Preventing falls: the use of machine learning for the prediction of future falls in individuals without history of fall

Using In-Shoe Inertial Measurement Unit Sensors to Understand Daily-Life Gait Characteristics in Patients With Distal Radius Fractures During 6 Months of Recovery: Cross-Sectional Study

BACKGROUND

A distal radius fracture (DRF) is a common initial fragility fracture among women in their early postmenopausal period, which is associated with an increased risk of subsequent fractures. Gait assessments are valuable for evaluating fracture risk; inertial measurement units (IMUs) have been widely used to assess gait under free-living conditions. However, little is known about long-term changes in patients with DRF, especially concerning daily-life gait. We hypothesized that, in the long term, the daily-life gait parameters in patients with DRF could enable us to reveal future risk factors for falls and fractures.

OBJECTIVE

This study assessed the spatiotemporal characteristics of patients with DRF at 4 weeks and 6 months of recovery.

METHODS

We recruited 16 women in their postmenopausal period with DRF as their first fragility fracture (mean age 62.3, SD 7.0 years) and 28 matched healthy controls (mean age 65.6, SD 8.0 years). Daily-life gait assessments and physical assessments, such as hand grip strength (HGS), were performed using an in-shoe IMU sensor. Participants' results were compared with those of the control group, and their recovery was assessed for 6 months after the fracture.

RESULTS

In the fracture group, at 4 weeks after DRF, lower foot height in the swing phase (P=.049) and higher variability of stride length (P=.03) were observed, which improved gradually. However, the dorsiflexion angle in the fracture group tended to be lower consistently during 6 months (at 4 weeks: P=.06; during 6 months: P=.07). As for the physical assessments, the fracture group showed lower HGS at all time points (at 4 weeks: P<.001; during 6 months: P=.04), despite significant improvement at 6 months (P<.001).

CONCLUSIONS

With an in-shoe IMU sensor, we discovered the recovery of spatiotemporal gait characteristics 6 months after DRF surgery without the participants' awareness. The consistently unchanged dorsiflexion angle in the swing phase and lower HGS could be associated with fracture risk, implying the high clinical importance of appropriate interventions for patients with DRF to prevent future fractures. These results could be applied to a screening tool for evaluating the risk of falls and fractures, which may contribute to constructing a new health care system using wearable devices in the near future.

A Clustering-Based Approach to Functional and Biomechanical Parameters Recorded with a Pair of Smart Eyeglasses in Older Adults in Order to Determine Physical Performance Groups

Falls and frailty status are often associated with a decline in physical capacity and multifactorial assessment is highly recommended. Based on the functional and biomechanical parameters measured during clinical tests with an accelerometer integrated into smart eyeglasses, the purpose was to characterize a population of older adults through an unsupervised analysis into different physical performance groups. A total of 84 participants (25 men and 59 women) over the age of sixty-five (age: 74.17 ± 5.80 years; height: 165.70 ± 8.22 cm; body mass: 68.93 ± 13.55 kg) performed a 30 s Sit-to-Stand test, a six-minute walking test (6MWT), and a 3 m Timed Up and Go (TUG) test. The acceleration data measured from the eyeglasses were processed to obtain six parameters: the number of Sit-to-Stands, the maximal vertical acceleration values during Sit-to-Stand movements, step duration and length, and the duration of the TUG test. The total walking distance covered during the 6MWT was also retained. After supervised analyses comparison (i.e., ANOVAs), only one of the parameters (i.e., step length) differed between faller groups and no parameters differed between frail and pre-frail participants. In contrast, unsupervised analysis (i.e., clustering algorithm based on K-means) categorized the population into three distinct physical performance groups (i.e., low, intermediate, and high). All the measured parameters discriminated the low- and high-performance groups. Four of the measured parameters differentiated the three groups. In addition, the low-performance group had a higher proportion of frail participants. These results are promising for monitoring activities in older adults to prevent the decline of physical capacities.

