Wearable sensors offer an innovative, continuous, and objective method for diagnosing and monitoring pediatric neurological conditions, overcoming limitations associated with traditional, subjective clinical assessments. They have been successfully applied to conditions such as cerebral palsy, epilepsy, autism spectrum disorder, and various genetic and neuromuscular disorders, providing valuable insights into motor function, seizure activity, and daily movements. Despite existing challenges regarding compliance, ethics, and regulatory aspects, wearable technology has significant potential to enhance clinical outcomes and improve pediatric neurology care.
Introduction to Wearable Sensors in Child Neurology
- Growing importance due to limitations of traditional assessment methods (subjectivity, snapshot evaluations, patient cooperation).
- Wearable sensors offer continuous, objective, real-world data collection.
- Useful in both active (task-based) and passive (daily activity) assessments.
Advantages of Wearable Sensors
- Objective measurement, minimizing subjective biases.
- Continuous monitoring, capturing real-world variations.
- Increased patient convenience and trial participation rates.
Applications in Specific Neurological Disorders
Cerebral Palsy (CP)
- Monitoring motor function (accelerometers, inertial sensors).
- Assessment of upper limb function, gait, and dystonia.
- Home-based monitoring enhances long-term disease tracking.
Wearable Sensors in Cerebral Palsy
Axivity AX3
- Position: Wrists, chest, upper arms
- Predict clinical outcomes via home-based acceleration data (Franchi de’ Cavalieri M et al., (2023))
- Feasible for monitoring upper limb function in very young children (von Gunten et al., (2023)).
DOT (Xsens Technologies)
- Position: Wrist, ankle
- Personalized machine learning tracks dystonia progression at home (den Hartog et al., (2022)).
ETH Orientation Sensor
- Position: Upper arms, wrists, chest, hip, thighs, foot
- Findings: Minimal sensor setups reliably evaluate daily activities and motor performance (Strohrmann et al., (2013)).
FSR Sensors
- Position: Foot
- Findings: Accurate activity and gait monitoring via footwear-integrated sensors with machine learning (Hegde et al., (2018)).
GT3X Actigraph
- Position: Wrists, hip, ankle
- Findings:
- Effective activity classification and clinical assessments
- Personalized models improve accuracy in severely impaired individuals (Ahmadi et al. (2018)).
- Strong correlation with standardized clinical hand function assessments (Ahmadi et al. (2020)).
G-Walk
Login to Read More
