Combining principal component analysis and logistic regression for multifactorial fall risk prediction among community-dwelling older adults.

Falls require comprehensive assessment in older adults due to their diverse risk factors. This study aimed to develop an effective fall risk prediction model for community-dwelling older adults by integrating principal component analysis (PCA) with machine learning. Data were collected for 45 fall-related variables from 1630 older adults in Taiwan, and models were developed using PCA and logistic regression. The optimal model, PCA with stepwise logistic regression, had an area under the receiver operating characteristic curve of 0.78, sensitivity of 74 %, specificity of 70 %, and accuracy of 71 %. While dimensionality reduction via PCA is not essential, it aids practicality. Our framework combines PCA and logistic regression, providing a reliable method for fall risk prediction to support consistent screening and targeted health promotion. The key innovation is using PCA prior to logistic regression, overcoming conventional limitations. This offers an effective community-based fall screening tool for older adults.

Feasibility of predicting functional decline in the elderly through key posture information during sit-to-stand movement.

BACKGROUND: Early detection of functional decline in the elderly in day care centres facilitates timely implementation of preventive and treatment measures. RESEARCH QUESTION: Whether or not a predictive model can be developed by applying image recognition to analyze elderly individuals' posture during the sit-to-stand (STS) manoeuvre. METHODS: We enrolled sixty-six participants (24 males and 42 females) in an observational study design. To estimate posture key point information, we employed a region-based convolutional neural network model and utilized nine key points and their coordinates to calculate seven eigenvalues (X1-X7) that represented the motion curve features during the STS manoeuvre. One-way analysis of variance was performed to evaluate four STS strategies and four types of compensation strategies for three groups with different capacities (college students, community-dwelling elderly, and day care center elderly). Finally, a machine learning predictive model was established. RESULTS: Significant differences (p < 0.05) were observed in all eigenvalues except X2 (momentum transfer phase, p = 0.168) between participant groups; significant differences (p < 0.05) were observed in all eigenvalues except X2 (p = 0.219) and X3 (hip-rising phase, p = 0.286) between STS patterns; significant differences (p < 0.05) were observed in all eigenvalues except X2 (p = 0.842) and X3 (p = 0.074) between compensation strategies. The motion curve eigenvalues of the seven posture key points were used to build a machine learning model with 85% accuracy in capacity detection, 70% accuracy in pattern detection, and 85% accuracy in compensation strategy detection. SIGNIFICANCE: This study preliminarily demonstrates that eigenvalues can be used to detect STS patterns and compensation strategies adopted by individuals with different capacities. Our machine learning model has excellent predictive accuracy and may be used to develop inexpensive and effective systems to help caregivers to continuously monitor STS patterns and compensation strategies of elderly individuals as warning signs of functional decline.

Comparative Analysis of Fall Risk Assessment Features in Community-Elderly and Stroke Survivors: Insights from Sensor-Based Data.

Fall-risk assessment studies generally focus on identifying characteristics that affect postural balance in a specific group of subjects. However, falls affect a multitude of individuals. Among the groups with the most recurrent fallers are the community-dwelling elderly and stroke survivors. Thus, this study focuses on identifying a set of features that can explain fall risk for these two groups of subjects. Sixty-five community dwelling elderly (forty-nine female, sixteen male) and thirty-five stroke-survivors (twenty-two male, thirteen male) participated in our study. With the use of an inertial sensor, some features are extracted from the acceleration data of a Timed Up and Go (TUG) test performed by both groups of individuals. A short-form berg balance scale (SFBBS) score and the TUG test score were used for labeling the data. With the use of a 100-fold cross-validation approach, Relief-F and Extra Trees Classifier algorithms were used to extract sets of the top 5, 10, 15, 20, 25, and 30 features. Random Forest classifiers were trained for each set of features. The best models were selected, and the repeated features for each group of subjects were analyzed and discussed. The results show that only the stand duration was an important feature for the prediction of fall risk across all clinical tests and both groups of individuals.

[Education for Sustainability and the Development of Smart Healthcare Systems: An Exploratory Study].

