Plantar Pressure Data Research Articles

Evaluation of novel plantar pressure-based 3-dimensional printed accommodative insoles - A feasibility study

BackgroundCustom insoles are commonly prescribed to patients with diabetes to redistribute plantar pressure and decrease the risk of ulceration. Advances in 3D printing have enabled the creation of 3D-printed personalized metamaterials whose properties are derived not only from the base material but also the lattice microstructures within the metamaterial. Insoles manufactured using personalized metamaterials have both patient-specific geometry and stiffnesses. However, the safety and biomechanical effect of the novel insoles have not yet been tested clinically. MethodsIndividuals without ulcer, neuropathy, or deformity were recruited for this study. In-shoe walking plantar pressure at baseline visit was taken and sensels with pressure over 200 kPa was used to define offloading region(s). Three pairs of custom insoles (two 3D printed insoles with personalized metamaterials (Hybrid and Full) designed based on foot shape and plantar pressure mapping and one standard-of-care diabetic insole as a comparator). In-shoe plantar pressure measurements during walking were recorded in a standardized research shoe and the three insoles and compared across all four conditions. FindingsTwelve individuals were included in the final analysis. No adverse events occurred during testing. Maximum peak plantar pressure and the pressure time integral were reduced in the offloading regions in the Hybrid and Full but not in the standard-of-care compared to the research shoe. InterpretationThis feasibility study confirms our ability to manufacture the 3D printed personalized metamaterials insoles and demonstrates their ability to reduce plantar pressure. We have demonstrated the ability to modify the 3D printed design to offload certain parts of the foot using plantar pressure data and a patient-specific metamaterials in the 3D printed insole design. The advance in 3D printed technology has shown its potential to improve current care.

Using Simultaneous Confidence Bands to Calculate the Margin of Error in Estimating Typical Biomechanical Waveforms.

Studies of human movement usually collect data from multiple repetitions of a task and use the average of all movement trials to approximate the typical kinematics or kinetics pattern for each individual. Few studies report the expected accuracy of these estimated mean kinematics or kinetics waveforms for each individual. The purpose of this study is to demonstrate how simultaneous confidence bands, which is an approach to quantify uncertainty across an entire waveform based on limited data, can be used to calculate margin of error (MOE) for waveforms. Bilateral plantar pressure data were collected from 70 participants as they walked over 4 surfaces for an average of at least 300 steps per surface. The relationship between MOE and the number of steps included in the analysis was calculated using simultaneous confidence bands, and 3 methods commonly used for pointwise estimates: intraclass correlation, sequential averaging, and T-based MOE. The conventional pointwise approaches underestimated the number of trials required to estimate biomechanical waveforms within a desired MOE. Simultaneous confidence bands are an objective approach to more accurately estimate the relationship between the number of trials collected and the MOE in estimating typical biomechanical waveforms.

Gait Recognition Based on the Plantar Pressure Data of Ice and Snow Athletes.

The study of plantar pressure has become a research consensus in the field of biomechanics. The purpose of this paper is to study some lower limb movements in the daily activities of ice and snow athletes to obtain relevant data so as to carry out gait recognition analysis research. This paper selects the average foot pressure, forefoot foot pressure, front and rear foot pressure, foot pressure, toe pressure, 2–5 toe pressure, standing with eyes closed, x- and y-axes speed, foot length, foot width, and other actions of ice and snow athletes. Therefore, correlation analysis, work analysis, and curve fitting analysis were carried out on the joint motion in a single gait cycle. The collection and application of foot pressure and foot posture information are also analyzed. According to the plantar structure, the sole is divided into four parts. The maximum pressure point and coordinates of each part, the pressure center point, the ratio of the width and height of the sole of the foot, and so on are extracted as the haptic features of the gait. The experimental data shows that it can be seen that if the plantar area is divided in advance and the weight of each area is marked, whether standing, walking, or standing with one leg closed eyes can achieve better recognition results, and the accuracy rate is all more than 90 percent. The average recognition accuracy rate using the method of dividing four regions is only about 80%, and the accuracy rate of recognition using the method of dividing eight regions is 82%. It can be seen that the features extracted by the FCM model proposed in this paper contain more information of the plantar pressure image, and the accuracy rate is higher in the classification and recognition.

