Prediction of Freezing of Gait in Parkinson's Disease Using Unilateral and Bilateral Plantar-Pressure Data.

Background: Freezing of gait (FOG) is an intermittent walking disturbance experienced by people with Parkinson's disease (PD). FOG has been linked to falling, injury, and overall reduced mobility. Wearable sensor-based devices can detect freezes already in progress and provide a cue to help the person resume walking. While this is helpful, predicting FOG episodes before onset and providing a timely cue may prevent the freeze from occurring. Wearable sensors mounted on various body parts have been used to develop FOG prediction systems. Despite the known asymmetry of PD motor symptom manifestation, the difference between the most affected side (MAS) and least affected side (LAS) is rarely considered in FOG detection and prediction studies. Methods: To examine the effect of using data from the MAS, LAS, or both limbs for FOG prediction, plantar pressure data were collected during a series of walking trials and used to extract time and frequency-based features. Three datasets were created using plantar pressure data from the MAS, LAS, and both sides together. ReliefF feature selection was performed. FOG prediction models were trained using the top 5, 10, 15, 20, 25, or 30 features for each dataset. Results: The best models were the MAS model with 15 features and the LAS and bilateral models with 5 features. The LAS model had the highest sensitivity (79.5%) and identified the highest percentage of FOG episodes (94.9%). The MAS model achieved the highest specificity (84.9%) and lowest false positive rate (1.9 false positives/walking trial). Overall, the bilateral model was best with 77.3% sensitivity and 82.9% specificity. In addition, the bilateral model identified 94.2% of FOG episodes an average of 0.8 s before FOG onset. Compared to the bilateral model, the LAS model had a higher false positive rate; however, the bilateral and LAS models were similar in all the other evaluation metrics. Conclusion: The LAS model would have similar FOG prediction performance to the bilateral model at the cost of slightly more false positives. Given the advantages of single sensor systems, the increased false positive rate may be acceptable to people with PD. Therefore, a single plantar pressure sensor placed on the LAS could be used to develop a FOG prediction system and produce performance similar to a bilateral system.

Prediction and detection of freezing of gait in Parkinson's disease from plantar pressure data using long short-term memory neural-networks.

BACKGROUND: Freezing of gait (FOG) is a walking disturbance in advanced stage Parkinson's disease (PD) that has been associated with increased fall risk and decreased quality of life. Freezing episodes can be mitigated or prevented with external intervention such as visual or auditory cues, activated by FOG prediction and detection systems. While most research on FOG detection and prediction has been based on inertial measurement unit (IMU) and accelerometer data, plantar-pressure data may capture subtle weight shifts unique to FOG episodes. Different machine learning algorithms have been used for FOG detection and prediction; however, long short-term memory (LSTM) deep learning methods hold an advantage when dealing with time-series data, such as sensor data. This research aimed to determine if LSTM can be used to detect and predict FOG from plantar pressure data alone, specifically for use in a real-time wearable system. METHODS: Plantar pressure data were collected from pressure-sensing insole sensors worn by 11 participants with PD as they walked a predefined freeze-provoking path. FOG instances were labelled, 16 features were extracted, and the dataset was balanced and normalized (z-score). The resulting datasets were classified using long short-term memory neural-network models. Separate models were trained for detection and prediction. For prediction models, data before FOG were included in the target class. Leave-one-freezer-out cross validation was used for model evaluation. In addition, the models were tested on all non-freezer data to determine model specificity. RESULTS: The best FOG detection model had 82.1% (SD 6.2%) mean sensitivity and 89.5% (SD 3.6%) mean specificity for one-freezer-held-out cross validation. Specificity improved to 93.3% (SD 4.0%) when ignoring inactive state data (standing) and analyzing the model only on active states (turning and walking). The model correctly detected 95% of freeze episodes. The best FOG prediction method achieved 72.5% (SD 13.6%) mean sensitivity and 81.2% (SD 6.8%) mean specificity for one-freezer-held-out cross validation. CONCLUSIONS: Based on FOG data collected in a laboratory, the results suggest that plantar pressure data can be used for FOG detection and prediction. However, further research is required to improve FOG prediction performance, including training with a larger sample of people who experience FOG.

Grouping successive freezing of gait episodes has neutral to detrimental effect on freeze detection and prediction in Parkinson's disease.

