Pre-impact fall detection

A dynamic spatiotemporal model for fall warning and protection

Early detection of falls is important for reducing fall injuries. However, existing fall detection strategies mostly focus on reducing impact injuries rather than avoiding falls. This study proposed the concept of identifying "Imbalance Point" to warn the body imbalance, allowing sufficient time to recover balance. And if falling cannot be avoided, an impact sign is released by detecting the "Fall Point" prior to the impact. To achieve this goal, motion prediction model and balance recovery model are integrated into a spatiotemporal framework to analyze dynamic and kinematic features of body motion. Eight healthy young volunteers participated in three sets of experiment: Normal trial, Recovery trial and Fall trial. The body motion in the trials was recorded using Microsoft Azure Kinect. The results show that the developed algorithm for Fall Point detection achieved 100% sensitivity and 98.6% specificity, along with an average lead time of 297 ms. Moreover, Imbalance Point was successfully detected in all Fall trials, and the average time interval between Imbalance Point and Fall Point was 315 ms, longer than reported step reaction time for elderly (approximately 270 ms). The experiment results demonstrate that the developed algorithm have great potential for fall warning and protection in the elderly.

The Methods of Fall Detection: A Literature Review

Fall Detection Systems (FDS) are automated systems designed to detect falls experienced by older adults or individuals. Early or real-time detection of falls may reduce the risk of major problems. This literature review explores the current state of research on FDS and its applications. The review shows various types and strategies of fall detection methods. Each type of fall detection is discussed with its pros and cons. Datasets of fall detection systems are also discussed. Security and privacy issues related to fall detection systems are also considered in the discussion. The review also examines the challenges of fall detection methods. Sensors, algorithms, and validation methods related to fall detection are also talked over. This work found that fall detection research has gradually increased and become popular in the last four decades. The effectiveness and popularity of all strategies are also discussed. The literature review underscores the promising potential of FDS and highlights areas for further research and development.

The Chinese Short Version of the Activities-Specific Balance Confidence Scale: Its Validity, Reliability, and Predictive Value for Future Falls in Community-Dwelling Older Adults

Purpose

To examine the reliability and validity of the Chinese short version of the Activities-specific Balance Confidence scale (ABC-6), and its predictive value for prospective falls in community-dwelling older adults.

Patients and Methods

A total of 391 community older adults completed the prospective study. Internal consistency reliability, test-retest reliability, structural validity and discriminant validity were analyzed. To determine the accuracy of ABC-6 total score in predicting falls, a receiver operating characteristic curve analysis was performed, and comparisons with the Activities-specific Balance Confidence scale (ABC-16) and Berg Balance Scale (BBS) were made.

Results

Excellent internal consistency (Cronbach’s α = 0.938) and test-retest reliability (ICC=0.964, 95% CI: 0.947–0.977) were found for the ABC-6. Exploratory factor analysis suggested that ABC-6 had a one-factor structure (explained variance, 68.30%). The optimal cutoff value, sensitivity and specificity of ABC-6 to distinguish fallers from non-fallers was ≤ 60.00%, 70.83% and 84.26%, respectively, and there was no significant difference in the predictive value among the ABC-6, ABC-16, and BBS.

Conclusion

The Chinese version of the ABC-6 scale was a valid and reliable tool for measuring self-perceived balance confidence in community-dwelling older adults, and can be used as an effective assessment tool to predict future falls.

Prevalence and Risk Factors for Fall among Rural Elderly: A County-Based Cross-Sectional Survey

AIM

The aim of the study was to provide evidence for the prevention and reduction of falls in the elderly living in rural areas by analyzing epidemiological data of falls among the rural older people (>65 years old) and identifying the risk and protective factors.

METHODS

This study analyzed the sociodemographic characteristics, living environment, lifestyle, chronic disease condition, mental health, activities of daily living (ADL), and detailed information of falls of 3752 rural elderly. Rank tests, chi-square tests, and binary logistic regression were used for data analysis.

RESULTS

The prevalence of falls was 30.0%, and the 75-84-years age group had the highest fall rate (18.8%). According to the binary logistic regression analysis, six variables, including roughage intake frequency, age, gender, cane use, floor tiles, and IADL, were involved in the fall patterns. Low roughage intake (OR = 2.48, 95% CI 1.24-4.97), female gender (OR = 2.12, 95% CI 1.48-3.05), the use of a cane (OR = 2.11, 95% CI 1.08-4.10), and medium IADL (OR = 2.02, 95% CI 1.89-2.32) were the top four risk factors.