Gait Analysis in Children with Cerebral Palsy: Are Plantar Pressure Insoles a Reliable Tool?

Cerebral palsy (CP) is a common cause of motor disability, and pedobarography is a useful, non-invasive, portable, and accessible tool; is easy to use in a clinical setting; and can provide plenty of information about foot–soil interaction and gait deviations. The reliability of this method in children with CP is lacking. The aim of this study is to investigate test–retest reliability and minimal detectable change (MDC) of plantar pressure insole variables in children with CP. Eight children performed two trials 8 ± 2.5 days apart, using foot insoles to collect plantar pressure data. Whole and segmented foot measurements were analyzed using intraclass correlation coefficients (ICC). The variability of the data was measured by calculating the standard error of measurement (SEM) and the MDC/ICC values demonstrated high test–retest reliability for most variables, ranging from good to excellent (ICC ≥ 0.60). The SEM and the MDC values were considered low for the different variables. The variability observed between sessions may be attributed to the heterogeneous sub-diagnosis of CP.

Footsteps required for reliable and valid in-shoe plantar pressure assessment during gait per foot region in people with hallux valgus

BackgroundPlantar pressure assessment is commonly performed to identify pathognomonic gait characteristics and evaluate therapeutics against them in people with various foot disorders. Little is known about the reliability and validity of this assessment in people with hallux valgus (HV) per foot region. Research questionThis study aimed to assess the reliability and validity of the in-shoe plantar pressure measurement method during gait in people with HV and the required number of footsteps, as an intra-subject sample size, to ensure a reliable and valid use of this method. MethodsWith an inserted disposable insole plantar pressure sensor in shoes, 17 females with HV (HV angle > 15°) completed three gait trials over the ground at a comfortable speed. Peak plantar pressure data and its distribution in 15 stance phases on the foot clinically diagnosed with HV in each participant were extracted by dividing the foot into eight regions. The intraclass correlation coefficient per foot region and the number of footsteps required to produce a valid peak plantar pressure and distribution (intraclass correlation coefficient > 0.90) were used to measure reliability. Based on the limit of agreement analysis, the coefficient of variation between the averaged value from each incremental footstep (2–14 footsteps) and 15 reference footsteps was calculated. ResultsThe intraclass correlation coefficient of plantar pressure assessment with the in-shoe sensor was 0.606–0.847 in the eight foot regions in people with HV. Additionally, the number of steps required for a valid assessment ranged from two to nine. Hence, the application of averaged values from more than nine footsteps is recommended for this evaluation. SignificanceThis reference sample size is intended to be used in future studies and clinical settings to determine the efficacy of HV treatment.

Medical and Biomechanical Risk Factors for Incident Bone Stress Injury in Collegiate Runners: Can Plantar Pressure Predict Injury?

Background:Bone stress injury (BSI) is a common reason for missed practices and competitions in elite track and field runners.Hypothesis:It was hypothesized that, after accounting for medical risk factors, higher plantar loading during running, walking, and athletic movements would predict the risk of future BSI in elite collegiate runners.Study Design:Cohort study; Level of evidence, 2.Methods:A total of 39 elite collegiate runners (24 male, 15 female) were evaluated during the 2014-2015 academic year to determine the degree to which plantar pressure data and medical history (including Female and Male Athlete Triad risk factors) could predict subsequent BSI. Runners completed athletic movements while plantar pressures and contact areas in 7 key areas of the foot were recorded, and the measurements were reported overall and by specific foot area. Regression models were constructed to determine factors related to incident BSI.Results:Twenty-one runners (12 male, 9 female) sustained ≥1 incident BSI during the study period. Four regression models incorporating both plantar pressure measurements and medical risk factors were able to predict the subsequent occurrence of (A) BSIs in female runners, (B) BSIs in male runners, (C) multiple BSIs in either male or female runners, and (D) foot BSIs in female runners. Model A used maximum mean pressure (MMP) under the first metatarsal during a jump takeoff and only misclassified 1 female with no BSI. Model B used increased impulses under the hindfoot and second through fifth distal metatarsals while walking, and under the lesser toes during a cutting task, correctly categorizing 83.3% of male runners. Model C used higher medial midfoot peak pressure during a shuttle run and triad cumulative risk scores and correctly categorized 93.3% of runners who did not incur multiple BSIs and 66.7% of those who did. Model D included lower hindfoot impulses in the shuttle run and higher first metatarsal MMP during treadmill walking to correctly predict the subsequent occurrence of a foot BSI for 75% of women and 100% without.Conclusion:The models collectively suggested that higher plantar pressure may contribute to risk for BSI.