Freezing of gait (FOG) is an intermittent walking disturbance experienced by people with Parkinson's disease (PD). Wearable FOG identification systems can improve gait and reduce the risk of falling due to FOG by detecting FOG in real-time and providing a cue to reduce freeze duration. However, FOG prediction and prevention is desirable. Datasets used to train machine learning models often generate ground truth FOG labels based on visual observation of specific lower limb movements (event-based definition) or an overall inability to walk effectively (period of gait disruption based definition). FOG definition ambiguity may affect model performance, especially with respect to multiple FOG in rapid succession. This research examined whether merging multiple freezes that occurred in rapid succession could improve FOG detection and prediction model performance. Plantar pressure and lower limb acceleration data were used to extract a feature set and train decision tree ensembles. FOG was labeled using an event-based definition. Additional datasets were then produced by merging FOG that occurred in rapid succession. A merging threshold was introduced where FOG that were separated by less than the merging threshold were merged into one episode. FOG detection and prediction models were trained for merging thresholds of 0, 1, 2, and 3 s. Merging slightly improved FOG detection model performance; however, for the prediction model, merging resulted in slightly later FOG identification and lower precision. FOG prediction models may benefit from using event-based FOG definitions and avoiding merging multiple FOG in rapid succession.

Early Detection of Freezing of Gait during Walking Using Inertial Measurement Unit and Plantar Pressure Distribution Data.

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.

High-accuracy 3D surface measurement using hybrid multi-frequency composite-pattern temporal phase unwrapping.

Multi-frequency temporal phase unwrapping (TPU) has been extensively used in phase-shifting profilometry (PSP) for the high-accuracy measurement of objects with surface discontinuities and isolated objects. However, a large number of fringe patterns are commonly required. To reduce the number of required patterns, a new hybrid multi-frequency composite-pattern TPU method was developed using fewer patterns than conventional TPU. The new method combines a unit-frequency ramp pattern with three low-frequency phase-shifted fringe patterns to form three composite patterns. These composite patterns are used together with three high-frequency phase-shifted fringe patterns to generate a high-accuracy phase map. The optimal high frequency to achieve high measurement accuracy and reliable phase unwrapping is determined by analyzing the effect of temporal intensity noise on phase error. Experimental results demonstrated that new grayscale hybrid and color hybrid multi-frequency composite-pattern TPU methods can achieve a high-accuracy measurement using only six and three images, respectively.

Prediction of Freezing of Gait in Parkinson's Disease from Foot Plantar-Pressure Arrays using a Convolutional Neural Network.

Freezing of gait (FOG) is a sudden cessation of locomotion in advanced Parkinson's disease (PD). A FOG episode can lead to falls, decreased mobility, and decreased overall quality of life. Prediction of FOG episodes provides an opportunity for intervention and freeze prevention. A novel method of FOG prediction that uses foot plantar pressure data acquired during gait was developed and evaluated, with plantar pressure data treated as 2D images and classified using a convolutional neural network (CNN). Data from five people with PD and a history of FOG were collected during walking trials. FOG instances were identified and data preceding each freeze were labeled as Pre-FOG. Left and right foot FScan pressure frames were concatenated into a single 60x42 pressure array. Each frame was considered as an independent image and classified as Pre-FOG, FOG, or Non-FOG, using the CNN. From prediction models using different Pre-FOG durations, shorter Pre-FOG durations performed best, with Pre-FOG class sensitivity 94.3%, and specificity 95.1%. These results demonstrated that foot pressure distribution alone can be a good FOG predictor when treating each plantar pressure frame as a 2D image, and classifying the images using a CNN. Furthermore, the CNN eliminated the need for feature extraction and selection.Clinical Relevance- This research demonstrated that foot plantar pressure data can be used to predict freezing of gait occurrence, using a convolutional neural network deep learning technique. This had the added advantage of eliminating the need for feature extraction and selection.

Selection of Plantar-Pressure and Ankle-Acceleration Features for Freezing of Gait Detection in Parkinson's Disease using Minimum-Redundancy Maximum-Relevance.

