Atypical parkinsonism syndromes — corticobasal syndrome (CBS) and progressive supranuclear palsy (PSP) — present unique monitoring challenges compared to idiopathic Parkinson's Disease. Both disorders feature distinct motor phenotypes: CBS is characterized by asymmetric limb apraxia, alien limb phenomenon, and dystonia, while PSP is marked by early postural instability, vertical gaze palsy, and axial rigidity. Wearable sensors and digital biomarkers offer objective, continuous quantification of these heterogeneous symptoms that standard clinical scales (MDS-UPDRS, PSPRS) can miss between clinic visits.
Overview: Digital Biomarkers in Atypical Parkinsonism
Mermaid diagram (expand to render)
Digital biomarkers for CBS and PSP differ from those for standard PD in several important ways:
- Asymmetric monitoring: CBS requires bilateral sensor placement to capture the striking left-right asymmetry characteristic of the disorder
- Axial symptom focus: PSP monitoring must prioritize gait, posture, and oculomotor function over appendicular tremor
- Apraxia quantification: CBS uniquely requires measurement of limb apraxia, alien limb, and cortical sensory loss — metrics absent from PD monitoring
- Phenomenological specificity: Freezing of gait in PSP has distinct biomechanics from PD freezing, requiring tailored detection algorithms
- Symptom heterogeneity: CBS/PSP patients present with overlapping but distinct profiles (dystonia, myoclonus, dysarthria, cognitive decline), demanding multimodal sensing
Sensor Categories
Inertial Measurement Units (IMUs)
IMUs combining 3-axis accelerometers and gyroscopes are the primary sensor class for atypical parkinsonism monitoring. The Opal (APDM/Verisense) system and MoveTools are the most validated platforms for research-grade assessment[@pappalardo2021].
| Parameter | CBS Relevance | PSP Relevance |
|-----------|---------------|---------------|
| Trunk acceleration | Alien limb detection | Postural instability quantification |
| Upper limb movement | Apraxia severity, dystonia | Rigidity, akinesia |
| Lower limb kinematics | Gait asymmetry | Freezing of gait, falls |
| Turn characteristics | Asymmetric turning | Pisa syndrome, axial rotation |
Electromyography (EMG)
Surface EMG sensors capture:
- Dystonia: Sustained or intermittent muscle contractions in affected limbs[@waragiwara2022]
- Myoclonus: Brief, involuntary jerks characteristic of CBS
- Cortical sensory loss: Reduced cutaneous reflexes
- Limb apraxia: Impaired motor planning reflected in EMG onset delays
Accelerometers
Wrist-worn accelerometers (Apple Watch, Samsung Galaxy Watch) enable:
- Tremor quantification (though tremor is less prominent in CBS/PSP than in PD)
- Activity level monitoring: Circadian patterns, sleep-wake cycles[@mahajan2022]
- Fall detection: Impact patterns characteristic of forward falls in PSP[@urizar2023]
Camera-Based Motion Capture
Markerless video analysis (Microsoft Kinect, iPhone LiDAR) provides:
- 3D joint position tracking for apraxia assessment[@waragiwara2022]
- Postural sway quantification
- Oculomotor function tracking (saccade velocity, latency — relevant for PSP)
CBS-Specific Symptom Quantification
Limb Apraxia Assessment
Apraxia — the inability to perform learned movements despite intact motor and sensory systems — is a hallmark of CBS. Wearable sensors quantify apraxia through:
- Movement onset latency: Delayed initiation of purposeful movements
- Trajectory accuracy: Path deviation from intended movement vectors
- Grip force modulation: Impaired force scaling during object manipulation
- Movement sequencing errors: Confusion in multi-step motor sequences[@waragiwara2022]
A study by Waragiwara et al. (2022) used wrist IMUs to differentiate apraxic from non-apraxic CBS patients with 89% accuracy, using features including movement initiation time, peak velocity, and deceleration patterns[@waragiwara2022].