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

BackgroundFreezing 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.MethodsTo 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.ResultsThe 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.ConclusionThe 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.

Does weight loss affect the center of pressure of children with obesity: a follow-up study

BackgroundChildren with obesity were found to show the greater postural instability compared to the normal-weighted children. However, it’s still unclear if their altered postural control ability would recover towards normal pattern after weight loss. The purpose of this study was to investigate the effect of weight loss on the center of pressure (COP) for obese children.MethodTotally 147 children were conducted a follow-up study in three years. A total number of 22 participants aged 7–13 years were recruited for their remission of obesity problem after 36 months. Their dynamic plantar pressure data were collected by Footscan pressure plate. The normalized time of four sub-phases, displacements and velocities of COP in anterior–posterior (AP) and medial–lateral (ML) directions were calculated to perform the Kolmogorov–Smirnov test and paired sample t test for statistical analyses.ResultsAfter weight loss, children’s normalized time of forefoot contact phase (FFCP) increased significantly, and their duration of flat foot phase (FFP) decreased significantly. They also exhibited the more medial and posterior orientated COP path after weight loss. In ML-direction, the COP displacement during FFP and FFPOP increased, and the COP velocity during FFPOP increased. In AP-direction, COP velocity during FFP and FFPOP increased.ConclusionsThe findings indicated that weight loss would have effects on the COP characteristics and postural stability for obese children. COP trajectory can provide essential information for evaluating foot function. The findings may be useful for obese children, medical staff, and healthcare physician.Graphical

IDF21-0164 Effect of stimulating footwear on gait and posture in people with Diabetes and foot complications

Background: The maintenance of human posture and gait requires the central integration of afferent information and is highly dependent on the somatosensory information from the plantar cutaneous mechanoreceptors. Normal foot structure sends undistorted signals to the brain due to the proper stimulation of mechanoreceptors in the foot soles and therefore brain responds properly by adjusting the skeletal framework into good posture. In the case of abnormal foot structure, the brain receives distorted signals due to poor stimulation of mechanoreceptors. As a result, the brain generates alternate signals to deal with these abnormalities, resulting in poor gait and posture. Aim: The main intention of this study was to develop a new footwear with ultrasonic sensors that emit ultrasonic waves at a lower frequency of 35 kHz to properly stimulate plantar mechanoreceptors. The objective of this study was to evaluate the effect of the above footwear on gait and posture of people with diabetic neuropathy, with foot deformity (bow knee, bilateral genu valgum, leg length discrepancy, abnormal foot arch) and also with foot and/or joint discomfort after 15days of wearing it for 10minutes each day. Method: A total of 5 (3 men and 2 women) subjects volunteered for this study. Informed consent was obtained from each participant. Subjects were prepared using a specialized wireless inertial sensor as per the protocol and were asked to walk freely on the sensorized platform for measuring their plantar pressure and also their spatial temporal parameters. Data was captured using Plantar pressure measuring device and wearable inertial system (BTSBioengineering, Italy). For data analysis, three trials were recorded. A single best trial was selected for processing and reporting. After completion of the initial assessment, subjects were asked to wear the test footwear as a therapy for 10 minutes every day for 15 days. When the switch is on the sensors will emit ultrasound at a frequency of 35 kHz. Following the completion of the 15-days, the subjects were re-evaluated using plantar pressure measuring device and wearable inertial system. Then a comparison was made between the data collected before and after therapy. Results: See Table 1 and Table 2.Table 1Results of Spatial temporal data before and after the therapy. Open table in a new tab Table 2Results of Plantar pressure data before and after the therapy. Open table in a new tab Discussion: The spatiotemporal data, in Table 1, shows a considerable improvement after using the developed footwear. There was a considerable decrease in double limb support time and increase in single limb support, indicating that the subject was able to minimize the contact time of the foot during walking which significantly minimizes foot plantar pressure loading which is the precursor of diabetic foot ulcer. Also, there was a significant increase in cadence and gait velocity after completion of therapy. The plantar pressure data, in Table 2, indicates an increase in the foot contact area which significantly improve the foot pressure distribution, leads to reduction in peak plantar pressure. Also, there was a shift in the maximum pressure from lateral foot to medial foot which shows the distribution of body weight shifted from lateral to medial which is the sign for good posture.