Freezing of gait (FOG) is a major hindrance to daily mobility and can lead to falling in people with Parkinson's disease. While wearable accelerometers and gyroscopes have been commonly used for FOG detection, foot plantar pressure distribution could also be considered for this application, given its usefulness in previous gait-based classification. This research examined 325 plantar-pressure based features and 132 acceleration-based features extracted from the walking data of five males with Parkinson's disease who experienced FOG. A set of 61 features calculated from the time domain, Fast Fourier transform (FFT), and wavelet transform (WT) were extracted from multiple input signals; including, total ground reaction force, foot centre of pressure (COP) position, COP velocity, COP acceleration, and 3D ankle acceleration. Minimum-redundancy maximum relevance (mRMR) feature selection was used to rank all features. Plantar-pressure based features accounted for 4 of the top 5 features (ranks 2, 3, 4, 5); the remaining feature was an ankle acceleration based feature (rank 1). The three highest ranked features were the freeze index (calculated from ankle acceleration), total power in the frequency domain (calculated using the FFT from COP velocity), and mean of the WT detail coefficients (calculated from COP velocity). This preliminary analysis demonstrated that features calculated from plantar pressure, specifically COP velocity, performed comparably to ankle acceleration features. Thus, feature sets for FOG detection may benefit from plantar-pressure based features.

High-frequency color-encoded fringe-projection profilometry based on geometry constraint for large depth range.

In multi-view fringe projection profilometry (FPP), a limitation of geometry-constraint based approaches is the reduced measurement depth range often used to reduce the number of candidate points and increase the corresponding point selection reliability, when high-frequency fringe patterns are used. To extend the depth range, a new method of high-frequency fringe projection profilometry was developed by color encoding the projected fringe patterns to allow reliable candidate point selection even when six candidate points are in the measurement volume. The wrapped phase is directly retrieved using the intensity component of the hue-saturation-intensity (HSI) color space and complementary-hue is introduced to identify color codes for correct corresponding point selection. Mathematical analyses of the effect of color crosstalk on phase calculation and color code identification show that the phase calculation is independent of color crosstalk and that color crosstalk has little effect on color code identification. Experiments demonstrated that the new method can achieve high accuracy in 3D measurement over a large depth range and for isolated objects, using only two high-frequency color-encoded fringe patterns.

Wearable-Sensor-based Detection and Prediction of Freezing of Gait in Parkinson's Disease: A Review.

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.

Real-time motion-induced-error compensation in 3D surface-shape measurement.

Object motion can introduce unknown phase shift and thus measurement error in multi-image phase-shifting methods of fringe projection profilometry. This paper presents a new method to estimate the unknown phase shifts and reduce the motion-induced error by using three phase maps computed over a multiple measurement sequence and calculating the difference between phase maps. The pixel-wise estimation of the motion-induced phase shifts permits phase-error compensation for non-homogeneous surface motion. Experiments demonstrated the ability of the method to reduce motion-induced error in real-time, for shape measurement of surfaces with high depth variation, and moving and deforming surfaces.

Dual-Task Elderly Gait of Prospective Fallers and Non-Fallers: A Wearable-Sensor Based Analysis.

Wearable sensors could facilitate point of care, clinically feasible assessments of dynamic stability and associated fall risk through an assessment of single-task (ST) and dual-task (DT) walking. This study investigated gait changes between ST and DT walking and between older adult prospective fallers and non-fallers. The results were compared to a study based on retrospective fall occurrence. Seventy-five individuals (75.2 ± 6.6 years; 47 non-fallers, 28 fallers; 6 month prospective fall occurrence) walked 7.62 m under ST and DT conditions while wearing pressure-sensing insoles and accelerometers at the head, pelvis, and on both shanks. DT-induced gait changes included changes in temporal measures, centre of pressure (CoP) path stance deviations and coefficient of variation, acceleration descriptive statistics, Fast Fourier Transform (FFT) first quartile, ratio of even to odd harmonics, and maximum Lyapunov exponent. Compared to non-fallers, prospective fallers had significantly lower DT anterior⁻posterior CoP path stance coefficient of variation, DT head anterior⁻posterior FFT first quartile, ST left shank medial⁻lateral FFT first quartile, and ST right shank superior maximum acceleration. DT-induced gait changes were consistent regardless of faller status or when the fall occurred (retrospective or prospective). Gait differences between fallers and non-fallers were dependent on retrospective or prospective faller identification.

