Related Experiment Video
Updated: Oct 8, 2025
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
The Human Tic Detector: An automatic approach to tic characterization using wearable sensors
Stephanie Cernera1, Leena Pramanik2, Zachary Boogaart2
1J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, United States; Norman Fixel Institute for Neurological Diseases and the Program for Movement Disorders and Neurorestoration, University of Florida, Gainesville, FL, United States.
Wearable sensors accurately detect and classify Tourette syndrome (TS) tics by analyzing physiological data. This technology offers an objective, real-world measure for improved TS patient care.
Area of Science:
- Biomedical Engineering
- Neuroscience
- Wearable Technology
Background:
- Current Tourette syndrome (TS) rating scales rely on subjective recall or limited observation periods.
- Objective, quantifiable measures for tic assessment in TS are needed to overcome existing limitations.
Purpose of the Study:
- To develop and validate a sensor-based system for detecting and classifying tics in individuals with TS.
- To explore the utility of wearable sensors in providing objective tic data.
Main Methods:
- Electromyogram and acceleration data were collected from 17 TS patients during voluntary movements and tics.
- Spectral properties of sensor data were extracted and used to train a support vector machine (SVM) for movement classification.
Main Results:
- The SVM achieved high accuracy (96.69%), sensitivity (98.24%), and specificity (96.03%) in classifying movements.
- Tic detection accuracy during clinical rating (mRVTRS) reached 85.63%, with overall movement classification at 94.23%.
Conclusions:
- Wearable sensors can reliably differentiate between tic and voluntary movements in TS patients.
- This sensor-based approach offers a promising, objective method for tic assessment, comparable to expert evaluation.
