Accelerometer-based predictive models of fall risk in older women: a pilot study

Predicting physical functioning status in older adults: insights from wrist accelerometer sensors and derived digital biomarkers of physical activity

OBJECTIVE

Conventional physical activity (PA) metrics derived from wearable sensors may not capture the cumulative, transitions from sedentary to active, and multidimensional patterns of PA, limiting the ability to predict physical function impairment (PFI) in older adults. This study aims to identify unique temporal patterns and develop novel digital biomarkers from wrist accelerometer data for predicting PFI and its subtypes using explainable artificial intelligence techniques.

MATERIALS AND METHODS

Wrist accelerometer streaming data from 747 participants in the National Health and Aging Trends Study (NHATS) were used to calculate 231 PA features through time-series analysis techniques-Tsfresh. Predictive models for PFI and its subtypes (walking, balance, and extremity strength) were developed using 6 machine learning (ML) algorithms with hyperparameter optimization. The SHapley Additive exPlanations method was employed to interpret the ML models and rank the importance of input features.

RESULTS

Temporal analysis revealed peak PA differences between PFI and healthy controls from 9:00 to 11:00 am. The best-performing model (Gradient boosting Tree) achieved an area under the curve score of 85.93%, accuracy of 81.52%, sensitivity of 77.03%, and specificity of 87.50% when combining wrist accelerometer streaming data (WAPAS) features with demographic data.

DISCUSSION

The novel digital biomarkers, including change quantiles, Fourier transform (FFT) coefficients, and Aggregated (AGG) Linear Trend, outperformed traditional PA metrics in predicting PFI. These findings highlight the importance of capturing the multidimensional nature of PA patterns for PFI.

CONCLUSION

This study investigates the potential of wrist accelerometer digital biomarkers in predicting PFI and its subtypes in older adults. Integrated PFI monitoring systems with digital biomarkers would improve the current state of remote PFI surveillance.

Leveraging feature selection for enhanced fall risk prediction in elderly using gait analysis

There is no effective fall risk screening tool for the elderly that can be integrated into clinical practice. Developing a system that can be easily used in primary care services is a current need. Current studies focus on the use of multiple sensors or activities to achieve higher accuracy. However, multiple sensors and activities reduce the availability of these systems. This study aims to develop a system to perform fall prediction for the elderly by using signals recorded from a single sensor during a short-term activity. A total of 168 features in the time and frequency domains were created using acceleration signals obtained from 71 elderly people. The features were weighted based on the ReliefF algorithm, and the artificial neural networks model was developed using the most important features. The best classification result was obtained using the 17 most important features of those weighted for K = 20 nearest neighbors. The highest accuracy was 82.2% (82.9% Sensitivity, 81.6% Specificity). The partially high accuracy obtained in our study shows that falling can be detected early with a sensor and a simple activity by determining the right features and can be easily applied in the assessment of the elderly during routine follow-ups.

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.

Validity and Reliability of the Short Physical Performance Battery Tool in Institutionalized Spanish Older Adults

BACKGROUND

In order to be used safely, accurately and reliably, measuring instruments in the health field must first be validated, for which the study of their psychometric properties is necessary. The Short Physical Performance Battery (SPPB) tool is a widely used clinical assessment test that has been approved for usage across several nations, languages and demographics. Finding SPPB's psychometric properties for a sample of institutionalized older individuals is the aim of this research.

METHODS

This is a multicenter, retrospective and observational study of the psychometric properties of the Short Physical Performance Battery tool with a convenience sample of 194 institutionalized older adults. Reliability (internal consistency) and validity (construct validity and convergent validity) tests were performed.

RESULTS

The results show a very good internal consistency, construct validity and convergent validity. In addition, the factorial structure of the SPPB is provided, which reflects that it is a unidimensional scale.

CONCLUSIONS

In conclusion, the Short Physical Performance Battery is a valid and reliable tool for use with institutionalized older adults. Its use is recommended as part of the Comprehensive Geriatric Assessment for the evaluation of the physical or functional sphere. This study was not registered.

