Objective: Characterize clinical workflow insights gained from expanded access to neural data via a cloud connected platform in adaptive DBS.

Background: Adaptive deep brain stimulation (aDBS) may provide improvement over continuous DBS (cDBS) in Parkinson’s disease (PD) by automatically adjusting stimulation amplitude based on patient-specific brain neural biomarkers^1–4. aDBS is inherently data‑driven with workflows focused on neural data to inform programming⁵. However, neural signal characteristics can change over the PD DBS journey as the disease progression, medications, and stimulation parameters evolve. Therefore, expanding access to longitudinal, patient-specific neural data may help contextualize postoperative changes and inform aDBS programming.

Method: This cohort (n=10) includes people with PD implanted with DBS targeting the subthalamic nucleus (STN) or globus pallidus interna (GPi) using brain sensing‑enabled DBS systems and cloud data connectivity. Brain sensing was initiated immediately postoperative and neural data were collected and aggregated across care settings via secure cloud-based platform. Data were reviewed in a clinician-facing portal for individual aDBS programming decisions and longitudinally to identify brain signals of interest and support determination of thresholds and stimulation limits. This workflow is intended to support data-informed aDBS programming decisions.

Results: To date, brain sensing has been longitudinally collected in 6 PD participants (5 STN and 1 GPi) over multiple clinic visits. The movement disorder neurologists were able to access and use the brain sensing data collected from the early postoperative period to support aDBS in the postoperative period, without significant stabilization challenges. Moreover, their early experience was that minimal aDBS threshold adjustments were required during subsequent maintenance visits (mean change ~2% across all thresholds). Additional analyses will explore neural data dynamics, clinical outcomes and workflow experiences over time.

Conclusion: This work describes the review of longitudinal brain sensing using a cloud-connected platform during routine DBS programming visits. The results demonstrate the utility of these data for supporting aDBS programming and maintenance in the postoperative period.Furthermore, the results demonstrate the feasibility of a cloud connected data-driven DBS programming.

References: 1. Bronte-Stewart HM, Beudel M, Ostrem JL, et al. Long-Term Personalized Adaptive Deep Brain Stimulation in Parkinson Disease: A Nonrandomized Clinical Trial. JAMA Neurol. 2025;82(11):1171. doi:10.1001/jamaneurol.2025.2781
2. Little S, Beudel M, Zrinzo L, et al. Bilateral adaptive deep brain stimulation is effective in Parkinson’s disease. J Neurol Neurosurg Psychiatry. 2016;87(7):717-721. doi:10.1136/jnnp-2015-310972
3. Rosa M, Arlotti M, Marceglia S, et al. Adaptive deep brain stimulation controls levodopa-induced side effects in Parkinsonian patients: DBS Controls Levodopa-Induced Side Effects. Mov Disord. 2017;32(4):628-629. doi:10.1002/mds.26953
4. Oehrn CR, Cernera S, Hammer LH, et al. Chronic adaptive deep brain stimulation versus conventional stimulation in Parkinson’s disease: a blinded randomized feasibility trial. Nat Med. Published online August 19, 2024. doi:10.1038/s41591-024-03196-z
5. Stanslaski S, Summers RLS, Tonder L, et al. Sensing data and methodology from the Adaptive DBS Algorithm for Personalized Therapy in Parkinson’s Disease (ADAPT-PD) clinical trial. Npj Park Dis. 2024;10(1):174. doi:10.1038/s41531-024-00772-5

« Back to 2026 International Congress

MDS Abstracts - https://www.mdsabstracts.org/abstract/data-driven-clinical-insights-from-longitudinal-cloud-aggregated-neural-data-to-inform-a-real-world-adaptive-dbs-programming/