The development of smart healthcare systems that are accurate and efficient may be used to improve the health and well-being of different age groups. These systems should incorporate a human-centered design approach to ensure that products and services meet user needs and that systems are user-friendly. In this study, an "education for sustainability" perspective is used in tandem with human-factors engineering and human-computer interaction techniques to achieve a creative dimensional design within a workshop setting. Workshop settings help learners transcend the limitations of traditional classroom education by encouraging them to integrate their daily needs and develop feasible healthcare solutions. Using an iterative process, proposed designs are repeatedly validated and prototypes are continuously improved. We hope that this article provides educators with a better sustainable educational perspective that they may use to construct accurate and efficient smart healthcare systems that meet the needs of users.

Random Forest for Automatic Feature Importance Estimation and Selection for Explainable Postural Stability of a Multi-Factor Clinical Test.

Falling is a common incident that affects the health of elder adults worldwide. Postural instability is one of the major contributors to this problem. In this study, we propose a supplementary method for measuring postural stability that reduces doctor intervention. We used simple clinical tests, including the timed-up and go test (TUG), short form berg balance scale (SFBBS), and short portable mental status questionnaire (SPMSQ) to measure different factors related to postural stability that have been found to increase the risk of falling. We attached an inertial sensor to the lower back of a group of elderly subjects while they performed the TUG test, providing us with a tri-axial acceleration signal, which we used to extract a set of features, including multi-scale entropy (MSE), permutation entropy (PE), and statistical features. Using the score for each clinical test, we classified our participants into fallers or non-fallers in order to (1) compare the features calculated from the inertial sensor data, and (2) compare the screening capabilities of the multifactor clinical test against each individual test. We use random forest to select features and classify subjects across all scenarios. The results show that the combination of MSE and statistic features overall provide the best classification results. Meanwhile, PE is not an important feature in any scenario in our study. In addition, a t-test shows that the multifactor test of TUG and BBS is a better classifier of subjects in this study.

Using a Stacked Autoencoder for Mobility and Fall Risk Assessment via Time-Frequency Representations of the Timed Up and Go Test.

Fall risk assessment is very important for the graying societies of developed countries. A major contributor to the fall risk of the elderly is mobility impairment. Timely detection of the fall risk can facilitate early intervention to avoid preventable falls. However, continuous fall risk monitoring requires extensive healthcare and clinical resources. Our objective is to develop a method suitable for remote and long-term health monitoring of the elderly for mobility impairment and fall risk without the need for an expert. We employed time-frequency analysis (TFA) and a stacked autoencoder (SAE), which is a deep neural network (DNN)-based learning algorithm, to assess the mobility and fall risk of the elderly according to the criteria of the timed up and go test (TUG). The time series signal of the triaxial accelerometer can be transformed by TFA to obtain richer image information. On the basis of the TUG criteria, the semi-supervised SAE model was able to achieve high predictive accuracies of 89.1, 93.4, and 94.1% for the vertical, mediolateral and anteroposterior axes, respectively. We believe that deep learning can be used to analyze triaxial acceleration data, and our work demonstrates its applicability to assessing the mobility and fall risk of the elderly.

Effects of robotic care interventions for dementia care: A systematic review and meta-analysis randomised controlled trials.

BACKGROUND: The role of robotic care has been studied because it may be a care option applicable to dementia care. However, the effects of robotic care in dementia care are still inconclusive. AIM: To explore the span of the effects of robotic care intervention among patients with dementia. DESIGN: Systematic review and meta-analysis. METHODS: This study searched systematically using the following databases: Academic Search Complete, CINAHL, Cochrane Library, MEDLINE, PubMed, SocINDEX, UpToDate (OVID) and Web of Science. The eligibility criteria were patients with dementia, randomised controlled trials and publications in English. The PEDro scale was used to assess the methodological quality in the included studies. The meta-analysis was performed using a fixed-effects model to calculate the pooled effects of robotic care interventions. STATA 16.0 was used for statistical analysis. The results are reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines. RESULTS: A total of 15 studies met the eligibility criteria and included 1684 participants. Overall, the robotic care interventions had positive effects on agitation (SMD = 0.09; 95% CI [-0.22-0.33]), anxiety (SMD = -0.07; 95% CI [-0.42-0.28]), cognitive function (SMD = 0.16; 95% CI [-0.08-0.40]), depression (SMD = -0.35; 95% CI [-0.69-0.02]), neuropsychiatric symptoms (SMD = 0.16; 95% CI [-0.29-0.61]), total hours of sleep during daytime (SMD = -0.31; 95% CI [-0.55 to 0.07]) and quality of life (SMD = 0.24; 95% CI [-0.23-0.70]). CONCLUSION: Robotic care intervention may be an effective and alternative intervention for improving the health outcomes for people with dementia. The robotic care effect on anxiety should be confirmed. Further studies may consider the frequency, duration of intervention and possible negative outcomes after robotic care interventions. RELEVANCE TO CLINICAL PRACTICE: As a non-pharmacological approach, nursing staff may consider the robotic care intervention in providing care for patients with dementia since this intervention has clinical benefits.

