Digital Diagnostic Devices for Parkinson's Disease (NCT06663826)

Trial Overview

Trial Overview

| Field | Value |
|-------|-------|
| NCT Number | NCT06663826 |
| Status | Recruiting |
| Phase | Observational (Device Development) |
| Sponsor | machineMD AG |
| Collaborators | University of Zurich, University Hospital Zurich, University of Exeter, gaitQ Limited |
| Study Type | Observational / Patient Registry |
| Target Enrollment | 100 patients |
| Study Duration | 15 days per patient |
| Locations | University Hospital of Zurich, Switzerland |

Scientific Rationale

The Challenge of Parkinson's Disease Diagnosis

Parkinson's disease (PD) is one of the most common neurodegenerative diseases worldwide, affecting approximately 1% of the population over 65 years of age [1](https://pubmed.ncbi.nlm.nih.gov/). Current PD diagnosis relies heavily on:

• Patient history and subjective symptom descriptions
• Clinical assessments using the Movement Disorder Society (MDS) criteria
• Neurological examination including the MDS-UPDRS (Unified Parkinson's Disease Rating Scale)
• Short walking tests such as the 3-meter Timed Up and Go (TUG)

The Role of Ocular Motor Dysfunction

Several oculo-visual abnormalities have been described in PD. Research indicates that abnormal ocular motor function occurs in 75-87.5% of people with PD [2](https://pubmed.ncbi.nlm.nih.gov/). These dysfunctions may:

• Precede motor symptoms
• Follow motor symptoms
• Provide valuable information for early disease detection
• Serve as biomarkers for disease progression

• Saccadic impairments: Abnormalities in rapid eye movements
• Smooth pursuit deficits: Difficulty tracking moving objects
• Vergence dysfunction: Problems with focusing on near vs. far objects

The Role of Gait Analysis

Gait impairments are among the most common and disabling symptoms of PD [3](https://pubmed.ncbi.nlm.nih.gov/), including:

• Freezing of gait (FOG): An inability to initiate or maintain normal walking patterns
• Festinating gait (FSG): Shortening of stride length with elevated step frequency

• Real-time tracking of gait impairments
• Objective disease progression monitoring
• Personalized care delivery

Trial Objectives

Primary Objective

Collect ocular motor, pupil, and gait data from people with PD to develop and compare machine learning models for diagnosing and monitoring PD.

Secondary Objectives

• Disease stage
• Disease duration
• Age of onset
• Medication status
• MDS-UPDRS score

Trial Design

Study Protocol

This is an exploratory open-label single-centre research project. Each patient will undergo:

| Visit | Duration | Assessments |
|-------|----------|-------------|
| Visit 1 | 3 hours | MDS-UPDRS, neos examination, standard ocular motor/pupil exam, gait assessment |
| Visit 2 (after 2 weeks) | 2 hours | Repeat assessments |
| Home monitoring (2 weeks) | Daily | TUG test (15m walk, 5 sit-to-stand, 5-minute walk) |

Devices Used

neos - Ocular Motor Measurement Device

The neos device is a medical device approved for objective ocular motor and pupil measurement. It provides:

• High-precision eye tracking
• Pupil response measurements
• Standardized oculomotor assessments
• Quantitative data for machine learning

GaitQ senti

A consumer device enabling objective and continuous remote gait monitoring, consisting of:

• IMU (Inertial Measurement Unit) sensor placed on the patient's back
• Wearable leg sensor for gait analysis

Data Collection

The machine learning algorithms will be trained on a clinical dataset comprising:

• 50 PD patients
• Healthy individuals (data from another study)
• 12 patients with other parkinsonian disorders (atypical parkinsonism)

Eligibility Criteria

Inclusion Criteria

Exclusion Criteria

Outcome Measures

Primary Outcomes

| Measure | Description | Timeframe |
|---------|-------------|-----------|
| Machine learning model development | Train algorithms using clinical dataset for PD diagnosis and monitoring | 1 year |

Secondary Outcomes

| Measure | Description | Timeframe |
|---------|-------------|-----------|
| Correlation with clinical parameters | Correlation between ocular motor parameters and disease stage, duration, onset age, medication, MDS-UPDRS | 1 year |

Clinical Significance

advancing PD Diagnostics

This trial represents a significant step toward objective, quantitative PD diagnosis by:

Machine Learning Integration

By integrating machine learning with high-quality sensor data, this approach aims to:

• Improve diagnostic accuracy beyond current clinical criteria
• Enable earlier PD detection
• Provide objective disease progression tracking
• Support personalized treatment decisions

Cross-References

• [Parkinson's Disease](/diseases/parkinsons-disease)
• [MDS-UPDRS Assessment](/clinical-trials/alzheimers-disease) (related scale)
• [Ocular Motor Dysfunction in Neurodegeneration](/mechanisms/ocular-motor-dysfunction)
• [Gait Analysis in Movement Disorders](/mechanisms/gait-analysis-parkinson)
• [Digital Health Technologies in Neurology](/therapeutics/digital-therapeutics)

Research Team

| Investigator | Role | Affiliation |
|--------------|------|-------------|
| Konrad Weber, Prof. Dr. med. | Principal Investigator | University of Zurich |
| Ana Coito, Ph.D. | Contact | machineMD AG |
| Pia Massatsch, Ph.D. | Contact | machineMD AG |
| Erika Han, MD | Sub-Investigator | University Hospital Zurich |

References

Detailed Background: Ocular Motor Assessment in PD

Neuroanatomical Basis

The neural circuits underlying ocular motor control are closely integrated with the basal ganglia, the same structures profoundly affected in Parkinson's disease. The basal ganglia play a critical role in modulating saccadic eye movements, smooth pursuit, and vergence through complex dopaminergic pathways [1](https://pubmed.ncbi.nlm.nih.gov/)[2](https://pubmed.ncbi.nlm.nih.gov/).

