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

10.2196/30135 ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. e30135
Author(s):  
Yu-Cheng Hsu ◽  
Hailiang Wang ◽  
Yang Zhao ◽  
Frank Chen ◽  
Kwok-Leung Tsui
Keyword(s):  
Older Adults ◽  
High Risk ◽  
Inertial Sensor ◽  
Community Dwelling ◽  
Measurement Unit ◽  
Support Vector ◽  
Balance Assessment ◽  
Sit To Stand ◽  
Effective Manner ◽  
Community Dwelling Older Adults

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.

scholarly journals Day-to-Day Variability and Year-to-Year Reproducibility of Accelerometer-Measured Free-Living Sit-to-Stand Transitions Volume and Intensity among Community-Dwelling Older Adults

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6068
Author(s):  
Antti Löppönen ◽  
Laura Karavirta ◽  
Erja Portegijs ◽  
Kaisa Koivunen ◽  
Taina Rantanen ◽  
...  
Keyword(s):  
Older Adults ◽  
Angular Velocity ◽  
Functional Disability ◽  
Intraclass Correlation ◽  
Living Environment ◽  
Community Dwelling ◽  
Free Living ◽  
Sit To Stand ◽  
Increased Risk ◽  
Community Dwelling Older Adults

(1) Background: The purpose of this study was to evaluate the day-to-day variability and year-to-year reproducibility of an accelerometer-based algorithm for sit-to-stand (STS) transitions in a free-living environment among community-dwelling older adults. (2) Methods: Free-living thigh-worn accelerometry was recorded for three to seven days in 86 (women n = 55) community-dwelling older adults, on two occasions separated by one year, to evaluate the long-term consistency of free-living behavior. (3) Results: Year-to-year intraclass correlation coefficients (ICC) for the number of STS transitions were 0.79 (95% confidence interval, 0.70–0.86, p < 0.001), for mean angular velocity—0.81 (95% ci, 0.72–0.87, p < 0.001), and maximal angular velocity—0.73 (95% ci, 0.61–0.82, p < 0.001), respectively. Day-to-day ICCs were 0.63–0.72 for number of STS transitions (95% ci, 0.49–0.81, p < 0.001) and for mean angular velocity—0.75–0.80 (95% ci, 0.64–0.87, p < 0.001). Minimum detectable change (MDC) was 20.1 transitions/day for volume, 9.7°/s for mean intensity, and 31.7°/s for maximal intensity. (4) Conclusions: The volume and intensity of STS transitions monitored by a thigh-worn accelerometer and a sit-to-stand transitions algorithm are reproducible from day to day and year to year. The accelerometer can be used to reliably study STS transitions in free-living environments, which could add value to identifying individuals at increased risk for functional disability.

Physical Performance Predictors for Incident Dementia Among Japanese Community-Dwelling Older Adults

2019 ◽  
Vol 99 (9) ◽  
pp. 1132-1140
Author(s):  
Takehiko Doi ◽  
Kota Tsutsumimoto ◽  
Sho Nakakubo ◽  
Min-Ji Kim ◽  
Satoshi Kurita ◽  
...  
Keyword(s):  
Older Adults ◽  
Risk Assessment ◽  
Grip Strength ◽  
Physical Performance ◽  
Performance Level ◽  
Community Dwelling ◽  
Sit To Stand ◽  
Dementia Risk ◽  
Incident Dementia ◽  
Community Dwelling Older Adults

Abstract Background Evaluating physical performance could facilitate dementia risk assessment. However, findings differ regarding which type of physical performance best predicts dementia. Objective The objective of this study was to examine the association between physical performance and incidence of dementia in Japanese community-dwelling older adults. Design This was a prospective study of community-dwelling older adults. Methods Of 14,313 invited individuals who were ≥ 65 years old, 5104 agreed to participate from 2011 to 2012, and 4086 (52% women; mean age = 72.0 years) met the criteria. Baseline assessments of the following physical performance indicators were obtained: grip strength, the Five-Times Sit-to-Stand Test, and the Timed “Up & Go” Test. The physical performance level in each test was categorized as C1 (highest), C2 (middle–high), C3 (middle–low), or C4 (lowest) on the basis of sex-stratified quartile values. Incident dementia status was obtained from medical records that were updated monthly. Results During follow-up (mean duration = 42.9 months), there were 243 incident cases of dementia (5.9%). Log-rank test results indicated that a lower physical performance level constituted a significant risk factor for dementia. After adjustment for covariates, Cox proportional hazards models (reference: highest physical performance level [C1]) demonstrated that the Five-Times Sit-to-Stand Test in the group with the lowest physical performance level (hazard ratio = 1.69; 95% CI = 1.10–2.59) was significantly associated with a risk of dementia. Likewise, the Timed “Up & Go” Test in the group with the lowest physical performance level (hazard ratio = 1.54; 95% CI = 1.01–2.35) was significantly associated with a risk of dementia. However, grip strength was not significantly associated with a risk of dementia. Limitations This study was limited by the use of medical record data. Conclusions A lower mobility-related physical performance level was associated with dementia risk. Dementia risk assessment should include an adequate evaluation of physical function.

