Prospective elderly fall prediction by older-adult fall-risk modeling with feature selection

Accurate fall risk classification in elderly using one gait cycle data and machine learning

BACKGROUND

Falls among the elderly are a major societal problem. While observations of medium-distance walking using inertial sensors identified potential fall predictors, classifying individuals at risk based on single gait cycles remains elusive. This challenge stems from individual variability and step-to-step fluctuations, making accurate classification difficult.

METHODS

We recruited 44 participants, equally divided into high and low fall-risk groups. A smartphone secured on their second sacral spinous process recorded data during indoor walking. Features were extracted at each gait cycle from a 6-dimensional time series (tri-axial angular velocity and tri-axial acceleration) and classified using the gradient boosting decision tree algorithm.

FINDINGS

Mean accuracy across five-fold cross-validation was 0.936. "Age" was the most influential individual feature, while features related to acceleration in the gait direction held the highest total relative importance when aggregated by axis (0.5365).

INTERPRETATION

Combining acceleration, angular velocity data, and the gradient boosting decision tree algorithm enabled accurate fall risk classification in the elderly, previously challenging due to lack of discernible features. We reveal the first-ever identification of three-dimensional pelvic motion characteristics during single gait cycles in the high-risk group. This novel method, requiring only one gait cycle, is valuable for individuals with physical limitations hindering repetitive or long-distance walking or for use in spaces with limited walking areas. Additionally, utilizing readily available smartphones instead of dedicated equipment has potential to improve gait analysis accessibility.

Predictability of Fall Risk Assessments in Community-Dwelling Older Adults: A Scoping Review

Fall risk increases with age, and one-third of adults over 65 years old experience a fall annually. Due to the aging population, the number of falls and related medical costs will progressively increase. Correct prediction of who will fall in the future is necessary to timely intervene in order to prevent falls. Therefore, the aim of this scoping review is to determine the predictive value of fall risk assessments in community-dwelling older adults using prospective studies. A total of 37 studies were included that evaluated clinical assessments (questionnaires, physical assessments, or a combination), sensor-based clinical assessments, or sensor- based daily life assessments using prospective study designs. The posttest probability of falling or not falling was calculated. In general, fallers were better classified than non-fallers. Questionnaires had a lower predictive capability compared to the other assessment types. Contrary to conclusions drawn in reviews that include retrospective studies, the predictive value of physical tests evaluated in prospective studies varies largely, with only smaller-sampled studies showing good predictive capabilities. Sensor-based fall risk assessments are promising and improve with task complexity, although they have only been evaluated in relatively small samples. In conclusion, fall risk prediction using sensor data seems to outperform conventional tests, but the method's validity needs to be confirmed by large prospective studies.

A Systematic Review of Wearable Sensor-Based Technologies for Fall Risk Assessment in Older Adults

Falls have been recognized as the major cause of accidental death and injury in people aged 65 and above. The timely prediction of fall risks can help identify older adults prone to falls and implement preventive interventions. Recent advancements in wearable sensor-based technologies and big data analysis have spurred the development of accurate, affordable, and easy-to-use approaches to fall risk assessment. The objective of this study was to systematically assess the current state of wearable sensor-based technologies for fall risk assessment among community-dwelling older adults. Twenty-five of 614 identified research articles were included in this review. A comprehensive comparison was conducted to evaluate these approaches from several perspectives. In general, these approaches provide an accurate and effective surrogate for fall risk assessment. The accuracy of fall risk prediction can be influenced by various factors such as sensor location, sensor type, features utilized, and data processing and modeling techniques. Features constructed from the raw signals are essential for predictive model development. However, more investigations are needed to identify distinct, clinically interpretable features and develop a general framework for fall risk assessment based on the integration of sensor technologies and data modeling.

Improved screening of fall risk using free-living based accelerometer data

Falls are one of the most costly population health issues. Screening of older adults for fall risks can allow for earlier interventions and ultimately lead to better outcomes and reduced public health spending. This work proposes a solution to limitations in existing fall screening techniques by utilizing a hip-based accelerometer worn in free-living conditions. The work proposes techniques to extract fall risk features from periods of free-living ambulatory activity. Analysis of the proposed techniques is conducted and compared with existing screening methods using Functional Tests and Lab-based Gait Analysis. 1705 Older Adults from Umea (Sweden) were assessed. Data consisted of 1 Week of hip worn accelerometer data, gait measurements and performance metrics for 3 functional tests. Retrospective and Prospective fall data were also recorded based on the incidence of falls occurring 12 months before and after the study commencing respectively. Machine learning based experiments show accelerometer based measures perform best when predicting falls. Prospective falls had a sensitivity and specificity of 0.61 and 0.66 respectively while retrospective falls had a sensitivity and specificity of 0.61 and 0.68 respectively.