Does insole hardness affect the dynamic postural stability of basketball athletes during jump landing?

This study aimed to examine the effects of shoe insole hardness on the dynamic postural stability of basketball athletes during jump landing manoeuvres. Twenty college basketball athletes were recruited to complete a single-leg jump landing task on a force plate in three insole conditions (soft-, rigid- and no-insole). Kistler force plate and Pedar-X insole system were used to collect the ground reaction force (GRF) and plantar pressure data. Dynamic Postural Stability Index (DPSI), Anterior-Posterior Stability Index (APSI), Medial-Lateral Stability Index (MLSI), and Vertical Stability Index (VSI) were then calculated from GRF data. DPSI, APSI, MLSI, and VSI were statistically conducted among the three insole conditions by a one-way ANOVA with repeated measures. MLSI were decreased when wearing soft- and rigid insoles compared with no-insole condition (p < 0.05). However, there were no significant differences in APSI and VSI among the three insole conditions. In the midfoot region, contact areas were increased in the soft- and rigid insole than the no-insole condition (p < 0.0001). Dynamic balance of basketball athletes in the medial-lateral direction could be enhanced by wearing insoles during jump landings tasks. However, the postural stability of basketball athletes did not increase with insole hardness increasing.

New Distinct Component Patterns for Plantar Pressure Variables by Using Principal Component Analysis.

It is important to determine the plantar pressure distribution of schoolchildren by applying static and dynamic foot analyses using a pedobarography device. However, it is difficult to obtain clear interpretations from results that can be explained by a large number of plantar pressure variables. The aim of this study was to use principal component analysis (PCA) to predict the main components for reducing the size of big data sets, provide a practical overview, and minimize information loss on the subject of plantar pressure assessment in youths. In total, 112 schoolchildren were included in the study (mean ± SD: age, 10.58 ± 1.27 years; body mass index, 18.86 ± 4.33). During the research, a pedobarography device was used to obtain plantar pressure data. Each foot was divided into six anatomical regions and evaluated. Global and regional plantar pressure distributions, load and surface areas, pressure-time integrals, weight ratios, and geometric foot properties were calculated. The PCA yielded ten principal components that together account for 81.88% of the variation in the data set and represent new and distinct patterns. Thus, 137 variables affecting the subject were reduced to ten components. The numerous variables that affect static and dynamic plantar pressure distributions can be reduced to ten components by PCA, making the research results more concise and understandable.

Deep learning-based networks for automated recognition and classification of awkward working postures in construction using wearable insole sensor data

Among the numerous work-related risk factors, construction workers are often exposed to awkward working postures that may lead them to develop work-related musculoskeletal disorders (WMSDs). To mitigate WMSDs among construction workers, awkward working posture recognition is the first step in proactive WMSD prevention. Several researchers have proposed wearable sensor-based systems and machine learning classifiers for awkward posture recognition. However, these wearable sensor-based systems (e.g., surface electromyography) are either intrusive or require attaching multiple sensors on workers' bodies, which may lead to workers' discomfort and systemic instability, thus, limiting their application on construction sites. In addition, machine learning classifiers are limited to human-specific shallow features which influence model performance. To address these limitations, this study proposes a novel approach by using wearable insole pressure system and recurrent neural network (RNN) models, which automate feature extraction and are widely used for sequential data classification. Therefore, the research objective is to automatically recognize and classify different types of awkward working postures in construction by using deep learning-based networks and wearable insole sensor data. The classification performance of three RNN-based deep learning models, namely: (1) long-short term memory (LSTM), (2) bidirectional LSTM (Bi-LSTM), and (3) gated recurrent units (GRU), was evaluated using plantar pressure data captured by a wearable insole system from workers on construction sites. The experimental results show that GRU model outperforms the other RNN-based deep learning models with a high accuracy of 99.01% and F1-score between 93.19% and 99.39%. These results demonstrate that GRU models can be employed to learn sequential plantar pressure patterns captured by a wearable insole system to recognize and classify different types of awkward working postures. The findings of this study contribute to wearable sensor-based posture-related recognition and classification, thus, enhancing construction workers' health and safety.