Trunk range of motion: A wearable sensor-based test protocol and indicator of fall risk in older people

Conventionally, trunk range of motion (TROM) requires manual measurement by an external health professional with a general-purpose goniometer. This study aims to propose a convenient test protocol to assess TROM based on a single wearable sensor and to further investigate the relationship between TROM and fall risk of older people. We first explored the optimal sensor position by comparing TROMs from four representative locations (T1, T12, L5 and sternum) and optical motion capture system (golden reference). A follow-up experiment was conducted to evaluate the relationship between TROM and fall risk. The results showed that T12 achieved the minimum root mean square error (3.8 ± 2.2°) against the golden reference and the non-faller group had significantly higher TROMs than the faller group. These findings suggest that the newly proposed protocol is convenient yet valid and TROM can be a promising indicator of fall risk in older people.

Population analysis of mortality risk: Predictive models from passive monitors using motion sensors for 100,000 UK Biobank participants

Many studies have utilized physical activity for predicting mortality risk, using measures such as participant walk tests and self-reported walking pace. The rise of passive monitors to measure participant activity without requiring specific actions opens the possibility for population level analysis. We have developed novel technology for this predictive health monitoring, using limited sensor inputs. In previous studies, we validated these models in clinical experiments with carried smartphones, using only their embedded accelerometers as motion sensors. Using smartphones as passive monitors for population measurement is critically important for health equity, since they are already ubiquitous in high-income countries and increasingly common in low-income countries. Our current study simulates smartphone data by extracting walking window inputs from wrist worn sensors. To analyze a population at national scale, we studied 100,000 participants in the UK Biobank who wore activity monitors with motion sensors for 1 week. This national cohort is demographically representative of the UK population, and this dataset represents the largest such available sensor record. We characterized participant motion during normal activities, including daily living equivalent of timed walk tests. We then compute walking intensity from sensor data, as input to survival analysis. Simulating passive smartphone monitoring, we validated predictive models using only sensors and demographics. This resulted in C-index of 0.76 for 1-year risk decreasing to 0.73 for 5-year. A minimum set of sensor features achieves C-index of 0.72 for 5-year risk, which is similar accuracy to other studies using methods not achievable with smartphone sensors. The smallest minimum model uses average acceleration, which has predictive value independent of demographics of age and sex, similar to physical measures of gait speed. Our results show passive measures with motion sensors can achieve similar accuracy to active measures of gait speed and walk pace, which utilize physical walk tests and self-reported questionnaires.

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.

Real-World Stair Ambulation Characteristics Differ Between Prospective Fallers and Non-Fallers in Parkinson's Disease

Falls are among the leading causes of injuries or death for individuals from the age of 65 and the prevalence of falls is especially high for patients suffering from neurological diseases like Parkinson's disease (PD). Due to advancements in wearable sensor technology, inertial measurement units (IMUs) can be integrated unobtrusively into patients' everyday lives to monitor various mobility and gait parameters, which are related to common risk factors like reduced balance and reduced lower-limb muscle strength, or lower range of joints. Although stair ambulation is a fundamental part of our daily lives and is known for its unique challenges for the gait and balance system, long-term gait analysis studies have not investigated real-world stair ambulation parameters yet. Therefore, we applied a recently published gait analysis pipeline on real-world foot-worn IMU data of 40 PD patients over a recording period of two weeks to extract objective gait parameters from level walking but also from stair ascending and stair descending gait. In combination with fall records from a prospective three-month follow-up phase, we investigated group differences in gait parameters of future fallers compared to non-fallers for each individual gait activity. We found significant differences in stair ascending and descending parameters. Stance time was increased by up to 20% and gait speed reduced by up to 16% for fallers compared to non-fallers during stair walking. These differences were not present in level walking parameters. Hence, these results suggest that real-world stair ambulation provides sensitive parameters for mobility and fall risk due to the unique challenges stairs add to the balance and control system. Our work complements existing gait analysis studies by adding new insights into mobility and gait performance during real-world gait.

Intelligent Fall-Risk Assessment Based on Gait Stability and Symmetry Among Older Adults Using Tri-Axial Accelerometry