CONCLUSION

The fall in the rural elderly was mainly due to the poor living and working conditions. Routine fall assessment could address several preventable risk factors to reduce the prevalence and mitigate the harm of falls.

Wearable inertial sensors for human movement analysis: a five-year update

INTRODUCTION

The aim of the present review is to track the evolution of wearable IMUs from their use in supervised laboratory- and ambulatory-based settings to their application for long-term monitoring of human movement in unsupervised naturalistic settings.

AREAS COVERED

Four main emerging areas of application were identified and synthesized, namely, mobile health solutions (specifically, for the assessment of frailty, risk of falls, chronic neurological diseases, and for the monitoring and promotion of active living), occupational ergonomics, rehabilitation and telerehabilitation, and cognitive assessment. Findings from recent scientific literature in each of these areas was synthesized from an applied and/or clinical perspective with the purpose of providing clinical researchers and practitioners with practical guidance on contemporary uses of inertial sensors in applied clinical settings.

EXPERT OPINION

IMU-based wearable devices have undergone a rapid transition from use in laboratory-based clinical practice to unsupervised, applied settings. Successful use of wearable inertial sensing for assessing mobility, motor performance and movement disorders in applied settings will rely also on machine learning algorithms for managing the vast amounts of data generated by these sensors for extracting information that is both clinically relevant and interpretable by practitioners.

Human inspired fall arrest strategy for humanoid robots based on stiffness ellipsoid optimisation

Falls are a common risk and impose severe threats to both humans and humanoid robots as a product of bipedal locomotion. Inspired by human fall arrest, we present a novel humanoid robot fall prevention strategy by using arms to make contact with environmental objects. Firstly, the capture point method is used to detect falling. Once the fall is inevitable, the arm of the robot will be actuated to gain contact with an environmental object to prevent falling. We propose a hypothesis that humans naturally favour to select a pose that can generate a suitable Cartesian stiffness of the arm end-effector. Based on this principle, a configuration optimiser is designed to choose a pose of the arm that maximises the value of the stiffness ellipsoid of the endpoint along the impact force direction. During contact, the upper limb acts as an adjustable active spring-damper and absorbs impact shock to steady itself. To validate the proposed strategy, several simulations are performed in MATLAB & Simulink by having the humanoid robot confront a wall as a case study in which the strategy is proved to be effective and feasible. The results show that using the proposed strategy can reduce the joint torque during impact when the arms are used to arrest the fall.

A Large-Scale Open Motion Dataset (KFall) and Benchmark Algorithms for Detecting Pre-impact Fall of the Elderly Using Wearable Inertial Sensors

Research on pre-impact fall detection with wearable inertial sensors (detecting fall accidents prior to body-ground impacts) has grown rapidly in the past decade due to its great potential for developing an on-demand fall-related injury prevention system. However, most researchers use their own datasets to develop fall detection algorithms and rarely make these datasets publicly available, which poses a challenge to fairly evaluate the performance of different algorithms on a common basis. Even though some open datasets have been established recently, most of them are impractical for pre-impact fall detection due to the lack of temporal labels for fall time and limited types of motions. In order to overcome these limitations, in this study, we proposed and publicly provided a large-scale motion dataset called “KFall,” which was developed from 32 Korean participants while wearing an inertial sensor on the low back and performing 21 types of activities of daily living and 15 types of simulated falls. In addition, ready-to-use temporal labels of the fall time based on synchronized motion videos were published along with the dataset. Those enhancements make KFall the first public dataset suitable for pre-impact fall detection, not just for post-fall detection. Importantly, we have also developed three different types of latest algorithms (threshold based, support-vector machine, and deep learning), using the KFall dataset for pre-impact fall detection so that researchers and practitioners can flexibly choose the corresponding algorithm. Deep learning algorithm achieved both high overall accuracy and balanced sensitivity (99.32%) and specificity (99.01%) for pre-impact fall detection. Support vector machine also demonstrated a good performance with a sensitivity of 99.77% and specificity of 94.87%. However, the threshold-based algorithm showed relatively poor results, especially the specificity (83.43%) was much lower than the sensitivity (95.50%). The performance of these algorithms could be regarded as a benchmark for further development of better algorithms with this new dataset. This large-scale motion dataset and benchmark algorithms could provide researchers and practitioners with valuable data and references to develop new technologies and strategies for pre-impact fall detection and proactive injury prevention for the elderly.