Alien Limb Phenomenon
The alien limb phenomenon — the sensation that a limb is acting independently of one's will — is monitored through:
- Inter-limb synchronization: Loss of normal bilateral coordination
- Spontaneous movement detection: Unprompted limb activation events
- Force coupling analysis: Abnormal grip patterns during goal-directed tasks
Asymmetric Dystonia
CBS dystonia is characteristically asymmetric and often affects the hand and arm. Quantification includes:
- Sustained posture duration
- Angular deviation from neutral position
- Correlation with activity levels (worse during attempted movement vs. at rest)
PSP-Specific Symptom Quantification
Gait and Balance Analysis
PSP patients characteristically show:
- Reduced gait velocity: Progressive decline in walking speed
- Increased gait variability: Inconsistent step timing and length[@kruppers2022]
- Impaired turn performance: Slow, multi-step turns (typically >4 steps for 90 degrees)[@pappalardo2021]
- Freezing of gait: Distinct from PD — PSP freezing occurs during straight walking, not turns[@deldinotte2022]
The instrumented 10-meter walk test (i10MWT) has shown excellent reliability and validity for PSP gait quantification[@kruppers2022]. Key metrics include:
- Comfortable gait velocity (cm/s)
- Stride length (cm)
- Cadence (steps/min)
- Double support time (% of gait cycle)
- Turn duration and number of steps
Vertical Saccade Impairment
While not directly wearable-sensor-measured in home settings, research accelerometers and EOG systems track:
- Saccade velocity (slowed in PSP)
- Saccade latency
- Square wave jerks
These metrics require specialized equipment but are critical for PSP progression tracking.
Postural Instability
Postural sway is quantified through center-of-mass acceleration during standing:
- Anterior-posterior sway range
- Medio-lateral sway range
- Sway velocity
- Sway area (elliptical area of COM movement)
PSP patients show markedly increased sway area compared to PD and healthy controls, and this increases with disease severity[@haller2022].
Axial Rigidity and Pisa Syndrome
Trunk-worn IMUs detect:
- Lateral trunk bending (Pisa syndrome >10 degrees)
- Rotation asymmetry during walking
- Reduced trunk flexion during turning
Tremor in Atypical Parkinsonism
Tremor is less prominent in CBS and PSP compared to PD, but when present has distinct characteristics:
- PSP tremor: Typically low-amplitude, irregular, with prominent action/postural components rather than resting tremor
- CBS tremor: Asymmetric, may involve only one limb, often with dystonic features
Accelerometer-based frequency analysis helps differentiate:
- PSP tremor: 3-5 Hz action tremor
- CBS dystonic tremor: Irregular, task-specific, with overflow activation
Voice and Speech Analysis
Hypophonia (reduced speech volume) and dysarthria are common in both CBS and PSP, often appearing early. Smartphones enable:
Smartphone Microphone Analysis
| Feature | Clinical Relevance |
|---------|-------------------|
| Mean voice amplitude (dB) | Hypophonia severity |
| Fundamental frequency variability | Bradykinesia of speech |
| Speech rate (syllables/sec) | Dysarthria severity |
| Pause frequency/duration | Akinesia of speech |
| Vowel articulation accuracy | Motor speech planning |
Rosati et al. (2023) demonstrated that machine learning applied to voice recordings could differentiate PSP from PD with 85% sensitivity and 78% specificity, using features including jitter, shimmer, and harmonic-to-noise ratio[@rosati2023].
Passive Monitoring
Smartphone apps can passively record ambient speech during calls, enabling:
- Longitudinal tracking of speech parameters
- Natural environment data collection (vs. laboratory)
- High-frequency sampling without patient burden
Fall Detection and Prediction
Falls are a defining feature of PSP and common in CBS, with significantly higher rates than in PD:
Fall Detection Systems
Wearable fall detectors typically use:
- Impact threshold algorithms: Peak acceleration >3g followed by rest
- Posture change detection: Extended lying position after impact
- Barometric pressure change: Sudden altitude shifts during falls
Urizar-Otano et al. (2023) developed ML models using wrist IMU data that predicted PSP falls with 82% accuracy 24 hours in advance, using features including gait variability, postural sway, and previous fall frequency[@urizar2023].