Effects of orthotic insole on gait patterns in children with mild leg length discrepancy

BackgroundLeg length discrepancy (LLD) is commonly associated with compensatory gait strategies leading to musculoskeletal disorders of the lower extremity and lumbar spine. Orthotic insole (OI) is considered as a conservative treatment for patients with mild LLD, especially for children. However, the restoration of normal gait when wearing OI with foot lift are still poorly understood. Research questionWhat are the immediate effects of OI on the gait patterns in children with mild LLD? MethodsGait data and plantar pressure data were collected for 12 children with mild anatomical LLD in barefoot and OI conditions. Paired t-test was performed to determine the changes in gait between these two conditions, and also the symmetry between limbs in the same condition for spatiotemporal, kinematic, and kinetic variables. ResultsChildren with mild LLD showed an immediate gait improvement confirmed by increased step length and velocity, decreased peak plantar pressure in both limbs with OI. Additionally, the significant between-limb differences disappeared for peak ankle dorsiflexion, hip adduction, pelvis upward obliquity and also second peak plantar pressure with OI, which improved gait symmetry. SignificanceThis study provides a better understanding of the immediate effect of OI with foot lift on biomechanical changes in gait, which identify that OI with foot lift could be a potential therapeutic option for children with mild structural LLD to improve gait metrics.

Plantar pressure-based temporal analysis of gait disturbance in idiopathic normal pressure hydrocephalus: Indications from a pilot longitudinal study

Background and Objective: Idiopathic normal pressure hydrocephalus (iNPH) is a common yet potentially reversible neurodegenerative disease, and gait disturbance is a major symptom. Lots of methodological and clinical work has been conducted on gait disturbance analysis for differential diagnosis, presurgical test, and postsurgery assessment of iNPH. Nevertheless, the verification analysis was mostly lacking for surgery response, and the temporal characteristics of ground reaction force has been rarely investigated.Methods: In this work, we propose that plantar pressure features fundamentally signifies iNPH gait disturbance and improvement after cerebrospinal fluid (CSF) drainage by lumbar puncture tap test as well as surgical shunt implantation. The plantar pressure signals of six iNPH patients and eight healthy controls were collected, and an online database of sixteen healthy controls were used. For patients, data were collected in five periods, which are the baseline before the tap test, 8, 24, and 72 hours after the tap test, and one month after the shunt implantation surgery, respectively. Fast dynamic time warping (DTW) with an improved DTW barycenter averaging (DBA) method was proposed for temporal analysis with the measured and online plantar pressure data. An plantar-pressure variation index (PPVI) was formulated to characterize the temporal dynamic stability of walking.Results: The PPVI based on temporal analysis of plantar pressure well discriminated the impaired gait (baseline, 24 and 72 hours after tap test) with the improved gait (8 hours after tap test and follow up after surgery) of the patients. Further, the PPVI was close for the improved gait of the patients and the healthy gait measured in our study as well as in the online database.Conclusions: Plantar pressure-based temporal features are promisingly effective for clinical examination and treatment of iNPH.

Recognising and predicting gait cycle states for weight-reducing exoskeleton robots using deep learning

In this study, we propose to use plantar pressure distribution data. Using a combined approach of deep learning and ensemble learning. A proposal for implementing weight-reducing exoskeleton robot in walking gait recognition and temporal prediction. The challenge points of this problem is system architecture design, transformation of data features and morphology, plantar pressure data acquisition and gait data recognition and prediction in real-time. In this paper, we design the system design and implementation for real-time plantar pressure data collection using IoT approach, and real-time gait recognition and prediction using CNN + RNN + ensemble learning model. We designed a plantar pressure measurement device and obtained walking gait datasets through the device. The model is trained using the dataset to obtain a gait recognition and prediction model. Our proposed system solution was implemented for both non-actual walking and actual walking experiments. It is shown experimentally that the gait recognition and gait prediction results of the integrated learning approach in the non-actual walking experiments are 96% and 37%. The gait recognition and gait prediction results of the integrated learning approach in the actual walking experiments are 69% and 42% results.