Validation of a smartphone embedded inertial measurement unit for measuring postural stability in older adults

BACKGROUND

Identifying older adults with increased fall risk due to poor postural control on a large scale is only possible through omnipresent and low cost measuring devices such as the inertial measurement units (IMU) embedded in smartphones. However, the correlation between smartphone measures of postural stability and state-of-the-art force plate measures has never been assessed in a large sample allowing us to take into account age as a covariate.

RESEARCH QUESTION

How reliably can postural stability be measured with a smartphone embedded IMU in comparison to a force plate?

METHODS

We assessed balance in 97 adults aged 50-90 years in four different conditions (eyes open, eyes closed, semi-tandem and dual-task) in the anterio-posterior and medio-lateral directions. We used six different parameters (root mean square and average absolute value of COP displacement, velocity and acceleration) for the force plate and two different parameters (root mean square and average absolute value of COM acceleration) for the smartphone.

RESULTS

Test-retest reliability was smaller for the smartphone than for the force plate (intra class correlation) but both devices could equally well detect differences between conditions (similar Cohen's d). Parameters from the smartphone and the force plate, with age regressed out, were moderately correlated (robust correlation coefficients of around 0.5).

SIGNIFICANCE

This study comprehensively documents test-retest reliability and effect sizes for stability measures obtained with a force plate and smartphone as well as correlations between force plate and smartphone measures based on a large sample of older adults. Our large sample size allowed us to reliably determine the strength of the correlations between force plate and smartphone measures. The most important practical implication of our results is that more repetitions or longer trials are required when using a smartphone instead of a force plate to assess balance.

Acceleration Magnitude at Impact Following Loss of Balance Can Be Estimated Using Deep Learning Model

Pre-impact fall detection can detect a fall before a body segment hits the ground. When it is integrated with a protective system, it can directly prevent an injury due to hitting the ground. An impact acceleration peak magnitude is one of key measurement factors that can affect the severity of an injury. It can be used as a design parameter for wearable protective devices to prevent injuries. In our study, a novel method is proposed to predict an impact acceleration magnitude after loss of balance using a single inertial measurement unit (IMU) sensor and a sequential-based deep learning model. Twenty-four healthy participants participated in this study for fall experiments. Each participant worn a single IMU sensor on the waist to collect tri-axial accelerometer and angular velocity data. A deep learning method, bi-directional long short-term memory (LSTM) regression, is applied to predict a fall's impact acceleration magnitude prior to fall impact (a fall in five directions). To improve prediction performance, a data augmentation technique with increment of dataset is applied. Our proposed model showed a mean absolute percentage error (MAPE) of 6.69 ± 0.33% with r value of 0.93 when all three different types of data augmentation techniques are applied. Additionally, there was a significant reduction of MAPE by 45.2% when the number of training datasets was increased by 4-fold. These results show that impact acceleration magnitude can be used as an activation parameter for fall prevention such as in a wearable airbag system by optimizing deployment process to minimize fall injury in real time.

A Novel Hybrid Deep Neural Network to Predict Pre-impact Fall for Older People Based on Wearable Inertial Sensors