Fall Risk Prediction for Community-Dwelling Older Adults: Analysis of Assessment Scale and Evaluation Items without Actual Measurement

The frequency of falls increases with age. In Japan, the population is aging rapidly, and fall prevention measures are an urgent issue. However, assessing fall risk during the coronavirus disease pandemic was complicated by the social distancing measures implemented to prevent the disease, while traditional assessments that involve actual measurements are complicated. This prospective cohort study predicted the risk of falls in community-dwelling older adults using an assessment method that does not require actual measurements. A survey was conducted among 434 community-dwelling older adults to obtain data regarding baseline attributes (age, sex, living with family, use of long-term care insurance, and multimorbidity), Frailty Screening Index (FSI) score, and Questionnaire for Medical Checkup of Old-Old (QMCOO) score. The participants were categorized into fall (n = 78) and non-fall (n = 356) groups. The binomial logistic regression analysis showed that it is better to focus on the QMCOO sub-item score, which focuses on multiple factors. The items significantly associated with falls were Q5 (odds ratio [OR] 1.95), Q8 (OR 2.33), and Q10 (OR 3.68). Our results were similar to common risk factors for falls in normal times. During the pandemic, being able to gauge the risk factors for falls without actually measuring them was important.

Correlation enhanced distribution adaptation for prediction of fall risk

With technological advancements in diagnostic imaging, smart sensing, and wearables, a multitude of heterogeneous sources or modalities are available to proactively monitor the health of the elderly. Due to the increasing risks of falls among older adults, an early diagnosis tool is crucial to prevent future falls. However, during the early stage of diagnosis, there is often limited or no labeled data (expert-confirmed diagnostic information) available in the target domain (new cohort) to determine the proper treatment for older adults. Instead, there are multiple related but non-identical domain data with labels from the existing cohort or different institutions. Integrating different data sources with labeled and unlabeled samples to predict a patient's condition poses a significant challenge. Traditional machine learning models assume that data for new patients follow a similar distribution. If the data does not satisfy this assumption, the trained models do not achieve the expected accuracy, leading to potential misdiagnosing risks. To address this issue, we utilize domain adaptation (DA) techniques, which employ labeled data from one or more related source domains. These DA techniques promise to tackle discrepancies in multiple data sources and achieve a robust diagnosis for new patients. In our research, we have developed an unsupervised DA model to align two domains by creating a domain-invariant feature representation. Subsequently, we have built a robust fall-risk prediction model based on these new feature representations. The results from simulation studies and real-world applications demonstrate that our proposed approach outperforms existing models.

LVONet: automatic classification model for large vessel occlusion based on the difference information between left and right hemispheres

Objective.Stroke is a highly lethal condition, with intracranial vessel occlusion being one of its primary causes. Intracranial vessel occlusion can typically be categorized into four types, each requiring different intervention measures. Therefore, the automatic and accurate classification of intracranial vessel occlusions holds significant clinical importance for assessing vessel occlusion conditions. However, due to the visual similarities in shape and size among different vessels and variations in the degree of vessel occlusion, the automated classification of intracranial vessel occlusions remains a challenging task. Our study proposes an automatic classification model for large vessel occlusion (LVO) based on the difference information between the left and right hemispheres.Approach.Our approach is as follows. We first introduce a dual-branch attention module to learn long-range dependencies through spatial and channel attention, guiding the model to focus on vessel-specific features. Subsequently, based on the symmetry of vessel distribution, we design a differential information classification module to dynamically learn and fuse the differential information of vessel features between the two hemispheres, enhancing the sensitivity of the classification model to occluded vessels. To optimize the feature differential information among similar vessels, we further propose a novel cooperative learning loss function to minimize changes within classes and similarities between classes.Main results.We evaluate our proposed model on an intracranial LVO data set. Compared to state-of-the-art deep learning models, our model performs optimally, achieving a classification sensitivity of 93.73%, precision of 83.33%, accuracy of 89.91% and Macro-F1 score of 87.13%.Significance.This method can adaptively focus on occluded vessel regions and effectively train in scenarios with high inter-class similarity and intra-class variability, thereby improving the performance of LVO classification.