In PD, the degeneration of dopaminergic neurons in the substantia nigra pars compacta (SNc) disrupts these pathways, leading to characteristic ocular motor deficits:

• Saccadic hypometria: Reduced amplitude of voluntary saccades, requiring multiple corrective saccades to reach targets
• Antisaccade errors: Difficulty suppressing reflexive saccades toward visual stimuli
• Reduced saccadic velocity: Slower saccadic peak velocities compared to healthy controls
• Impaired smooth pursuit: Difficulty maintaining fixation on moving objects
• Vergence insufficiency: Reduced ability to adjust focus for near vs. far targets

Clinical Relevance of Ocular Motor Testing

The assessment of ocular motor function offers several advantages for PD diagnosis and monitoring:

Comparison with Traditional Assessments

| Feature | Traditional MDS-UPDRS | Ocular Motor Assessment |
|---------|----------------------|------------------------|
| Objectivity | Moderate (clinical rating) | High (quantitative) |
| Temporal resolution | Snapshot | Continuous |
| Early detection sensitivity | Low | High |
| Standardization | Variable | High |
| Remote monitoring capability | Limited | Excellent |

Detailed Background: Gait Analysis in PD

Neuroanatomical Basis of Parkinsonian Gait

Gait in Parkinson's disease is controlled by a complex network involving:

• Basal ganglia: Initiation and modulation of movement sequences
• Motor cortex: Voluntary movement planning
• Brainstem: Locomotor centers (pedunculopontine nucleus)
• Cerebellum: Movement coordination and adaptation
• Spinal cord: Central pattern generators

Gait Parameters Affected in PD

Freezing of Gait (FOG)

Freezing of gait is one of the most disabling PD symptoms, affecting approximately 50% of patients at some point during the disease. It is characterized by:

• Sudden cessation: Brief inability to initiate or continue walking
• Trembling in place: Rhythmic shaking of the legs without forward movement
• Complete block: Complete inability to move despite intense effort

• Initiating walking (start hesitation)
• Turning (turn hesitation)
• Approaching destinations (destination hesitation)
• Passing through narrow spaces
• Dual-task conditions

Festinating Gait

Festination is characterized by:

• Progressive shortening of stride length
• Increasing step frequency (shuffling)
• Forward leaning posture
• Reduced arm swing

Quantitative Gait Assessment

Traditional clinical gait assessment relies on subjective observation and timed tests (e.g., Timed Up and Go). Quantitative approaches using wearable sensors provide:

• Continuous monitoring: Assessment beyond the clinic environment
• Multiple parameters: Stride length, velocity, cadence, swing/stance ratio
• Symmetry analysis: Detection of asymmetric gait patterns
• Temporal variability: Measurement of gait variability over time
• Home-based assessment: Remote monitoring capabilities

Machine Learning Approach

Data Integration Strategy

The trial employs a multi-modal data integration approach:

Machine Learning Pipeline

Raw Data → Preprocessing → Feature Extraction → Model Training → Validation → Deployment

Preprocessing Steps

• Signal filtering (removing noise and artifacts)
• Eye blink detection and handling
• Gait cycle detection
• Missing data imputation
• Normalization and standardization

Feature Engineering

Key features extracted include:

Ocular Motor:

• Saccadic peak velocity
• Saccadic accuracy
• Antisaccade error rate
• Smooth pursuit gain
• Fixation stability (variability)

• Baseline pupil size
• Constriction amplitude
• Recovery time
• Sustained response

• Velocity (m/s)
• Stride length (m)
• Cadence (steps/min)
• Swing/stance ratio
• Gait variability index

Model Architecture Considerations

Potential machine learning approaches include:

• Supervised learning: Classification of PD vs. healthy controls using labeled data
• Unsupervised clustering: Identifying disease subtypes based on phenotypic presentations
• Time series analysis: Modeling disease progression over time
• Deep learning: Convolutional neural networks for raw sensor data, recurrent networks for temporal patterns

Validation Strategy

• Cross-validation using held-out patient cohorts
• External validation using independent datasets
• Comparison with established clinical scales
• Sensitivity and specificity analysis

Device Specifications

neos Device

The neos device represents a novel approach to objective ocular motor assessment:

Technical Specifications:

• Sampling rate: ≥ 500 Hz
• Spatial resolution: < 0.5°
• Binocular tracking capability
• Pupillometry integration
• Wireless data transmission

• CE/FDA cleared for clinical use
• Quick setup (< 5 minutes)
• Minimal training required
• Portable design
• Standardized protocols

GaitQ senti

Technical Specifications:

• IMU sampling rate: 100 Hz
• Battery life: 7+ days
• Data storage: Local + cloud sync
• Patient-app interface
• Real-time feedback capability

• Continuous home monitoring
• Freezing of gait detection
• Fall risk assessment
• Treatment response tracking

Future Directions

Clinical Translation

This trial aims to establish the foundation for:

Integration with Clinical Practice

The long-term vision includes integration with:

• Electronic health records
• Telehealth platforms
• Wearable devices
• Clinical decision support systems