Falls in the elderly is a major public health concern due to its high prevalence, serious consequences and heavy burden on the society. Many falls in older people happen within a very short time, which makes it difficult to predict a fall before it occurs and then to provide protection for the person who is falling. The primary objective of this study was to develop deep neural networks for predicting a fall during its initiation and descending but before the body impacts to the ground so that a safety mechanism can be enabled to prevent fall-related injuries. We divided the falling process into three stages (non-fall, pre-impact fall and fall) and developed deep neutral networks to perform three-class classification. Three deep learning models, convolutional neural network (CNN), long short term memory (LSTM), and a novel hybrid model integrating both convolution and long short term memory (ConvLSTM) were proposed and evaluated on a large public dataset of various falls and activities of daily living (ADL) acquired with wearable inertial sensors (accelerometer and gyroscope). Fivefold cross validation results showed that the hybrid ConvLSTM model had mean sensitivities of 93.15, 93.78, and 96.00% for non-fall, pre-impact fall and fall, respectively, which were higher than both LSTM (except the fall class) and CNN models. ConvLSTM model also showed higher specificities for all three classes (96.59, 94.49, and 98.69%) than LSTM and CNN models. In addition, latency test on a microcontroller unit showed that ConvLSTM model had a short latency of 1.06 ms, which was much lower than LSTM model (3.15 ms) and comparable with CNN model (0.77 ms). High prediction accuracy (especially for pre-impact fall) and low latency on the microboard indicated that the proposed hybrid ConvLSTM model outperformed both LSTM and CNN models. These findings suggest that our proposed novel hybrid ConvLSTM model has great potential to be embedded into wearable inertial sensor-based systems to predict pre-impact fall in real-time so that protective devices could be triggered in time to prevent fall-related injuries for older people.

High-Specificity Digital Architecture for Real-Time Recognition of Loss of Balance Inducing Fall

Falls are a significant cause of loss of independence, disability and reduced quality of life in people with Parkinson's disease (PD). Intervening quickly and accurately on the postural instability could strongly reduce the consequences of falls. In this context, the paper proposes and validates a novel architecture for the reliable recognition of losses of balance situations. The proposed system addresses some challenges related to the daily life applicability of near-fall recognition systems: the high specificity and system robustness against the Activities of Daily Life (ADL). In this respect, the proposed algorithm has been tested on five different tasks: walking steps, sudden curves, chair transfers via the timed up and go (TUG) test, balance-challenging obstacle avoidance and slip-induced loss of balance. The system analyzes data from wireless acquisition devices that capture electroencephalography (EEG) and electromyography (EMG) signals. The collected data are sent to two main units: the muscular unit and the cortical one. The first realizes a binary ON/OFF pattern from muscular activity (10 EMGs) and triggers the cortical unit. This latter unit evaluates the rate of variation in the EEG power spectrum density (PSD), considering five bands of interest. The neuromuscular features are then sent to a logical network for the final classification, which distinguishes among falls and ADL. In this preliminary study, we tested the proposed model on 9 healthy subjects (aged 26.3 ± 2.4 years), even if the study on PD patients is under investigation. Experimental validation on healthy subjects showed that the system reacts in 370.62 ± 60.85 ms with a sensitivity of 93.33 ± 5.16%. During the ADL tests the system showed a specificity of 98.91 ± 0.44% in steady walking steps recognition, 99.61 ± 0.66% in sudden curves detection, 98.95 ± 1.27% in contractions related to TUG tests and 98.42 ± 0.90% in the obstacle avoidance protocol.

Pre-Impact Fall Detection Using 3D Convolutional Neural Network

Early fall detection is an important issue during gait rehabilitation training. This paper proposes an approach for pre-impact fall detection during gait rehabilitation training based on a 3D convolutional neural network (CNN). Firstly, pre-training data is collected and used to pre-train the 3D CNN to differentiate between a normal walking and a fall based on their general spatio-temporal patterns. Secondly, fine-tuning data is created by combining the pre-training data with a 3second normal walking sample collected from a new trainee whose falls are to be detected. The pre-trained 3D CNN is further fine-tuned by the fine-tuning data to learn the spatiotemporal patterns of the new trainee. Finally, a temporal sliding window is used to feed video snippets into the fine-tuned 3D CNN for fall detection. To the best of our knowledge, this is the first pre-impact fall detection approach based on a 3D CNN using RGB images. Moreover, the training strategy used to train the 3D CNN can alleviate the generalization issue of the 3D CNN when only limited training data is available in gait rehabilitation training. With 225 testing trials from 5 trainees, the proposed pre-impact fall detection approach achieves a detection accuracy of 100% within 0.5 second after falls start. Experiment results show that this approach is efficient, accurate, and practical in achieving intelligent fall detection during gait rehabilitation training.