Exponential fringe pattern projection approach to gamma-independent phase computation without calibration for gamma nonlinearity in 3D optical metrology.

This paper presents a method that expresses the fringe pattern as an exponential function and a mathematical model for gamma-independent phase computation. The method was compared to: (i) conventional phase measurement without nonlinearity correction, and (ii) conventional gamma correction by pattern pre-distortion based on an input-to-projector camera-output look-up table. The pre-distorted and exponential methods achieved large reduction in error compared to conventional computation with no gamma correction. The advantage of the exponential method is that no system gamma nonlinearity calibration procedure or information is required. This reduces optical system setup before measurement and permits easier use of off-the-shelf projectors.

High-frequency background modulation fringe patterns based on a fringe-wavelength geometry-constraint model for 3D surface-shape measurement.

A new fringe projection method for surface-shape measurement was developed using four high-frequency phase-shifted background modulation fringe patterns. The pattern frequency is determined using a new fringe-wavelength geometry-constraint model that allows only two corresponding-point candidates in the measurement volume. The correct corresponding point is selected with high reliability using a binary pattern computed from intensity background encoded in the fringe patterns. Equations of geometry-constraint parameters permit parameter calculation prior to measurement, thus reducing measurement computational cost. Experiments demonstrated the ability of the method to perform 3D shape measurement for a surface with geometric discontinuity, and for spatially isolated objects.

Detection of Movement Related Cortical Potentials from EEG Using Constrained ICA for Brain-Computer Interface Applications.

The movement related cortical potential (MRCP), a slow cortical potential from the scalp electroencephalogram (EEG), has been used in real-time brain-computer-interface (BCI) systems designed for neurorehabilitation. Detecting MPCPs in real time with high accuracy and low latency is essential in these applications. In this study, we propose a new MRCP detection method based on constrained independent component analysis (cICA). The method was tested for MRCP detection during executed and imagined ankle dorsiflexion of 24 healthy participants, and compared with four commonly used spatial filters for MRCP detection in an offline experiment. The effect of cICA and the compared spatial filters on the morphology of the extracted MRCP was evaluated by two indices quantifying the signal-to-noise ratio and variability of the extracted MRCP. The performance of the filters for detection was then directly compared for accuracy and latency. The latency obtained with cICA (-34 ± 29 ms motor execution (ME) and 28 ± 16 ms for motor imagery (MI) dataset) was significantly smaller than with all other spatial filters. Moreover, cICA resulted in greater true positive rates (87.11 ± 11.73 for ME and 86.66 ± 6.96 for MI dataset) and lower false positive rates (20.69 ± 13.68 for ME and 19.31 ± 12.60 for MI dataset) compared to the other methods. These results confirm the superiority of cICA in MRCP detection with respect to previously proposed EEG filtering approaches.

Faller Classification in Older Adults Using Wearable Sensors Based on Turn and Straight-Walking Accelerometer-Based Features.

Faller classification in elderly populations can facilitate preventative care before a fall occurs. A novel wearable-sensor based faller classification method for the elderly was developed using accelerometer-based features from straight walking and turns. Seventy-six older individuals (74.15 ± 7.0 years), categorized as prospective fallers and non-fallers, completed a six-minute walk test with accelerometers attached to their lower legs and pelvis. After segmenting straight and turn sections, cross validation tests were conducted on straight and turn walking features to assess classification performance. The best "classifier model-feature selector" combination used turn data, random forest classifier, and select-5-best feature selector (73.4% accuracy, 60.5% sensitivity, 82.0% specificity, and 0.44 Matthew's Correlation Coefficient (MCC)). Using only the most frequently occurring features, a feature subset (minimum of anterior-posterior ratio of even/odd harmonics for right shank, standard deviation (SD) of anterior left shank acceleration SD, SD of mean anterior left shank acceleration, maximum of medial-lateral first quartile of Fourier transform (FQFFT) for lower back, maximum of anterior-posterior FQFFT for lower back) achieved better classification results, with 77.3% accuracy, 66.1% sensitivity, 84.7% specificity, and 0.52 MCC score. All classification performance metrics improved when turn data was used for faller classification, compared to straight walking data. Combining turn and straight walking features decreased performance metrics compared to turn features for similar classifier model-feature selector combinations.

Feature selection for elderly faller classification based on wearable sensors.