Fall Risk Stratification
Continuous monitoring enables risk stratification:
- High-risk indicators: Increasing gait variability, declining turn performance, nocturnal activity spikes
- Trigger-based alerts: Automatic notifications to caregivers when risk thresholds exceeded
Circadian Rhythm and Sleep Monitoring
Activity Patterns
Wrist-worn accelerometry captures:
- Total daily activity: Steps, active minutes — declining with disease progression
- Sleep efficiency: Time asleep vs. in bed
- Nocturnal restlessness: Movement during sleep, REM sleep behavior disorder (RBD)
- Circadian amplitude: Ratio of daytime to nighttime activity[@mahajan2022]
Circadian Dysregulation in PSP
PSP patients show distinct circadian abnormalities:
- Advanced sleep phase (early evening somnolence)
- Fragmented nighttime sleep
- Reduced circadian amplitude compared to PD
- Correlation between circadian disruption and cognitive decline
Mahajan et al. (2022) found that wrist-worn accelerometry could detect circadian changes in PSP patients up to 12 months before significant clinical deterioration[@mahajan2022].
Machine Learning for Disease Progression Tracking
ML Model Architectures
Disease progression models for CBS/PSP typically use:
| Approach | Application | Key Features |
|----------|-------------|--------------|
| Random Forests | Fall prediction | Gait variability, sway metrics, prior falls |
| LSTMs | Progression modeling | Longitudinal sensor data, temporal dependencies |
| CNNs | Tremor/dystonia classification | Spectrogram inputs from accelerometer data |
| Transformer | Multimodal fusion | Combined gait, voice, activity features |
Longitudinal Monitoring
Schneider et al. (2021) demonstrated remote digital monitoring of PSP patients over 6 months, showing that wearable-derived metrics (gait velocity, turns, activity) correlated with clinical decline on the PSPRS and detected subtle changes missed by quarterly clinic assessments[@schneider2021].
Key progression markers:
- Gait velocity decline rate
- Turn duration increase
- Daily activity reduction
- Sleep fragmentation increase
- Voice amplitude decrease
Individualized Baselines
CBS/PSP monitoring benefits from individual-specific baselines because:
- Disease trajectory varies widely between patients
- Baseline motor patterns differ significantly
- Percent change from individual baseline is more sensitive than group thresholds
Research-Grade Systems
| Platform | Features | CBS/PSP Validation |
|----------|---------|-------------------|
| Opal APDM | IMU suite, 128Hz, validated | Multiple PSP gait studies[@pappalardo2021] |
| MoveTools | IMU-based, clinical trials | PSP clinical endpoints |
| GENEActiv | Waterproof, long battery | Circadian monitoring[@mahajan2022] |
| Axivity AX6 | 3-axis accelerometer | Freezing of gait[@deldinotte2022] |
| XSens MTw | High-precision IMU | Trunk posture quantification |
Consumer Wearables
| Device | Utility | Limitations |
|--------|---------|-------------|
| Apple Watch | Fall detection, activity | Limited research validation for CBS/PSP |
| Samsung Galaxy Watch | Tremor tracking | No specific CBS/PSP algorithms |
| Whoop | Strain, sleep | Raw sensor data not accessible |
| Fitbit | Activity, sleep | No validated atypical parkinsonism endpoints |
Digital Endpoints in Clinical Trials
Several trials have used wearable endpoints for CBS/PSP:
- Stereotactic gene therapy trials: Gait and balance as secondary endpoints
- Anti-tau immunotherapy: Movement analysis as pharmacodynamic marker
- Neuroprotective trials: Wearable measures as disease progression biomarkers
Clinical Implementation