Intelligent Millimeter-Wave System for Human Activity Monitoring for Telemedicine

Telemedicine has the potential to improve access and delivery of healthcare to diverse and aging populations. Recent advances in technology allow for remote monitoring of physiological measures such as heart rate, oxygen saturation, blood glucose, and blood pressure. However, the ability to accurately detect falls and monitor physical activity remotely without invading privacy or remembering to wear a costly device remains an ongoing concern. Our proposed system utilizes a millimeter-wave (mmwave) radar sensor (IWR6843ISK-ODS) connected to an NVIDIA Jetson Nano board for continuous monitoring of human activity. We developed a PointNet neural network for real-time human activity monitoring that can provide activity data reports, tracking maps, and fall alerts. Using radar helps to safeguard patients' privacy by abstaining from recording camera images. We evaluated our system for real-time operation and achieved an inference accuracy of 99.5% when recognizing five types of activities: standing, walking, sitting, lying, and falling. Our system would facilitate the ability to detect falls and monitor physical activity in home and institutional settings to improve telemedicine by providing objective data for more timely and targeted interventions. This work demonstrates the potential of artificial intelligence algorithms and mmwave sensors for HAR.

Predicting balance impairments in older adults: a wavelet-based center of pressure classification approach

BACKGROUND

Aging is associated with a decline in postural control and an increased risk of falls. The Center of Pressure (CoP) trajectory analysis is a commonly used method to assess balance. In this study, we proposed a new method to identify balance impairments in older adults by analyzing their CoP trajectory frequency components, sensory inputs, reaction time, motor functions, and Fall-related Concerns (FrC).

METHODS

The study includes 45 older adults aged [Formula: see text] years who were assessed for sensory and motor functions. FrC and postural control in a quiet stance with open and closed eyes on stable and unstable surfaces. A Discrete Wavelet Transform (DWT) was used to detect features in frequency scales, followed by the K-means algorithm to detect different clusters. The multinomial logistic model was used to identify and predict the association of each group with the sensorimotor tests and FrC.

RESULTS

The study results showed that by DWT, three distinct groups of subjects could be revealed. Group 2 exhibited the broadest use of frequency scales, less decline in sensorimotor functions, and lowest FrC. The study also found that a decline in sensorimotor functions and fall-related concern may cause individuals to rely on either very low-frequency scales (group 1) or higher-frequency scales (group 3) and that those who use lower-frequency scales (group 1) can manage their balance more successfully than group 3.

CONCLUSIONS

Our study provides a new, cost-effective method for detecting balance impairments in older adults. This method can be used to identify people at risk and develop interventions and rehabilitation strategies to prevent falls in this population.

Computer Vision and Machine Learning-Based Gait Pattern Recognition for Flat Fall Prediction

BACKGROUND

Gait recognition has been applied in the prediction of the probability of elderly flat ground fall, functional evaluation during rehabilitation, and the training of patients with lower extremity motor dysfunction. Gait distinguishing between seemingly similar kinematic patterns associated with different pathological entities is a challenge for the clinician. How to realize automatic identification and judgment of abnormal gait is a significant challenge in clinical practice. The long-term goal of our study is to develop a gait recognition computer vision system using artificial intelligence (AI) and machine learning (ML) computing. This study aims to find an optimal ML algorithm using computer vision techniques and measure variables from lower limbs to classify gait patterns in healthy people. The purpose of this study is to determine the feasibility of computer vision and machine learning (ML) computing in discriminating different gait patterns associated with flat-ground falls.

METHODS

We used the Kinect^® Motion system to capture the spatiotemporal gait data from seven healthy subjects in three walking trials, including normal gait, pelvic-obliquity-gait, and knee-hyperextension-gait walking. Four different classification methods including convolutional neural network (CNN), support vector machine (SVM), K-nearest neighbors (KNN), and long short-term memory (LSTM) neural networks were used to automatically classify three gait patterns. Overall, 750 sets of data were collected, and the dataset was divided into 80% for algorithm training and 20% for evaluation.

RESULTS

The SVM and KNN had a higher accuracy than CNN and LSTM. The SVM (94.9 ± 3.36%) had the highest accuracy in the classification of gait patterns, followed by KNN (94.0 ± 4.22%). The accuracy of CNN was 87.6 ± 7.50% and that of LSTM 83.6 ± 5.35%.

CONCLUSIONS

This study revealed that the proposed AI machine learning (ML) techniques can be used to design gait biometric systems and machine vision for gait pattern recognition. Potentially, this method can be used to remotely evaluate elderly patients and help clinicians make decisions regarding disposition, follow-up, and treatment.