Freezing of gait (FOG) is a serious gait disturbance, common in mid- and late-stage Parkinson’s disease, that affects mobility and increases fall risk. Wearable sensors have been used to detect and predict FOG with the ultimate aim of preventing freezes or reducing their effect using gait monitoring and assistive devices. This review presents and assesses the state of the art of FOG detection and prediction using wearable sensors, with the intention of providing guidance on current knowledge, and identifying knowledge gaps that need to be filled and challenges to be considered in future studies. This review searched the Scopus, PubMed, and Web of Science databases to identify studies that used wearable sensors to detect or predict FOG episodes in Parkinson’s disease. Following screening, 74 publications were included, comprising 68 publications detecting FOG, seven predicting FOG, and one in both categories. Details were extracted regarding participants, walking task, sensor type and body location, detection or prediction approach, feature extraction and selection, classification method, and detection and prediction performance. The results showed that increasingly complex machine-learning algorithms combined with diverse feature sets improved FOG detection. The lack of large FOG datasets and highly person-specific FOG manifestation were common challenges. Transfer learning and semi-supervised learning were promising for FOG detection and prediction since they provided person-specific tuning while preserving model generalization.

Introduction: Falling is one of the primary concerns for people with Parkinson's Disease and occurs predominately during dynamic movements, such as walking. Several methods have been proposed to quantify dynamic balance and to assess fall risk. However, no consensus has been reached concerning which method is most appropriate for examining walking balance during unperturbed and perturbed conditions, particularly in Parkinson's Disease individuals. Therefore, this systematic review aimed to assess the current literature on quantifying dynamic balance in healthy young, elderly and Parkinson's individuals during unperturbed and perturbed walking. Methods: The PubMed database was searched by title and abstract for publications quantifying dynamic balance during unperturbed and mechanically perturbed walking conditions in elderly adults and PD. Inclusion criteria required publications to be published in English, be available in full-text, and implement a dynamic balance quantification method. Exclusion criteria included clinical dynamic balance measures, non-mechanical perturbations, pathologies other than PD, and dual-tasking conditions. The initial database search yielded 280 articles, however, only 81 articles were included after title, abstract and full-text screening. Methodological quality and data were extracted from publications included in the final synthesis. Results: The dynamic balance articles included 26 Coefficient of Variation of Spatiotemporal Variability, 10 Detrended Fluctuation Analysis, 20 Lyapunov Exponent, 7 Maximum Floquet Multipliers, 17 Extrapolated Center of Mass, 11 Harmonic Ratios, 4 Center of Mass-Center of Pressure Separation, 2 Gait Stability Ratio, 1 Entropy, 3 Spatiotemporal Variables, 2 Center of Gravity and Center of Pressure, and 2 Root Mean Square in the final synthesis. Assessment of methodological quality determined that 58 articles had a low methodological rating, a 22 moderate rating, and 1 having a high rating. Conclusion: Careful consideration must be given when selecting a method to quantify dynamic balance because each method defines balance differently, reflects a unique aspect of neuromuscular stability mechanisms, and is dependent on the walking condition (unperturbed vs. perturbed). Therefore, each method provides distinct information into stability impairment in elderly and PD individuals.

Freezing of gait (FOG) is a sudden and highly disruptive gait dysfunction that appears in mid to late-stage Parkinson’s disease (PD) and can lead to falling and injury. A system that predicts freezing before it occurs or detects freezing immediately after onset would generate an opportunity for FOG prevention or mitigation and thus enhance safe mobility and quality of life. This research used accelerometer, gyroscope, and plantar pressure sensors to extract 861 features from walking data collected from 11 people with FOG. Minimum-redundancy maximum-relevance and Relief-F feature selection were performed prior to training boosted ensembles of decision trees. The binary classification models identified Total-FOG or No FOG states, wherein the Total-FOG class included data windows from 2 s before the FOG onset until the end of the FOG episode. Three feature sets were compared: plantar pressure, inertial measurement unit (IMU), and both plantar pressure and IMU features. The plantar-pressure-only model had the greatest sensitivity and the IMU-only model had the greatest specificity. The best overall model used the combination of plantar pressure and IMU features, achieving 76.4% sensitivity and 86.2% specificity. Next, the Total-FOG class components were evaluated individually (i.e., Pre-FOG windows, Freeze windows, transition windows between Pre-FOG and Freeze). The best model detected windows that contained both Pre-FOG and FOG data with 85.2% sensitivity, which is equivalent to detecting FOG less than 1 s after the freeze began. Windows of FOG data were detected with 93.4% sensitivity. The IMU and plantar pressure feature-based model slightly outperformed models that used data from a single sensor type. The model achieved early detection by identifying the transition from Pre-FOG to FOG while maintaining excellent FOG detection performance (93.4% sensitivity). Therefore, if used as part of an intelligent, real-time FOG identification and cueing system, even if the Pre-FOG state were missed, the model would perform well as a freeze detection and cueing system that could improve the mobility and independence of people with PD during their daily activities.

Changes to arm swing and gait symmetry are symptomatic of several pathological gaits associated with reduced stability. The purpose of this study was to examine the relative contributions of arm swing and gait symmetry towards gait stability. We theorized that actively increasing arm swing would increase gait stability, while asymmetric walking would decrease gait stability. Fifteen healthy, young adults (23.4 ± 2.8 yrs) walked on a split-belt treadmill under symmetric (1.2 m/s) and asymmetric walking (left/right, 5:4 speed ratio) with three different arm swings: held, normal, and active. Trunk local dynamic stability, inter-limb coordination, and spatiotemporal gait variability and symmetry were measured. Active arm swing resulted in improved local trunk stability, increased gait variability, and decreased inter-limb coordination (p < .013). The changes in local trunk stability and gait variability during active arm swing suggests that these metrics quantify fundamentally different aspects of stability and are not always comparable. Split-belt walking caused reduced local trunk stability, increased gait variability, and increased lower limb asymmetry (p < .003). However, the arm swing symmetry was unaffected by gait asymmetry, this suggests that the decreases in gait stability are linked to the increases in gait asymmetry rather than increases in arm swing asymmetry.