Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation
July 14th, 2023
The protocol shows a prototype of the at-home multi-modal data collection platform that supports research optimizing adaptive deep brain stimulation (aDBS) for people with neurological movement disorders. We also present key findings from deploying the platform for over a year to the home of an individual with Parkinson's disease.
My research supports automating adaptive deep brain stimulation or ADBS for Parkinson's disease in the comfort of someone's home. One question is whether this therapy can be monitored safely for a long period outside the clinic while ensuring patient privacy. Additionally, we're looking into the possibility of automatically adjusting ADBS parameters without the need for the patient to return to the clinic.
ADBS research needs data collection platforms to accurately measure movement quality as patients go about their daily lives and to remotely deliver updates to therapy algorithms. This protocol collects multiple modalities as patients move freely about their homes, including video data to capture isolated kinematic like finger movements. Our results allow us to explore changes in Parkinson's disease over long periods of time, and they let us ask what measurements are necessary to analyze and treat the varied symptoms of Parkinson's disease outside clinical observation.
View the full transcript and gain access to thousands of scientific videos
Overview
This study presents a prototype at-home multi-modal data collection platform designed to optimize adaptive deep brain stimulation (aDBS) for individuals with neurological movement disorders, specifically Parkinson's disease. Key findings highlight the platform's deployment over a year, successfully monitoring therapy parameters and capturing crucial data while ensuring patient privacy.
Key Study Components
Area of Science
- Neuroscience
- Movement Disorders
- Technology in Rehabilitation
Background
- Adaptive deep brain stimulation (aDBS) is a promising therapy for Parkinson's disease.
- Long-term monitoring and adjustment of therapy parameters outside clinical settings is essential.
- The impact of various data types on assessing Parkinson's disease symptoms is investigated.
Purpose of Study
- To demonstrate the feasibility of at-home aDBS monitoring.
- To evaluate the effectiveness of remote data collection for therapy adjustments.
- To explore changes in symptoms and movement quality over extended periods.
Methods Used
- The study utilizes a multi-modal data collection platform designed for home use.
- Parkinson's disease serves as the biological model for evaluating aDBS efficacy.
- The platform captures video data to analyze kinematic movements, such as finger motions.
- Data collection occurs as patients move freely, enabling naturalistic observation.
- Key steps include continuous data monitoring and remote algorithm updates.
Main Results
- The platform successfully monitored therapy parameters over a year, allowing exploration of symptom progression.
- Data enabled in-depth analysis of movement quality in daily life scenarios.
- Insights gained inform necessary measurements for managing diverse Parkinson's symptoms outside clinical settings.
Conclusions
- The study demonstrates the potential for aDBS therapy to be effectively monitored at home.
- This approach enhances patient privacy and comfort while ensuring effective symptom management.
- It paves the way for further research on remote rehabilitation techniques and their implications in understanding Parkinson's disease mechanisms.
Frequently Asked Questions
Executive Industry Relevance
Remote, multi-modal data collection for adaptive deep brain stimulation (aDBS) addresses a critical bottleneck in scalable, personalized neuromodulation therapy for neurological disorders. By enabling continuous, real-world monitoring and algorithmic adjustment outside the clinic, this platform supports predictive confidence and long-term therapeutic optimization. The approach directly impacts translational research and portfolio strategies for digital therapeutics and neurotechnology development.
Strategic Applications in Biopharma R&D
Early Discovery & Target Validation
- Enables longitudinal, real-world measurement of symptom-related biomarkers for mechanistic de-risking.
- Supports functional validation of adaptive stimulation targets through continuous, patient-specific data.
- Facilitates hypothesis testing on biomarker-driven therapy adjustments in naturalistic settings.
Screening & Assay Development
- Provides standardized, time-aligned multi-modal datasets for quantitative assessment of motor function.
- Enables reproducible evaluation of algorithmic parameter changes across therapeutic conditions.
- Supports scalable screening of aDBS algorithm performance in diverse patient environments.
Translational & Preclinical Research
- Aligns at-home data collection with disease-relevant endpoints for translational biomarker development.
- Enables continuity from in-clinic discovery to real-world preclinical validation of neuromodulation strategies.
- Supports risk-adjusted advancement of digital and device-based therapeutics for neurological disorders.
Pipeline & Workflow Integration
This at-home ecosystem bridges early discovery, algorithm optimization, and translational validation for adaptive neuromodulation therapies.
- Discovery Biology: Captures real-world biomarker and symptom data to inform target validation and mechanistic understanding.
- Screening: Delivers reproducible, quantitative outputs for evaluating algorithmic and therapeutic adjustments.
- Analytics: Provides synchronized, multi-modal datasets for robust statistical comparison of therapeutic states.
- Translational Research: Extends discovery findings into home environments, supporting biomarker alignment and long-term outcome studies.
- Enterprise Reuse: Establishes a scalable, open-source platform for ongoing research and development across neurological indications.
Operational & Enterprise Impact
- Scientific Value: Increases predictive confidence in adaptive therapy algorithms and reduces mechanistic ambiguity.
- Operational Value: Standardizes remote data collection and supports reproducibility across patient cohorts.
- Strategic Value: Enables data-driven go/no-go decisions for digital and device-based therapeutic programs.
- Portfolio Impact: Supports risk-adjusted prioritization and advancement of neuromodulation assets.
Implementation Considerations
- Requires expertise in neurotechnology, data science, and patient privacy protocols.
- Demands robust hardware, secure data transfer, and analytical infrastructure for multi-modal integration.
- Necessitates cross-team standardization for data formats and analysis pipelines.
- Must be adaptable to different neurological models and home environments.
- Practical limitations include ensuring data quality and privacy in decentralized settings.