BACKGROUND: Wearable sensors can be used to derive numerous gait pattern features for elderly fall risk and faller classification; however, an appropriate feature set is required to avoid high computational costs and the inclusion of irrelevant features. The objectives of this study were to identify and evaluate smaller feature sets for faller classification from large feature sets derived from wearable accelerometer and pressure-sensing insole gait data. METHODS: A convenience sample of 100 older adults (75.5 ± 6.7 years; 76 non-fallers, 24 fallers based on 6 month retrospective fall occurrence) walked 7.62 m while wearing pressure-sensing insoles and tri-axial accelerometers at the head, pelvis, left and right shanks. Feature selection was performed using correlation-based feature selection (CFS), fast correlation based filter (FCBF), and Relief-F algorithms. Faller classification was performed using multi-layer perceptron neural network, naïve Bayesian, and support vector machine classifiers, with 75:25 single stratified holdout and repeated random sampling. RESULTS: The best performing model was a support vector machine with 78% accuracy, 26% sensitivity, 95% specificity, 0.36 F1 score, and 0.31 MCC and one posterior pelvis accelerometer input feature (left acceleration standard deviation). The second best model achieved better sensitivity (44%) and used a support vector machine with 74% accuracy, 83% specificity, 0.44 F1 score, and 0.29 MCC. This model had ten input features: maximum, mean and standard deviation posterior acceleration; maximum, mean and standard deviation anterior acceleration; mean superior acceleration; and three impulse features. The best multi-sensor model sensitivity (56%) was achieved using posterior pelvis and both shank accelerometers and a naïve Bayesian classifier. The best single-sensor model sensitivity (41%) was achieved using the posterior pelvis accelerometer and a naïve Bayesian classifier. CONCLUSIONS: Feature selection provided models with smaller feature sets and improved faller classification compared to faller classification without feature selection. CFS and FCBF provided the best feature subset (one posterior pelvis accelerometer feature) for faller classification. However, better sensitivity was achieved by the second best model based on a Relief-F feature subset with three pressure-sensing insole features and seven head accelerometer features. Feature selection should be considered as an important step in faller classification using wearable sensors.

Prospective Fall-Risk Prediction Models for Older Adults Based on Wearable Sensors.

Wearable sensors can provide quantitative, gait-based assessments that can translate to point-of-care environments. This investigation generated elderly fall-risk predictive models based on wearable-sensor-derived gait data and prospective fall occurrence, and identified the optimal sensor type, location, and combination for single and dual-task walking. 75 individuals who reported six month prospective fall occurrence (75.2 ± 6.6 years; 47 non-fallers and 28 fallers) walked 7.62 m under single-task and dual-task conditions while wearing pressure-sensinginsoles and tri-axial accelerometers at the head, pelvis, and left and right shanks. Fall-risk classificationmodels were assessed for all sensor combinations and three model types: neural network, naïve Bayesian, and support vector machine. The best performing model used a neural network, dual-task gait data, and input parameters from head, pelvis, and left shank accelerometers (accuracy = 57%, sensitivity = 43%, and specificity = 65%). The best single-sensor model used a neural network, dual-task gait data, and pelvis accelerometer parameters (accuracy = 54%, sensitivity = 35%, and specificity = 67%). Single-task and dual-task gait assessments provided similar fall-risk model performance. Fall-risk predictive models developed for point-of-care environments should use multi-sensor dual-task gait assessment with the pelvis location considered if assessment is limited to a single sensor.

Elderly fall risk prediction using static posturography.