This study aimed to use the k-nearest neighbor (kNN) algorithm, which combines gait stability and symmetry derived from a normalized cross-correlation (NCC) analysis of acceleration signals from the bilateral ankles of older adults, to assess fall risk. Fifteen non-fallers and 12 recurrent fallers without clinically significant musculoskeletal and neurological diseases participated in the study. Sex, body mass index, previous falls, and the results of the 10 m walking test (10 MWT) were recorded. The acceleration of the five gait cycles from the midsection of each 10 MWT was used to calculate the unilateral NCC coefficients for gait stability and bilateral NCC coefficients for gait symmetry, and then kNN was applied for classifying non-fallers and recurrent fallers. The duration of the 10 MWT was longer among recurrent fallers than it was among non-fallers (p < 0.05). Since the gait signals were acquired from tri-axial accelerometry, the kNN F1 scores with the x-axis components were 92% for non-fallers and 89% for recurrent fallers, and the root sum of squares (RSS) of the signals was 95% for non-fallers and 94% for recurrent fallers. The kNN classification on gait stability and symmetry revealed good accuracy in terms of distinguishing non-fallers and recurrent fallers. Specifically, it was concluded that the RSS-based NCC coefficients can serve as effective gait features to assess the risk of falls.

Changes in trunk and head acceleration during the 6-minute walk test and its relation to falls risk for adults with multiple sclerosis

For persons with multiple sclerosis (MS), the general decline in neuromuscular function underlies diminished balance, impaired gait and consequently, increased risk of falling. During gait, optimal control of head motion is an important feature which is achieved partly through control of the trunk-neck region to dampen gait-related oscillations. The primary aim of this study was to examine the effect performing a 6-minute walk test (6MWT) has on head, neck and trunk accelerations in individuals with MS. This was addressed using a repeated measures generalized linear model. We were also interested in assessing whether the 6MWT has an impact on a person's falls risk and specific physiological measures related to falls. Finally the relation between the amplitude (i.e., mean RMS) of head and trunk accelerations and falls risk was examined using linear regression. The main results were that over the course of the 6MWT, individuals progressively slowed down coupled with a concurrent increase in gait-related upper body accelerations (p's > 0.05). Despite the increased acceleration, no significant changes in attenuation from the trunk to the head were observed, indicating that persons were able to maintain an optimal level of control over these oscillations. Performing the 6MWT also had a negative impact on posture, with falls risk significantly increasing following this test (p > 0.05). Interestingly, the overall falls risk values were strongly linked with vertical accelerations about the trunk and head, but not average walking speed during the 6MWT. Overall, performing the 6MWT leads to changes in walking speed, upper body acceleration patterns and increases in overall falls risk.

Machine learning algorithms as new screening approach for patients with endometriosis

Endometriosis-a systemic and chronic condition occurring in women of childbearing age-is a highly enigmatic disease with unresolved questions. While multiple biomarkers, genomic analysis, questionnaires, and imaging techniques have been advocated as screening and triage tests for endometriosis to replace diagnostic laparoscopy, none have been implemented routinely in clinical practice. We investigated the use of machine learning algorithms (MLA) in the diagnosis and screening of endometriosis based on 16 key clinical and patient-based symptom features. The sensitivity, specificity, F1-score and AUCs of the MLA to diagnose endometriosis in the training and validation sets varied from 0.82 to 1, 0-0.8, 0-0.88, 0.5-0.89, and from 0.91 to 0.95, 0.66-0.92, 0.77-0.92, respectively. Our data suggest that MLA could be a promising screening test for general practitioners, gynecologists, and other front-line health care providers. Introducing MLA in this setting represents a paradigm change in clinical practice as it could replace diagnostic laparoscopy. Furthermore, this patient-based screening tool empowers patients with endometriosis to self-identify potential symptoms and initiate dialogue with physicians about diagnosis and treatment, and hence contribute to shared decision making.

Automatic Recognition and Analysis of Balance Activity in Community-Dwelling Older Adults: Algorithm Validation

BACKGROUND

Clinical mobility and balance assessments identify older adults who have a high risk of falls in clinics. In the past two decades, sensors have been a popular supplement to mobility and balance assessment to provide quantitative information and a cost-effective solution in the community environment. Nonetheless, the current sensor-based balance assessment relies on manual observation or motion-specific features to identify motions of research interest.

OBJECTIVE

The objective of this study was to develop an automatic motion data analytics framework using signal data collected from an inertial sensor for balance activity analysis in community-dwelling older adults.

METHODS

In total, 59 community-dwelling older adults (19 males and 40 females; mean age = 81.86 years, SD 6.95 years) were recruited in this study. Data were collected using a body-worn inertial measurement unit (including an accelerometer and a gyroscope) at the L4 vertebra of each individual. After data preprocessing and motion detection via a convolutional long short-term memory (LSTM) neural network, a one-class support vector machine (SVM), linear discriminant analysis (LDA), and k-nearest neighborhood (k-NN) were adopted to classify high-risk individuals.