Comparison of the Forefoot Pressure-Relieving Effects of Foot Orthoses.

PurposeMetatarsal pads are prescribed to decrease forefoot plantar pressure. However, the appropriate metatarsal pad placement location remains a debated issue. We aimed to identify the most effective insole design that reduces forefoot plantar pressure and determine the optimal position for metatarsal pad placement.Materials and MethodsWe recruited 16 healthy adult volunteers, and measured their plantar pressure data during walking while using an in-shoe system. The volunteers were randomly assigned to one of four insole conditions: 1/16-inch insole (i.e., control), 1/4-inch soft plastazote (SP) flat insole, metatarsal pad positioned proximal to the metatarsal head (MTH) on the control insole (P0), and metatarsal pad positioned 10 mm distal from the proximal border of the MTH on the control insole (P10). A masking protocol was created by dividing the forefoot into three subareas, distal to the MTH (dMTH), beneath to the MTH (bMTH), and proximal to the MTH (pMTH). The participants reported their comfort level for each insole using a visual analog scale.ResultsThe SP flat insole and metatarsal pads both had a forefoot plantar pressure-reducing effect and provided insole comfort. Of the three insole designs, the SP flat insole was the most effective. No clear difference existed in efficacy in terms of the location of the metatarsal pad placement.ConclusionConsidering the possibility of discomfort caused by improper metatarsal pad placement, the SP that increases shock absorption may be more clinically useful.

Validity of estimating center of pressure during walking and running with plantar load from a three-sensor wireless insole.

The purpose of this study was to determine if estimated center of pressure (COP) from plantar force data collected using three-sensor loadsol insoles was comparable to the COP from plantar pressure data collected using pedar insoles during walking and running. Ten healthy adults walked and ran at self-selected speeds on a treadmill while wearing both a loadsol and pedar insole in their right shoe. Plantar force recorded from the loadsol was used to estimate COP along mediolateral (COPx) and anteroposterior (COPy) axes. The estimated COPx and COPy were compared with the COPx and COPy from pedar using limits of agreement and Spearman's rank correlation. There were significant relationships and agreement within 5mm in COPx and 20mm in COPy between loadsol and pedar at 20-40% of stance during walking and running. However, loadsol demonstrated biases of 7mm in COPx and 10mm in COPy compared to pedar near initial contact and toe-off.

Prediction and detection of freezing of gait in Parkinson\u2019s disease from plantar pressure data using long short-term memory neural-networks

BackgroundFreezing 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.MethodsPlantar 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.ResultsThe 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.ConclusionsBased 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.

Impact of Asthma on Plantar Pressures in a Sample of Adult Patients: A Case-Control Study.

Based on the high prevalence of asthma in the population, and its relationship with various musculoskeletal and postural disorders, the aim of this study was to evaluate the plantar pressures in asthmatic patients compared to a control group. A case-control study involving 90 participants was conducted, consisting of 45 asthma patients and 45 healthy paired controls. Static plantar pressure data were recorded using a portable pressure sensor platform. Statistically significant differences were shown in the body weight on the left heel (p = 0.031), and the right forefoot maximum peak pressure was lower in the case group (p = 0.042). The findings of this study show alterations in static plantar pressures in asthmatic patients compared to healthy individuals. Specifically, the subjects with asthma showed less maximum pressure in the right forefoot and less weight on the left heel, which appear to be associated with the asthma disease.

Gait and balance patterns related to Free-Walking and TUG tests in Parkinson's Disease based on plantar pressure data.

Continuous monitoring of patients with Parkinson's Disease (PD) is critical for their effective management, as early detection of improvement or degradation signs play an important role on pharmaceutical and/or interventional plans. Within this work, a group of seven PD patients and a group of ten controls performed a set of exercises related to the evaluation of PD gait. Plantar pressure signals were collected and used to derive a set of analytics. Statistical tests and feature selection approaches revealed that the spatial distribution of the Center of Pressure during a static balance exercise is the most discriminative analytic and may be used for every-day monitoring of the patients. Results have revealed that out of the 28 features extracted from the collected signals, 10 were statistically significant (p < 0.05) and can be used to machine learning algorithms and/or similar approaches.