Main Menu
Menu
Get Started

Study Overview: The World’s Largest Parkinson’s Research Initiative

Background & Purpose

This large-scale, multi-center study is designed to advance the early detection and monitoring of Parkinson’s disease (PD) by investigating eye movement abnormalities as early biomarkers of neurodegenerative progression. In collaboration with the University of Michigan, we aim to leverage clinical, observational, and real-world evidence (RWE) approaches to refine AI-driven diagnostic algorithms, enhance early-stage detection, and support clinical validation for regulatory pathways, including FDA clearances.

Study Design & Methodology

  1. Clinical Trial Component (Prospective & Controlled)
    • Patient Population: PD patients, high-risk individuals (e.g., prodromal cases, genetic risk factors), and age-matched controls.
    • NeuroAI-Based Assessments:
      • Torsional eye movement tracking (biomechanical impact on neurofunction).
      • Balance & gait assessment (biomechanical and neurological interplay).
      • Neuro-mechanical interactions with real-time feedback on patient response to interventions.
    • Integration with Standard Clinical Metrics:
      • UPDRS (Unified Parkinson’s Disease Rating Scale)
      • MoCA (Montreal Cognitive Assessment)
      • Dopamine transporter (DaT) scans, where applicable
    • Outcome Measures:
      • Sensitivity and specificity of eye-tracking biomarkers vs. traditional PD assessments.
      • Longitudinal tracking of eye movement abnormalities in disease progression.
  2. Observational Study Component (Cross-Sectional & Longitudinal Data Collection)
    1. Objective: Identify and characterize the natural variability of eye-tracking biomarkers in a broad Parkinson’s and pre-Parkinson’s population.
    2. Cohort Inclusion:
      1. Newly diagnosed PD patients
      2. Prodromal cases with REM sleep behavior disorder (RBD)
      3. Patients with mild cognitive impairment (MCI) or early signs of neurodegeneration
    3. Key Observational Insights:
      1. Variability in neuro-mechanical function across different PD subtypes.
      2. Differences in balance and vestibular function before motor symptoms appear.
      3. Analysis of non-motor features (sleep, autonomic dysfunction, cognitive decline).
  3. Real-World Evidence (RWE) Component (Decentralized & Multi-Site Data Collection)
    1. Large-Scale Data Acquisition:
      1. Recruiting 10,000+ participants across clinical and non-clinical settings.
      2. Data captured from clinics, research centers, and at-home assessments.
      3. Inclusion of wearable and digital biomarkers to track disease progression remotely.
    2. Algorithm Refinement & AI Validation:
      1. Enhancing NeuroAI’s predictive analytics for earlier and more precise PD identification.
      2. Training AI models with heterogeneous real-world datasets to improve generalizability.
    3. Regulatory & Clinical Impact:
      1. Establishing clinically validated digital endpoints for regulatory submission.
      2. Supporting FDA clearances for AI-based PD screening and monitoring tools.

Key Objectives & Expected Outcomes

  1. Early-Stage Identification: Establishing eye movement biomarkers as early indicators of Parkinson’s.
  2. AI-Enhanced Diagnostic Tools: Refining algorithms for higher diagnostic precision in clinical practice.
  3. Clinical Validation for FDA Approval: Ensuring robust, scalable validation for AI-based PD diagnostics.
  4. Impact on Standard of Care: Integrating objective neuro-functional assessments into PD management.

This initiative will transform Parkinson’s detection and monitoring, driving early intervention strategies and setting a new standard for AI-driven neurological assessments. We invite researchers, clinicians, and healthcare innovators to be part of this groundbreaking study.

Scroll to Top