RESULTS

The framework developed in this study yielded mean accuracies of 87%, 86%, and 89% in detecting sit-to-stand, turning 360°, and stand-to-sit motions, respectively. The balance assessment classification showed accuracies of 90%, 92%, and 86% in classifying abnormal sit-to-stand, turning 360°, and stand-to-sit motions, respectively, using Tinetti Performance Oriented Mobility Assessment-Balance (POMA-B) criteria by the one-class SVM and k-NN.

CONCLUSIONS

The sensor-based approach presented in this study provided a time-effective manner with less human efforts to identify and preprocess the inertial signal and thus enabled an efficient balance assessment tool for medical professionals. In the long run, the approach may offer a flexible solution to relieve the community's burden of continuous health monitoring.

Activity Tracking Using Ear-Level Accelerometers

Introduction: By means of adding more sensor technology, modern hearing aids (HAs) strive to become better, more personalized, and self-adaptive devices that can handle environmental changes and cope with the day-to-day fitness of the users. The latest HA technology available in the market already combines sound analysis with motion activity classification based on accelerometers to adjust settings. While there is a lot of research in activity tracking using accelerometers in sports applications and consumer electronics, there is not yet much in hearing research.

Objective: This study investigates the feasibility of activity tracking with ear-level accelerometers and how it compares to waist-mounted accelerometers, which is a more common measurement location.

Method: The activity classification methods in this study are based on supervised learning. The experimental set up consisted of 21 subjects, equipped with two XSens MTw Awinda at ear-level and one at waist-level, performing nine different activities.

Results: The highest accuracy on our experimental data as obtained with the combination of Bagging and Classification tree techniques. The total accuracy over all activities and users was 84% (ear-level), 90% (waist-level), and 91% (ear-level + waist-level). Most prominently, the classes, namely, standing, jogging, laying (on one side), laying (face-down), and walking all have an accuracy of above 90%. Furthermore, estimated ear-level step-detection accuracy was 95% in walking and 90% in jogging.

Conclusion: It is demonstrated that several activities can be classified, using ear-level accelerometers, with an accuracy that is on par with waist-level. It is indicated that step-detection accuracy is comparable to a high-performance wrist device. These findings are encouraging for the development of activity applications in hearing healthcare.

Prediction of fall risk among community-dwelling older adults using a wearable system

Falls are among the most common cause of decreased mobility and independence in older adults and rank as one of the most severe public health problems with frequent fatal consequences. In the present study, gait characteristics from 171 community-dwelling older adults were evaluated to determine their predictive ability for future falls using a wearable system. Participants wore a wearable sensor (inertial measurement unit, IMU) affixed to the sternum and performed a 10-m walking test. Measures of gait variability, complexity, and smoothness were extracted from each participant, and prospective fall incidence was evaluated over the following 6-months. Gait parameters were refined to better represent features for a random forest classifier for the fall-risk classification utilizing three experiments. The results show that the best-trained model for faller classification used both linear and nonlinear gait parameters and achieved an overall 81.6 ± 0.7% accuracy, 86.7 ± 0.5% sensitivity, 80.3 ± 0.2% specificity in the blind test. These findings augment the wearable sensor's potential as an ambulatory fall risk identification tool in community-dwelling settings. Furthermore, they highlight the importance of gait features that rely less on event detection methods, and more on time series analysis techniques. Fall prevention is a critical component in older individuals’ healthcare, and simple models based on gait-related tasks and a wearable IMU sensor can determine the risk of future falls.

Machine-learning models for activity class prediction: A comparative study of feature selection and classification algorithms

PURPOSE

Machine-learning (ML) approaches have been repeatedly coupled with raw accelerometry to classify physical activity classes, but the features required to optimize their predictive performance are still unknown. Our aim was to identify appropriate combination of feature subsets and prediction algorithms for activity class prediction from hip-based raw acceleration data.

METHODS

The hip-based raw acceleration data collected from 27 participants was split into training (70 %) and validation (30 %) subsets. A total of 206 time- (TD) and frequencydomain (FD) features were extracted from 6-second non-overlapping windows of the signal. Feature selection was done using seven filter-based, two wrapper-based, and one embedded algorithm, and classification was performed with artificial neural network (ANN), support vector machine (SVM), and random forest (RF). For every combination between the feature selection method and the classifiers, the most appropriate feature subsets were found and used for model training within the training set. These models were then validated with the left-out validation set.