Maintaining and controlling postural balance is important for activities of daily living, with poor postural balance being predictive of future falls. This study investigated eyes open and eyes closed standing posturography with elderly adults to identify differences and determine appropriate outcome measure cut-off scores for prospective faller, single-faller, multi-faller, and non-faller classifications. 100 older adults (75.5 ± 6.7 years) stood quietly with eyes open and then eyes closed while Wii Balance Board data were collected. Range in anterior-posterior (AP) and medial-lateral (ML) center of pressure (CoP) motion; AP and ML CoP root mean square distance from mean (RMS); and AP, ML, and vector sum magnitude (VSM) CoP velocity were calculated. Romberg Quotients (RQ) were calculated for all parameters. Participants reported six-month fall history and six-month post-assessment fall occurrence. Groups were retrospective fallers (24), prospective all fallers (42), prospective fallers (22 single, 6 multiple), and prospective non-fallers (47). Non-faller RQ AP range and RQ AP RMS differed from prospective all fallers, fallers, and single fallers. Non-faller eyes closed AP velocity, eyes closed VSM velocity, RQ AP velocity, and RQ VSM velocity differed from multi-fallers. RQ calculations were particularly relevant for elderly fall risk assessments. Cut-off scores from Clinical Cut-off Score, ROC curves, and discriminant functions were clinically viable for multi-faller classification and provided better accuracy than single-faller classification. RQ AP range with cut-off score 1.64 could be used to screen for older people who may fall once. Prospective multi-faller classification with a discriminant function (-1.481 + 0.146 x Eyes Closed AP Velocity-0.114 x Eyes Closed Vector Sum Magnitude Velocity-2.027 x RQ AP Velocity + 2.877 x RQ Vector Sum Magnitude Velocity) and cut-off score 0.541 achieved an accuracy of 84.9% and is viable as a screening tool for older people at risk of multiple falls.

Wearable-Sensor-Based Classification Models of Faller Status in Older Adults.

Wearable sensors have potential for quantitative, gait-based, point-of-care fall risk assessment that can be easily and quickly implemented in clinical-care and older-adult living environments. This investigation generated models for wearable-sensor based fall-risk classification in older adults and identified the optimal sensor type, location, combination, and modelling method; for walking with and without a cognitive load task. A convenience sample of 100 older individuals (75.5 ± 6.7 years; 76 non-fallers, 24 fallers based on 6 month retrospective fall occurrence) walked 7.62 m under single-task and dual-task conditions while wearing pressure-sensing insoles and tri-axial accelerometers at the head, pelvis, and left and right shanks. Participants also completed the Activities-specific Balance Confidence scale, Community Health Activities Model Program for Seniors questionnaire, six minute walk test, and ranked their fear of falling. Fall risk classification models were assessed for all sensor combinations and three model types: multi-layer perceptron neural network, naïve Bayesian, and support vector machine. The best performing model was a multi-layer perceptron neural network with input parameters from pressure-sensing insoles and head, pelvis, and left shank accelerometers (accuracy = 84%, F1 score = 0.600, MCC score = 0.521). Head sensor-based models had the best performance of the single-sensor models for single-task gait assessment. Single-task gait assessment models outperformed models based on dual-task walking or clinical assessment data. Support vector machines and neural networks were the best modelling technique for fall risk classification. Fall risk classification models developed for point-of-care environments should be developed using support vector machines and neural networks, with a multi-sensor single-task gait assessment.

Analysis of dual-task elderly gait in fallers and non-fallers using wearable sensors.

Dual-task (DT) gait involves walking while simultaneously performing an attention-demanding task and can be used to identify impaired gait or executive function in older adults. Advancment is needed in techniques that quantify the influence of dual tasking to improve predictive and diagnostic potential. This study investigated the viability of wearable sensor measures to identify DT gait changes in older adults and distinguish between elderly fallers and non-fallers. A convenience sample of 100 older individuals (75.5±6.7 years; 76 non-fallers, 24 fallers based on 6 month retrospective fall occurrence) walked 7.62m under single-task (ST) and DT conditions while wearing pressure-sensing insoles and tri-axial accelerometers at the head, pelvis, and left and right shanks. Differences between ST and DT gait were identified for temporal measures, acceleration descriptive statistics, Fast Fourier Transform (FFT) quartiles, ratio of even to odd harmonics, center of pressure (CoP) stance path coefficient of variation, and deviations to expected CoP stance path. Increased posterior CoP stance path deviations, increased coefficient of variation, decreased FFT quartiles, and decreased ratio of even to odd harmonics suggested increased DT gait variability. Decreased gait velocity and decreased acceleration standard deviations (SD) at the pelvis and shanks could represent compensatory gait strategies that maintain stability. Differences in acceleration between fallers and non-fallers in head posterior SD and pelvis AP ratio of even to odd harmonics during ST, and pelvis vertical maximum Lyapunov exponent during DT gait were identified. Wearable-sensor-based DT gait assessments could be used in point-of-care environments to identify gait deficits.