scholarly journals Relationship Between Dynamic Balance Measures and Functional Performance in Community-Dwelling Elderly People

2010 ◽  
Vol 90 (5) ◽  
pp. 748-760 ◽  
Author(s):  
Ankur Desai ◽  
Valerie Goodman ◽  
Naaz Kapadia ◽  
Barbara L. Shay ◽  
Tony Szturm
Keyword(s):  
Older Adults ◽  
Elderly People ◽  
Dynamic Balance ◽  
Community Dwelling ◽  
Standing Balance ◽  
Self Report ◽  
Clinical Test ◽  
Balance Assessment ◽  
Test Protocol ◽  
Community Dwelling Older Adults

BackgroundPoor balance control, mobility restrictions, and fall injuries are serious problems for many older adults.ObjectiveThe purpose of this study was to evaluate a new dynamic standing balance assessment test for identifying individuals at risk for falling in a group of community-dwelling older adults.DesignThis was a cross-sectional observational study of 72 community-dwelling older adults who were receiving rehabilitation in a geriatric day hospital.MethodA Dynamic Balance Assessment (DBA) test protocol was developed based on the concept of the Sensory Organization Test and the Clinical Test of Sensory Interaction and Balance. The DBA consists of 6 tasks performed on a normal floor surface and repeated on a sponge surface. A flexible pressure mat was used to record the foot's center of pressure (COP) on both surfaces, and loss of balance was recorded. Balance performance also was evaluated using the Berg Balance Scale, the Timed “Up & Go” Test, gait speed, and the Six-Minute Walk Test. Participants were classified as “fallers” or “nonfallers” based on a self-report.ResultsNo significant differences were noted between the faller group (n=47) and the nonfaller group (n=25) for demographic variables or medications. The DBA composite scores, which were derived from analysis of COP excursions of the 6 tasks performed on the sponge surface, were able to distinguish between fallers and nonfallers. Of the clinical tests, only the Timed “Up & Go” Test was able to differentiate between the faller and nonfaller groups.LimitationsA prospective study is needed to confirm the current findings and to expand testing to a larger and more diverse sample.ConclusionsThe findings indicate that analysis of the extent and amount of COP displacements during selected tasks and under different surface conditions is an appropriate method to assess dynamic standing balance controls and can discriminate between fallers and nonfallers among community-dwelling elderly people.

scholarly journals Simple scoring algorithm to identify community-dwelling older adults with limited health literacy: a cross-sectional study in Taiwan

BMJ Open ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. e045411
Author(s):  
Wen-Hsuan Hou ◽  
Ken N Kuo ◽  
Mu-Jean Chen ◽  
Yao-Mao Chang ◽  
Han-Wei Tsai ◽  
...  
Keyword(s):  
Older Adults ◽  
Health Literacy ◽  
High Risk ◽  
Health Information ◽  
Cross Sectional Study ◽  
Community Dwelling ◽  
Sectional Study ◽  
Cross Sectional ◽  
Scoring Algorithm ◽  
Community Dwelling Older Adults

ObjectiveHealth literacy (HL) is the degree of individuals’ capacity to access, understand, appraise and apply health information and services required to make appropriate health decisions. This study aimed to establish a predictive algorithm for identifying community-dwelling older adults with a high risk of limited HL.DesignA cross-sectional study.SettingFour communities in northern, central and southern Taiwan.ParticipantsA total of 648 older adults were included. Moreover, 85% of the core data set was used to generate the prediction model for the scoring algorithm, and 15% was used to test the fitness of the model.Primary and secondary outcome measuresPearson’s χ2 test and multiple logistic regression were used to identify the significant factors associated with the HL level. An optimal cut-off point for the scoring algorithm was identified on the basis of the maximum sensitivity and specificity.ResultsA total of 350 (54.6%) patients were classified as having limited HL. We identified 24 variables that could significantly differentiate between sufficient and limited HL. Eight factors that could significantly predict limited HL were identified as follows: a socioenvironmental determinant (ie, dominant spoken dialect), a health service use factor (ie, having family doctors), a health cost factor (ie, self-paid vaccination), a heath behaviour factor (ie, searching online health information), two health outcomes (ie, difficulty in performing activities of daily living and requiring assistance while visiting doctors), a participation factor (ie, attending health classes) and an empowerment factor (ie, self-management during illness). The scoring algorithm yielded an area under the curve of 0.71, and an optimal cut-off value of 5 represented moderate sensitivity (62.0%) and satisfactory specificity (76.2%).ConclusionThis simple scoring algorithm can efficiently and effectively identify community-dwelling older adults with a high risk of limited HL.

Sign in / Sign up

Export Citation Format

Share Document