not period 1. INTERPRETATION: Our randomized trial demonstrated that PSA stimulation provided superior tremor suppression compared with VIM stimulation. A period effect reducing tremor for up to three months in both groups was most likely attributed to a post-surgery stun effect. ANN NEUROL 2022;91:585-601.

Current-dependent ocular tilt reaction in deep brain stimulation of the subthalamic nucleus: Evidence for an incerto-interstitial pathway?

BACKGROUND AND PURPOSE: The aim was to characterize a combined vestibular, ocular motor and postural syndrome induced by deep brain stimulation (DBS) of the subthalamic nucleus in a patient with Parkinson's disease. METHODS: In a systematic DBS programming session, eye, head and trunk position in roll and pitch plane were documented as a function of stimulation amplitude and field direction. Repeat ocular coherence tomography was used to estimate ocular torsion. The interstitial nucleus of Cajal (INC), zona incerta (ZI) and ascending vestibular fibre tracts were segmented on magnetic resonance imaging using both individual and normative structural connectomic data. Thresholded symptom-associated volumes of tissue activated (VTA) were calculated based on documented stimulation parameters. RESULTS: Ipsilateral ocular tilt reaction and body lateropulsion as well as contralateral torsional nystagmus were elicited by the right electrode in a current-dependent manner and subsided after DBS deactivation. With increasing currents, binocular tonic upgaze and body retropulsion were observed. Symptoms were consistent with an irritative effect on the INC. Symptom-associated VTA was found to overlap with the dorsal ZI and the ipsilateral vestibulothalamic tract, while lying rather distant to the INC proper. A ZI-to-INC 'incerto-interstitial' tract with contact to the medial-uppermost portion of the VTA could be traced. CONCLUSION: Unilateral stimulation of INC-related circuitry induces an ipsilateral vestibular, ocular motor and postural roll-plane syndrome, which converts into a pitch-plane syndrome when functional activation expands bilaterally. In this case, tractography points to an incerto-interstitial pathway, a tract previously only characterized in non-human primates. Directional current steering proved useful in managing this rare side effect.

A brain network for deep brain stimulation induced cognitive decline in Parkinson's disease.

Deep brain stimulation is an effective treatment for Parkinson's disease but can be complicated by side-effects such as cognitive decline. There is often a delay before this side-effect is apparent and the mechanism is unknown, making it difficult to identify patients at risk or select appropriate deep brain stimulation settings. Here, we test whether connectivity between the stimulation site and other brain regions is associated with cognitive decline following deep brain stimulation. First, we studied a unique patient cohort with cognitive decline following subthalamic deep brain stimulation for Parkinson's disease (n = 10) where reprogramming relieved the side-effect without loss of motor benefit. Using resting state functional connectivity data from a large normative cohort (n = 1000), we computed connectivity between each stimulation site and the subiculum, an a priori brain region functionally connected to brain lesions causing memory impairment. Connectivity between deep brain stimulation sites and this same subiculum region was significantly associated with deep brain stimulation induced cognitive decline (P < 0.02). We next performed a data-driven analysis to identify connections most associated with deep brain stimulation induced cognitive decline. Deep brain stimulation sites causing cognitive decline (versus those that did not) were more connected to the anterior cingulate, caudate nucleus, hippocampus, and cognitive regions of the cerebellum (PFWE < 0.05). The spatial topography of this deep brain stimulation-based circuit for cognitive decline aligned with an a priori lesion-based circuit for memory impairment (P = 0.017). To begin translating these results into a clinical tool that might be used for deep brain stimulation programming, we generated a 'heat map' in which the intensity of each voxel reflects the connectivity to our cognitive decline circuit. We then validated this heat map using an independent dataset of Parkinson's disease patients in which cognitive performance was measured following subthalamic deep brain stimulation (n = 33). Intersection of deep brain stimulation sites with our heat map was correlated with changes in the Mattis dementia rating scale 1 year after lead implantation (r = 0.39; P = 0.028). Finally, to illustrate how this heat map might be used in clinical practice, we present a case that was flagged as 'high risk' for cognitive decline based on intersection of the patient's deep brain stimulation site with our heat map. This patient had indeed experienced cognitive decline and our heat map was used to select alternative deep brain stimulation parameters. At 14 days follow-up the patient's cognition improved without loss of motor benefit. These results lend insight into the mechanism of deep brain stimulation induced cognitive decline and suggest that connectivity-based heat maps may help identify patients at risk and who might benefit from deep brain stimulation reprogramming.