RESULTS

The appropriate number of features for the ANN, SVM, and RF ranged from 20 to 45. Overall, the accuracy of all the three classifiers was higher when trained with feature subsets generated using filter-based methods compared with when they were trained with wrapper-based methods (range: 78.1 %-88 % vs. 66 %-83.5 %). TD features that reflect how signals vary around the mean, how they differ with one another, and how much and how often they change were more frequently selected via the feature selection methods.

CONCLUSIONS

A subset of TD features from raw accelerometry could be sufficient for ML-based activity classification if properly selected from different axes.

Latest Research Trends in Fall Detection and Prevention Using Machine Learning: A Systematic Review

Falls are unusual actions that cause a significant health risk among older people. The growing percentage of people of old age requires urgent development of fall detection and prevention systems. The emerging technology focuses on developing such systems to improve quality of life, especially for the elderly. A fall prevention system tries to predict and reduce the risk of falls. In contrast, a fall detection system observes the fall and generates a help notification to minimize the consequences of falls. A plethora of technical and review papers exist in the literature with a primary focus on fall detection. Similarly, several studies are relatively old, with a focus on wearables only, and use statistical and threshold-based approaches with a high false alarm rate. Therefore, this paper presents the latest research trends in fall detection and prevention systems using Machine Learning (ML) algorithms. It uses recent studies and analyzes datasets, age groups, ML algorithms, sensors, and location. Additionally, it provides a detailed discussion of the current trends of fall detection and prevention systems with possible future directions. This overview can help researchers understand the current systems and propose new methodologies by improving the highlighted issues.

Strength Training to Prevent Falls in Older Adults: A Systematic Review with Meta-Analysis of Randomized Controlled Trials

We performed a systematic review with meta-analysis of randomized controlled trials (RCTs) to assess the effects of strength training (ST), as compared to alternative multimodal or unimodal exercise programs, on the number of falls in older adults (≥60 years). Ten databases were consulted (CINAHL, Cochrane Library, EBSCO, EMBASE, PEDro, PubMed, Scielo, Scopus, SPORTDiscus and Web of Science), without limitations on language or publication date. Eligibility criteria were as follows: RCTs with humans ≥60 years of age of any gender with one group performing supervised ST and a group performing another type of exercise training, reporting data pertaining falls. Certainty of evidence was assessed with Grading of Recommendations, Assessment, Development and Evaluation (GRADE). Meta-analysis used a random effects model to calculate the risk ratio (RR) for number of falls. Five RCTs with six trials were included (n = 543, 76% women). There was no difference between ST and alternative exercise interventions for falls (RR = 1.00, 95% CI 0.77–1.30, p = 0.99). The certainty of evidence was very low. No dose–response relationship could be established. In sum, ST showed comparable RR based on number of falls in older adults when compared to other multimodal or unimodal exercise modalities, but evidence is scarce and heterogeneous, and additional research is required for more robust conclusions. Registration: PROSPERO CRD42020222908.

Sensor-based fall risk assessment in older adults with or without cognitive impairment: a systematic review

BACKGROUND

Higher age and cognitive impairment are associated with a higher risk of falling. Wearable sensor technology may be useful in objectively assessing motor fall risk factors to improve physical exercise interventions for fall prevention. This systematic review aims at providing an updated overview of the current research on wearable sensors for fall risk assessment in older adults with or without cognitive impairment. Therefore, we addressed two specific research questions: 1) Can wearable sensors provide accurate data on motor performance that may be used to assess risk of falling, e.g., by distinguishing between faller and non-faller in a sample of older adults with or without cognitive impairment?; and 2) Which practical recommendations can be given for the application of sensor-based fall risk assessment in individuals with CI? A systematic literature search (July 2019, update July 2020) was conducted using PubMed, Scopus and Web of Science databases. Community-based studies or studies conducted in a geriatric setting that examine fall risk factors in older adults (aged ≥60 years) with or without cognitive impairment were included. Predefined inclusion criteria yielded 16 cross-sectional, 10 prospective and 2 studies with a mixed design.