Assessing elderly's functional balance and mobility via analyzing data from waist-mounted tri-axial wearable accelerometers in timed up and go tests.

BACKGROUND: Poor balance has been cited as one of the key causal factors of falls. Timely detection of balance impairment can help identify the elderly prone to falls and also trigger early interventions to prevent them. The goal of this study was to develop a surrogate approach for assessing elderly's functional balance based on Short Form Berg Balance Scale (SFBBS) score. METHODS: Data were collected from a waist-mounted tri-axial accelerometer while participants performed a timed up and go test. Clinically relevant variables were extracted from the segmented accelerometer signals for fitting SFBBS predictive models. Regularized regression together with random-shuffle-split cross-validation was used to facilitate the development of the predictive models for automatic balance estimation. RESULTS: Eighty-five community-dwelling older adults (72.12 ± 6.99 year) participated in our study. Our results demonstrated that combined clinical and sensor-based variables, together with regularized regression and cross-validation, achieved moderate-high predictive accuracy of SFBBS scores (mean MAE = 2.01 and mean RMSE = 2.55). Step length, gender, gait speed and linear acceleration variables describe the motor coordination were identified as significantly contributed variables of balance estimation. The predictive model also showed moderate-high discriminations in classifying the risk levels in the performance of three balance assessment motions in terms of AUC values of 0.72, 0.79 and 0.76 respectively. CONCLUSIONS: The study presented a feasible option for quantitatively accurate, objectively measured, and unobtrusively collected functional balance assessment at the point-of-care or home environment. It also provided clinicians and elderly with stable and sensitive biomarkers for long-term monitoring of functional balance.

Estimating Postural Stability Using Improved Permutation Entropy via TUG Accelerometer Data for Community-Dwelling Elderly People.

To develop an effective fall prevention program, clinicians must first identify the elderly people at risk of falling and then take the most appropriate interventions to reduce or eliminate preventable falls. Employing feature selection to establish effective decision making can thus assist in the identification of a patient's fall risk from limited data. This work therefore aims to supplement professional timed up and go assessment methods using sensor technology, entropy analysis, and statistical analysis. The results showed the different approach of applying logistic regression analysis to the inertial data on a fall-risk scale to allow medical practitioners to predict for high-risk patients. Logistic regression was also used to automatically select feature values and clinical judgment methods to explore the differences in decision making. We also calculate the area under the receiver-operating characteristic curve (AUC). Results indicated that permutation entropy and statistical features provided the best AUC values (all above 0.9), and false positives were avoided. Additionally, the weighted-permutation entropy/statistical features test has a relatively good agreement rate with the short-form Berg balance scale when classifying patients as being at risk. Therefore, the proposed methodology can provide decision-makers with a more accurate way to classify fall risk in elderly people.

Evaluation of postural stability based on a force plate and inertial sensor during static balance measurements.

