The usefulness of wearable sensors for detecting freezing of gait in Parkinson’s disease

Background: Freezing of gait (FoG) is one of the most debilitating motor symptoms in Parkinson’s disease (PD). It often leads to falls and reduces quality of life due to the risk of injury and loss of independence. Several types of wearable sensors have emerged as promising tools for the detection of FoG in clinical and real-life settings. Objective: The main objective of this systematic review was to critically evaluate the current usability of wearable sensor technologies for FoG detection in PD patients. The focus of the study is on sensor types, sensor combinations, placement on the body and the applications of such detection systems in a naturalistic environment. Methods: PubMed, IEEE Explore and ACM digital library were searched using a search string of Boolean operators that yielded 328 results, which were screened by title and abstract. After the screening process, 43 articles were included in the review. In addition to the year of publication, authorship and demographic data, sensor types and combinations, sensor locations, ON/OFF medication states of patients, gait tasks, performance metrics and algorithms used to process the data were extracted and analyzed. Results: The number of patients in the reviewed studies ranged from a single PD patient to 205 PD patients, and just over 65% of studies have solely focused on FoG + PD patients. The accelerometer was identified as the most frequently utilized wearable sensor, appearing in more than 90% of studies, often in combination with gyroscopes (25.5%) or gyroscopes and magnetometers (20.9%). The best overall sensor configuration reported was the accelerometer and gyroscope setup, achieving nearly 100% sensitivity and specificity for FoG detection. The most common sensor placement sites on the body were the waist, ankles, shanks and feet, but the current literature lacks the overall standardization of optimum sensor locations. Real-life context for FoG detection was the focus of only nine studies that reported promising results but much less consistent performance due to increased signal noise and unexpected patient activity. Conclusions: Current accelerometer-based FoG detection systems along with adaptive machine learning algorithms can reliably and consistently detect FoG in PD patients in controlled laboratory environments. The transition of detection systems towards a natural environment, however, remains a challenge to be explored. The development of standardized sensor placement guidelines along with robust and adaptive FoG detection systems that can maintain accuracy in a real-life environment would significantly improve the usefulness of these systems.