RESULTS

Overall, sensor-based data was mainly collected during walking tests in a lab setting. The main sensor location was the lower back to provide wearing comfort and avoid disturbance of participants. The most accurate fall risk classification model included data from sit-to-walk and walk-to-sit transitions collected over three days of daily life (mean accuracy = 88.0%). Nine out of 28 included studies revealed information about sensor use in older adults with possible cognitive impairment, but classification models performed slightly worse than those for older adults without cognitive impairment (mean accuracy = 79.0%).

CONCLUSION

Fall risk assessment using wearable sensors is feasible in older adults regardless of their cognitive status. Accuracy may vary depending on sensor location, sensor attachment and type of assessment chosen for the recording of sensor data. More research on the use of sensors for objective fall risk assessment in older adults is needed, particularly in older adults with cognitive impairment.

TRIAL REGISTRATION

This systematic review is registered in PROSPERO ( CRD42020171118 ).

GRANADA consensus on analytical approaches to assess associations with accelerometer-determined physical behaviours (physical activity, sedentary behaviour and sleep) in epidemiological studies

The inter-relationship between physical activity, sedentary behaviour and sleep (collectively defined as physical behaviours) is of interest to researchers from different fields. Each of these physical behaviours has been investigated in epidemiological studies, yet their codependency and interactions need to be further explored and accounted for in data analysis. Modern accelerometers capture continuous movement through the day, which presents the challenge of how to best use the richness of these data. In recent years, analytical approaches first applied in other scientific fields have been applied to physical behaviour epidemiology (eg, isotemporal substitution models, compositional data analysis, multivariate pattern analysis, functional data analysis and machine learning). A comprehensive description, discussion, and consensus on the strengths and limitations of these analytical approaches will help researchers decide which approach to use in different situations. In this context, a scientific workshop and meeting were held in Granada to discuss: (1) analytical approaches currently used in the scientific literature on physical behaviour, highlighting strengths and limitations, providing practical recommendations on their use and including a decision tree for assisting researchers’ decision-making; and (2) current gaps and future research directions around the analysis and use of accelerometer data. Advances in analytical approaches to accelerometer-determined physical behaviours in epidemiological studies are expected to influence the interpretation of current and future evidence, and ultimately impact on future physical behaviour guidelines.

Gait Analysis with Wearables Can Accurately Classify Fallers from Non-Fallers: A Step toward Better Management of Neurological Disorders

Falls are the leading cause of mortality, morbidity and poor quality of life in older adults with or without neurological conditions. Applying machine learning (ML) models to gait analysis outcomes offers the opportunity to identify individuals at risk of future falls. The aim of this study was to determine the effect of different data pre-processing methods on the performance of ML models to classify neurological patients who have fallen from those who have not for future fall risk assessment. Gait was assessed using wearables in clinic while walking 20 m at a self-selected comfortable pace in 349 (159 fallers, 190 non-fallers) neurological patients. Six different ML models were trained on data pre-processed with three techniques such as standardisation, principal component analysis (PCA) and path signature method. Fallers walked more slowly, with shorter strides and longer stride duration compared to non-fallers. Overall, model accuracy ranged between 48% and 98% with 43-99% sensitivity and 48-98% specificity. A random forest (RF) classifier trained on data pre-processed with the path signature method gave optimal classification accuracy of 98% with 99% sensitivity and 98% specificity. Data pre-processing directly influences the accuracy of ML models for the accurate classification of fallers. Using gait analysis with trained ML models can act as a tool for the proactive assessment of fall risk and support clinical decision-making.

Foreseeing future falls with accelerometer features in active community-dwelling older persons with no recent history of falls

BACKGROUND

Acceleration sensors are a viable option for monitoring gait patterns and its application on monitoring falls and risk of falling. However the literature still lacks prospective studies to investigate such risk before the occurrence of falls.

OBJECTIVE

To investigate features extracted from accelerometer signals with the purpose of predicting future falls in individuals with no recent history of falls.

METHODS

In this study we investigate the risk of fall in active and healthy community-dwelling living older persons with no recent history of falls, using a single accelerometer and variants of the Timed Up and Go (TUG) test. A prospective study was conducted with 74 healthy non-fallers older persons. After collecting acceleration data from the participants at the baseline, the occurrence of falls (outcome) was monitored quarterly during one year. A set of frequency features were extracted from the signal and their ability to predict falls was evaluated.

