The Role of Large-Scale Data Infrastructure in Developing Next-Generation Deep Brain Stimulation Therapies

Abstract

Advances in neuromodulation technologies hold the promise of treating a patient’s unique brain network pathology using personalized stimulation patterns. In service of these goals, neuromodulation clinical trials using sensing-enabled devices are routinely generating large multi-modal datasets. However, with the expansion of data acquisition also comes an increasing difficulty to store, manage, and analyze the associated datasets, which integrate complex neural and wearable time-series data with dynamic assessments of patients’ symptomatic state. Here, we discuss a scalable cloud-based data platform that enables ingestion, aggregation, storage, query, and analysis of multi-modal neurotechnology datasets. This large-scale data infrastructure will accelerate translational neuromodulation research and enable the development and delivery of next-generation deep brain stimulation therapies.

Proceedings of the 10th annual deep brain stimulation think tank: Advances in cutting edge technologies, artificial intelligence, neuromodulation, neuroethics, interventional psychiatry, and women in neuromodulation

“…Patients with PD can experience residual motor fluctuations during optimized continuous deep brain stimulation (cDBS). Previous in-clinic and short at-home studies have suggested that adaptive DBS (aDBS), i.e., titrating stimulation amplitude in response to symptom-state-associated neural signals (i.e., biomarkers), could possibly alleviate residual symptoms (Little et al, 2013;Arlotti et al, 2018;Gilron et al, 2021a). It has been uncertain if these results can be replicated at-home for sustained periods.…”

“…These multimodal datasets can possibly be incorporated into routine clinical care to inform decisions about DBS – from patient selection, to DBS programming, to adaptive DBS ( Gilron et al, 2021a , b ; Fleming et al, 2022 ). However, collection and integration of these data require the development of new tools ( Chen et al, 2021a ). Using Rune Labs, we show an example of one patient who was continuously monitored for an entire year before and after implantation using a sensing enabled DBS, and we highlight ways in which this dataset paints a rich picture as compared to standard clinical scales.…”

In-Home Video and IMU Kinematics of Self Guided Tasks Correlate with Clinical Bradykinesia Scores

“…Three axes of accelerometry and gyroscope data were both collected at 50Hz. Recordings were automatically uploaded to a protected health information (PHI)-compliant third-party server (Rune Labs, Inc) [18], from which the data were later accessed for analysis.…”

Proceedings of the Ninth Annual Deep Brain Stimulation Think Tank: Advances in Cutting Edge Technologies, Artificial Intelligence, Neuromodulation, Neuroethics, Pain, Interventional Psychiatry, Epilepsy, and Traumatic Brain Injury

“…Overall, the recent widespread availability of LFP sensing technology embedded in commercial DBS devices offers unprecedented access to objective real-world data and promises a faster path to personalized care for DBS patients. Nonetheless, this large and growing amount of sensing data now being made available by DBS and potentially other neuromodulation devices highlights a critical need for the development of specialized algorithms, tools and infrastructure in order to provide the most potential benefit for patients (Chen et al, 2021).…”