BACKGROUND: Previous research on balance mostly focused on the assessment, training, and improvements of balance through interventions. We investigated tools commonly used to study static balance. Differences in postural stability were analyzed using multiscale entropy (MSE) and feature analysis. METHODS: A force plate and inertial sensor were used to collect acceleration and center-of-pressure (COP) nonlinear signals. MSE was also used to detect fractal correlations and assess the complexity of univariate data complexity. Fifteen healthy subjects participated in the experiments. Each stood on a force plate and wore a sensor while attempting to maintain postural stability for 30 s in four randomized experiments to evaluate their static balance via a copositive experiment with eyes open/closed and with standing on one foot or both feet. A Wilcoxon-signed rank test was used to confirm that the conditions were significant. Considering the effect of the assessment tools, the influence of the visual and lower limb systems on postural stability was assessed and the results from the inertial sensor and force plate experiments were compared. RESULTS: Force plate usage provided more accurate readings when completing static balance tasks based on the visual system, whereas an inertial sensor was preferred for lower-limb tasks. Further, the eyes-open-standing-on-one-foot case involved the highest complexity at the X, Y, and Z axes for acceleration and at the ML axis for COP compared with other conditions, from which the axial directions can be identified. CONCLUSIONS: The findings suggested investigation of different evaluation tool choices that can be easily adapted to suit different needs. The results for the complexity index and traditional balance indicators were comparable in their implications on different conditions. We used MSE to determine the equipment that measures the postural stability performance. We attempted to generalize the applications of complexity index to tasks and training characteristics and explore different tools to obtain different results. TRIAL REGISTRATION: This study was approved by the Research Ethics Committee of National Taiwan University and classified as expedited on August 24, 2017. The committee is organized under and operates in accordance with Social and Behavioral Research Ethical Principles and Regulations of National Taiwan University and government laws and regulations.

Influence of the Perspectives on the Movement of One-Leg Lifting in an Interactive-Visual Virtual Environment: A Pilot Study.

BACKGROUND: Numerous studies have confirmed the feasibility of active video games for clinical rehabilitation. To maximize training effectiveness, a personal program is necessary; however, little evidence is available to guide individualized game design for rehabilitation. This study assessed the perspectives and kinematic and temporal parameters of a participant's postural control in an interactive-visual virtual environment. METHODS: Twenty-four healthy participants performed one-leg standing by leg lifting when a posture frame appeared either in a first- or third-person perspective of a virtual environment. A foot force plate was used to detect the displacement of the center of pressure. A three-way mixed factor design was applied, where the perspective was the between-participant factor, and the leg-lifting times (0.7 and 2.7 seconds) and leg-lifting angles (30°and 90°) were the within-participant factors. The reaction time, accuracy of the movement, and ability to shift weight were the dependent variables. RESULTS: Regarding the reaction time and accuracy of the movement, there were no significant main effects of the perspective, leg-lifting time, or angle. For the ability to shift weight, however, both the perspective and time exerted significant main effects, F(1,22) = 6.429 and F(1,22) = 13.978, respectively. CONCLUSIONS: Participants could shift their weight more effectively in the third-person perspective of the virtual environment. The results can serve as a reference for future designs of interactive-visual virtual environment as applied to rehabilitation.

An impact study of the design of exergaming parameters on body intensity from objective and gameplay-based player experience perspectives, based on balance training exergame.

Kinect-based exergames allow players to undertake physical exercise in an interactive manner with visual stimulation. Previous studies focused on investigating physical fitness based on calories or heart rate to ascertain the effectiveness of exergames. However, designing an exergame for specific training purposes, with intensity levels suited to the needs and skills of the players, requires the investigation of motion performance to study player experience. This study investigates how parameters of a Kinect-based exergame, combined with balance training exercises, influence the balance control ability and intensity level the player can tolerate, by analyzing both objective and gameplay-based player experience, and taking enjoyment and difficulty levels into account. The exergame tested required participants to maintain their balance standing on one leg within a posture frame (PF) while a force plate evaluated the player's balance control ability in both static and dynamic gaming modes. The number of collisions with the PF depended on the frame's travel time for static PFs, and the leg-raising rate and angle for dynamic PFs. In terms of center of pressure (COP) metrics, significant impacts were caused by the frame's travel time on MDIST-AP for static PFs, and the leg-raising rate on MDIST-ML and TOTEX for dynamic PFs. The best static PF balance control performance was observed with a larger frame offset by a travel time of 2 seconds, and the worst performance with a smaller frame and a travel time of 1 second. The best dynamic PF performance was with a leg-raising rate of 1 second at a 45-degree angle, while the worst performance was with a rate of 2 seconds at a 90-degree angle. The results demonstrated that different evaluation methods for player experience could result in different findings, making it harder to study the design of those exergames with training purposes based on player experience.