RESULTS

The best individual feature result shows an accuracy of 0.75, sensitivity of 0.71 and specificity of 0.76. A fusion of the three best features increases the sensitivity to 0.86. On the other hand, the cut-off points of the TUG seconds, often used to assess fall risk, did not demonstrate adequate sensitivity.

CONCLUSION

The results confirms previous evidence that accelerometer features can better estimate fall risk, and support potential applications that try to infer falls risk in less restricted scenarios, even in a sample stratified by age and gender composed of active and healthy community-dwelling living older persons.

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.

Learning endometriosis phenotypes from patient-generated data

Endometriosis is a systemic and chronic condition in women of childbearing age, yet a highly enigmatic disease with unresolved questions: there are no known biomarkers, nor established clinical stages. We here investigate the use of patient-generated health data and data-driven phenotyping to characterize endometriosis patient subtypes, based on their reported signs and symptoms. We aim at unsupervised learning of endometriosis phenotypes using self-tracking data from personal smartphones. We leverage data from an observational research study of over 4000 women with endometriosis that track their condition over more than 2 years. We extend a classical mixed-membership model to accommodate the idiosyncrasies of the data at hand, i.e., the multimodality and uncertainty of the self-tracked variables. The proposed method, by jointly modeling a wide range of observations (i.e., participant symptoms, quality of life, treatments), identifies clinically relevant endometriosis subtypes. Experiments show that our method is robust to different hyperparameter choices and the biases of self-tracking data (e.g., the wide variations in tracking frequency among participants). With this work, we show the promise of unsupervised learning of endometriosis subtypes from self-tracked data, as learned phenotypes align well with what is already known about the disease, but also suggest new clinically actionable findings. More generally, we argue that a continued research effort on unsupervised phenotyping methods with patient-generated health data via new mobile and digital technologies will have significant impact on the study of enigmatic diseases in particular, and health in general.

Smart Environments and Social Robots for Age-Friendly Integrated Care Services

The world is facing major societal challenges because of an aging population that is putting increasing pressure on the sustainability of care. While demand for care and social services is steadily increasing, the supply is constrained by the decreasing workforce. The development of smart, physical, social and age-friendly environments is identified by World Health Organization (WHO) as a key intervention point for enabling older adults, enabling them to remain as much possible in their residences, delay institutionalization, and ultimately, improve quality of life. In this study, we survey smart environments, machine learning and robot assistive technologies that can offer support for the independent living of older adults and provide age-friendly care services. We describe two examples of integrated care services that are using assistive technologies in innovative ways to assess and deliver of timely interventions for polypharmacy management and for social and cognitive activity support in older adults. We describe the architectural views of these services, focusing on details about technology usage, end-user interaction flows and data models that are developed or enhanced to achieve the envisioned objective of healthier, safer, more independent and socially connected older people.

Relevance of sex, age and gait kinematics when predicting fall-risk and mortality in older adults

Approximately one-third of elderly people fall each year with severe consequences, including death. The aim of this study was to identify the most relevant features to be considered to maximize the accuracy of a logistic regression model designed for prediction of fall/mortality risk among older people. This study included 261 adults, aged over 65 years. Men and women were analyzed separately because sex stratification was revealed as being essential for our purposes of feature ranking and selection. Participants completed a 3-m walk test at their own gait velocity. An inertial sensor attached to their lumbar spine was used to record acceleration data in the three spatial directions. Signal processing techniques allowed the extraction of 21 features representative of gait kinematics, to be used as predictors to train and test the model. Age and gait speed data were also considered as predictors. A set of 23 features was considered. These features demonstrate to be more or less relevant depending on the sex of the cohort under analysis and the classification label (risk of falls and mortality). In each case, the minimum size subset of relevant features is provided to show the maximum accuracy prediction capability. Gait speed has been largely used as the single feature for the prediction fall risk among older adults. Nevertheless, prediction accuracy can be substantially improved, reaching 70% in some cases, if the task of training and testing the model takes into account some other features, namely, sex, age and gait kinematic parameters. Therefore we recommend considering sex, age and step regularity to predict fall-risk.

Human activity recognition using magnetic induction-based motion signals and deep recurrent neural networks

Recognizing human physical activities using wireless sensor networks has attracted significant research interest due to its broad range of applications, such as healthcare, rehabilitation, athletics, and senior monitoring. There are critical challenges inherent in designing a sensor-based activity recognition system operating in and around a lossy medium such as the human body to gain a trade-off among power consumption, cost, computational complexity, and accuracy. We introduce an innovative wireless system based on magnetic induction for human activity recognition to tackle these challenges and constraints. The magnetic induction system is integrated with machine learning techniques to detect a wide range of human motions. This approach is successfully evaluated using synthesized datasets, laboratory measurements, and deep recurrent neural networks.