Fall Risk Assessment Using Wearable Sensors: A Narrative Review

Recently, fall risk assessment has been a main focus in fall-related research. Wearable sensors have been used to increase the objectivity of this assessment, building on the traditional use of oversimplified questionnaires. However, it is necessary to define standard procedures that will us enable to acknowledge the multifactorial causes behind fall events while tackling the heterogeneity of the currently developed systems. Thus, it is necessary to identify the different specifications and demands of each fall risk assessment method. Hence, this manuscript provides a narrative review on the fall risk assessment methods performed in the scientific literature using wearable sensors. For each identified method, a comprehensive analysis has been carried out in order to find trends regarding the most used sensors and its characteristics, activities performed in the experimental protocol, and algorithms used to classify the fall risk. We also verified how studies performed the validation process of the developed fall risk assessment systems. The identification of trends for each fall risk assessment method would help researchers in the design of standard innovative solutions and enhance the reliability of this assessment towards a homogeneous benchmark solution.

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.

Exploration of Machine Learning to Identify Community Dwelling Older Adults with Balance Dysfunction Using Short Duration Accelerometer Data

The incidence of fall-related injuries in older adults is high. Given the significant and adverse outcomes that arise from injurious falls in older adults, it is of the utmost importance to identify older adults at greater risk for falls as early as possible. Given that balance dysfunction provides a significant risk factor for falls, an automated and objective identification of balance dysfunction in community dwelling older adults using wearable sensor data when walking may be beneficial. In this study, we examine the feasibility of using wearable sensors, when walking, to identify older adults who have trouble with balance at an early stage using state-of-the-art machine learning techniques. We recruited 21 community dwelling older women. The experimental paradigm consisted of two tasks: Normal walking with a self-selected comfortable speed on an instrumented treadmill and a test of reflexive postural response, using the motor control test (MCT). Based on the MCT, identification of older women with low or high balance function was performed. Using short duration accelerometer data from sensors placed on the knee and hip while walking, supervised machine learning was carried out to classify subjects with low and high balance function. Using a Gradient Boosting Machine (GBM) algorithm, we classified balance function in older adults using 60 seconds of accelerometer data with an average cross validation accuracy of 91.5% and area under the receiver operating characteristic curve (AUC) of 0.97. Early diagnosis of balance dysfunction in community dwelling older adults through the use of user friendly and inexpensive wearable sensors may help in reducing future fall risk in older adults through earlier interventions and treatments, and thereby significantly reduce associated healthcare costs.

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.

Deep Learning for Fall Risk Assessment With Inertial Sensors: Utilizing Domain Knowledge in Spatio-Temporal Gait Parameters

Fall risk assessment is essential to predict and prevent falls in geriatric populations, especially patients with life-long conditions like neurological disorders. Inertial sensor-based pervasive gait analysis systems have become viable means to facilitate continuous fall risk assessment in non-hospital settings. However, a gait analysis system is not sufficient to detect the characteristics leading to increased fall risk, and powerful inference models are required to detect the underlying factors specific to fall risk. Machine learning models and especially the recently proposed deep learning methods offer the needed predictive power. Deep neural networks have the potential to produce models that can operate directly on the raw data, thus alleviating the need for feature engineering. However, the domain knowledge inherent in the well-established spatio-temporal gait parameters are still valuable to help a model achieve high inference accuracies. In this study, we explore deep learning methods, specifically long short-term memory (LSTM) neural networks, for the problem of fall risk assessment. We utilize sequences of spatio-temporal gait parameters extracted by an inertial sensor-based gait analysis system as input features. To quantify the performance of the proposed approach, we compare it with more traditional machine learning methods. The proposed LSTM model, trained with a gait dataset collected from 60 neurological disorder patients, achieves a superior classification accuracy of 92.1% on a separate test dataset collected from 16 patients. This study serves as one of the first attempts to employ deep learning approaches in this domain and the results demonstrate their potential.

Falls Risk Classification of Older Adults Using Deep Neural Networks and Transfer Learning

Prior research in falls risk classification using inertial sensors has relied on the use of engineered features, which has resulted in a feature space containing hundreds of features that are likely redundant and possibly irrelevant. In this paper, we propose using fully convolutional neural networks (FCNNs) to classify older adults at low or high risk of falling using inertial sensor data collected from a smartphone. Due to the limited nature of older adult inertial gait datasets, we first pre-train the FCNN models using a publicly available dataset for pedestrian activity recognition. Then via transfer learning, we train the network for falls risk classification. We show that via transfer learning, our falls risk classifier obtains an area under the receiver operating characteristic curve of 93.3%, which is 10.6% higher than the equivalent model trained without the use of transfer learning. Additionally, we show that our method outperforms other standard machine learning classifiers trained on features developed in prior research.

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.