Evaluation of time-frequency features as detectors of lack of balance due to tripping-like perturbations

Unbalancing events during gait can end up in falls and, thus, injury. Detecting events that could bring to fall and consequently activating fall prevention systems before the impact may help to mitigate related injuries. However, there is uncertainty about signals and methods that could offer the best performance. In this paper we investigated a novel trip detection method based on time-frequency features to evaluate the performances of these features as trip detectors. Hip angles of eight healthy young subjects were recorded while performing unexpected tripping trials delivered during steady locomotion. Then the Short-Time Fourier Transform (STFT) of the hip angle was estimated. Median frequency, power, centroidal frequency as well as frequency dispersion were computed for each time sliced power spectrum. These features were used as input for a trip detection algorithm. We assessed detection time (T_detect), specificity (Spec) and sensitivity (Sens) for each feature. Performances obtained with median frequencies over time(T_detect 0.91 ± 0.47 s; Sens 0.96) were better than those obtained using the hip angle signal in time domain (T_detect 1.19 ± 0.27 s; Sens 0.83). Other features did not show significant results. Thus, median frequency over time expected to achieve effective real-time event detection systems, with the aim of a future on-board application concerning detection and prevention measures.

Pre-Impact Detection Algorithm to Identify Tripping Events Using Wearable Sensors

This study aimed to investigate the performance of an updated version of our pre-impact detection algorithm parsing out the output of a set of Inertial Measurement Units (IMUs) placed on lower limbs and designed to recognize signs of lack of balance due to tripping. Eight young subjects were asked to manage tripping events while walking on a treadmill. An adaptive threshold-based algorithm, relying on a pool of adaptive oscillators, was tuned to identify abrupt kinematics modifications during tripping. Inputs of the algorithm were the elevation angles of lower limb segments, as estimated by IMUs located on thighs, shanks and feet. The results showed that the proposed algorithm can identify a lack of balance in about 0.37 ± 0.11 s after the onset of the perturbation, with a low percentage of false alarms (<10%), by using only data related to the perturbed shank. The proposed algorithm can hence be considered a multi-purpose tool to identify different perturbations (i.e., slippage and tripping). In this respect, it can be implemented for different wearable applications (e.g., smart garments or wearable robots) and adopted during daily life activities to enable on-demand injury prevention systems prior to fall impacts.

Machine learning-based pre-impact fall detection model to discriminate various types of fall

Preimpact fall detection can send alarm service faster to reduce long-lie conditions and decrease the risk of hospitalization. Detecting various types of fall to determine the impact site or direction prior to impact is important because it increases the chance of decreasing the incidence or severity of fall-related injuries. In this study, a robust preimpact fall detection model was developed to classify various activities and falls as multi-class and its performance was compared with the performance of previous developed models. Twelve healthy subjects participated in this study. All subjects were asked to place an inertial measuring unit module by fixing on a belt near the left iliac crest to collect accelerometer data for each activity. Our novel proposed model consists of feature calculation and infinite latent feature selection algorithm, auto labeling of activities, application of machine learning classifiers for discrete and continuous time series data. Nine machine-learning classifiers were applied to detect falls prior to impact and derive final detection results by sorting the classifier. Our model showed the highest classification accuracy. Results for the proposed model that could classify as multi-class showed significantly higher average classification accuracy of 99.57 ± 0.01% for discrete data-based classifiers and 99.84 ± 0.02% for continuous time series-based classifiers than previous models (p < 0.01). In the future, multi-class preimpact fall detection models can be applied to fall protector devices by detecting various activities for sending alerts or immediate feedback reactions to prevent falls.

Wearables for independent living in older adults: Gait and falls

Solutions are needed to satisfy care demands of older adults to live independently. Wearable technology (wearables) is one approach that offers a viable means for ubiquitous, sustainable and scalable monitoring of the health of older adults in habitual free-living environments. Gait has been presented as a relevant (bio)marker in ageing and pathological studies, with objective assessment achievable by inertial-based wearables. Commercial wearables have struggled to provide accurate analytics and have been limited by non-clinically oriented gait outcomes. Moreover, some research-grade wearables also fail to provide transparent functionality due to limitations in proprietary software. Innovation within this field is often sporadic, with large heterogeneity of wearable types and algorithms for gait outcomes leading to a lack of pragmatic use. This review provides a summary of the recent literature on gait assessment through the use of wearables, focusing on the need for an algorithm fusion approach to measurement, culminating in the ability to better detect and classify falls. A brief presentation of wearables in one pathological group is presented, identifying appropriate work for researchers in other cohorts to utilise. Suggestions for how this domain needs to progress are also summarised.