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.

Fall detection and fall risk assessment in older person using wearable sensors: A systematic review

BACKGROUND

wearable sensors are often used to acquire data for gait analysis as a strategy to study fall events, due to greater availability of acquisition platforms, and advances in computational intelligence. However, there are no review papers addressing the three most common types of applications related to fall using sensors, namely: fall detection, fallers classification and fall risk screening.

OBJECTIVE

To identify the state of art of fall-related events detection in older person using wearable sensors, as well as the main characteristics of the studies in the literature, pointing gaps for future studies.

METHODS

A systematic review design was used to search peer-reviewed literature on fall detection and risk in elderly through inertial sensors, published in English, Portuguese, Spanish or French between August 2002 and June 2019. The following questions are investigated: the type of sensors and their sampling rate, the type of signal and data processing employed, the scales and tests used in the study and the type of application.

RESULTS

We identified 608 studies, from which 29 were included. The accelerometer, with sampling rate 50 or 100 Hz, allocated in the waist or lumbar was the most used sensor setting. Methods comparing features or variables extracted from the accelerometry signal are the most common, and fall risk screening the most observed application.

CONCLUSION

This review identifies the main elements to be addressed in studies on the detection of events related to falls in the elderly and may help in future studies on the subject. However, some aspects are still no reach consensus in the literature such as the size of the sample to be studied, the population under study and how to acquire data for each application.

A Patient-Specific Single Sensor IoT-Based Wearable Fall Prediction and Detection System

Falls in older adults are a major cause of morbidity and mortality and are a key class of preventable injuries. This paper presents a patient-specific (PS) fall prediction and detection prototype system that utilizes a single tri-axial accelerometer attached to the patient's thigh to distinguish between activities of daily living (ADL) and fall events. The proposed system consists of two modes of operation: 1) fast mode for fall predication (FMFP) predicting a fall event (300-700 msec) before occurring and 2) slow mode for fall detection (SMFD) with a 1-sec latency for detecting a fall event. The nonlinear support vector machine classifier (NLSVM)-based FMFP algorithm extracts seven discriminating features for the pre-fall case to identify a fall risk event and alarm the patient. The proposed SMFD algorithm utilizes a Three-cascaded 1-sec sliding frames classification architecture with a linear regression-based offline training to identify a single and optimal threshold for each patient. Fall incidence will trigger an alarming notice to the concern healthcare providers via the Internet. Experiments are performed with 20 different subjects (age above 65 years) and a total number of 100 associated falls and ADL recordings indoors and outdoors. The accuracy of the proposed algorithms is furthermore validated via MobiFall Dataset. FMFP achieves sensitivity and specificity of 97.8% and 99.1%, respectively, while SMFD achieves sensitivity and specificity of 98.6% and 99.3%, respectively, for a total number of 600 measured falls and ADL cases from 77 subjects.

Application of Wearable Inertial Sensors and A New Test Battery for Distinguishing Retrospective Fallers from Non-fallers among Community-dwelling Older People

Considering the challenge of population ageing and the substantial health problem among the elderly population from falls, the purpose of this study was to verify whether it is possible to distinguish accurately between older fallers and non-fallers, based on data from wearable inertial sensors collected during a specially designed test battery. A comprehensive but practical test battery using 5 wearable inertial sensors for multifactorial fall risk assessment was designed. This was followed by an experimental study on 196 community-dwelling Korean older women, categorized as fallers (N1 = 82) and non-fallers (N2 = 114) based on prior history of falls. Six machine learning models (logistic regression, naïve bayes, decision tree, random forest, boosted tree and support vector machine) were proposed for faller classification. Results indicated that compared with non-fallers, fallers performed significantly worse on the test battery. In addition, the application of sensor data and support vector machine for faller classification achieved an overall accuracy of 89.4% with 92.7% sensitivity and 84.9% specificity. These findings suggest that wearable inertial sensor based systems show promise for elderly fall risk assessment, which could be implemented in clinical practice to identify "at-risk" individuals reliably to promote proactive fall prevention.