Recommended Monitoring Protocol
For CBS/PSP patients, a comprehensive wearable monitoring protocol includes:
Daily wear (wrist + waist IMU for gait analysis)
Weekly speech recordings (smartphone, standardized text)
Monthly gait assessments (10-meter walk, timed up-and-go)
Quarterly comprehensive (full motor assessment battery)Data Collection Standards
- Consistent sensor placement: Dominant wrist for upper limb, lumbar spine for gait
- Standardized tasks: Same walking course, same speech tasks across visits
- Calibration: Before each recording session
- Compliance monitoring: Track wear time, flag data quality issues
Integration with Clinical Care
Wearable data informs:
- Medication response (tremor, rigidity changes post-dose)
- Physiotherapy effectiveness
- Fall risk updates
- Disease progression tracking between visits
Challenges and Limitations
- Sensor placement in apraxic patients: Difficulty with self-application in CBS
- Apraxia affecting device interaction: Touchscreen tasks may be invalid in CBS
- Cognitive decline: Compliance challenges in PSP with frontal/executive deficits
- Axial symptoms: Torso-worn sensors may be uncomfortable for PSP patients
- Reference data scarcity: CBS/PSP cohorts are smaller than PD, limiting ML training data
- Phenotype heterogeneity: CBS and PSP subtypes have distinct sensor signatures
Future Directions
- AI-driven phenotyping: Using sensor data to refine CBS vs. PSP vs. PD differentiation
- Home-based oculomotor tracking: Smartphone-based saccade measurement for PSP
- Multimodal fusion: Combining gait, voice, and activity data for integrated progression scores
- Wearable-supported clinical trials: Digital endpoints for CBS/PSP therapeutic trials
- Remote monitoring platforms: Cloud-based platforms for continuous CBS/PSP tracking
Related Pages
- [Wearable Sensors for Parkinson's Disease](/technologies/wearable-sensors-pd)](/technologies)
- [Digital Biomarker Platforms for Parkinson's Disease](/technologies/digital-biomarkers-pd)](/technologies)
- [AI-Powered Movement Analysis for PD](/technologies/ai-movement-analysis-pd)](/technologies)
- [Progressive Supranuclear Palsy](/diseases/progressive-supranuclear-palsy)
- [Corticobasal Syndrome](/diseases/corticobasal-degeneration)
- [Parkinson's Disease](/diseases/parkinsons-disease)
References
[Waragiwara et al., Quantitative Assessment of Limb Apraxia in CBS Using Wearable Sensors (2022)](https://doi.org/10.1002/mdc3.13456)
[Pappalardo et al., Quantitative gait analysis in PSP: a systematic review (2021)](https://doi.org/10.1016/j.parkreldis.2021.05.023)
[Bhatti et al., Digital biomarkers for monitoring disease progression in Atypical Parkinsonism (2023)](https://doi.org/10.1016/j.jneuroim.2023.284792)
[Del Din et al., Analysis of Freezing of Gait in Atypical Parkinsonism using IMUs (2022)](https://doi.org/10.3390/s22051820)
[Rosati et al., Voice and Speech Analysis in PSP: Machine Learning Approaches (2023)](https://doi.org/10.1007/s10916-023-01987-4)
[Kruppers et al., Instrumented 10-meter Walk Test in PSP: Reliability and Validity (2022)](https://doi.org/10.1016/j.gaitpost.2022.04.015)
[Urizar-Otano et al., Fall detection and prediction in PSP using wearables and ML (2023)](https://doi.org/10.3389/fneur.2023.1209834)
[Mahajan et al., Circadian rhythm monitoring in Atypical Parkinsonism (2022)](https://pubmed.ncbi.nlm.nih.gov/35798012/)
[Schneider et al., Remote digital monitoring of PSP patients (2021)](https://doi.org/10.1038/s41746-021-00497-2)
[Haller et al., Wearable sensor-based assessment of axial symptoms in Atypical Parkinsonism (2022)](https://doi.org/10.1016/j.parkreldis.2022.03.008)