• ETRI Journal
• /
• v.44 no.4
• /
• pp.654-671
• /
• 2022

Accidental falls frequently occur during activities of daily living. Although many studies have proposed various accident detection methods, no high-performance accident detection system is available. In this study, we propose a method for integrating data and accident detection algorithms presented in existing studies, collect new data (from two stunt performers and 15 people over age 60) using a developed wearable device, demonstrate new features and related accident detection algorithms, and analyze the performance of the proposed method against existing methods. Comparative analysis results show that the newly defined features extracted reflect more important risk factors than those used in existing studies. Further, although the traditional algorithms applied to integrated data achieved an accuracy (AC) of 79.5% and a false positive rate (FPR) of 19.4%, the proposed accident detection algorithms achieved 97.8% AC and 2.9% FPR. The high AC and low FPR for accidental falls indicate that the proposed method exhibits a considerable advancement toward developing a commercial accident detection system.

• Korean Journal of Occupational Health Nursing
• /
• v.32 no.2
• /
• pp.79-88
• /
• 2023

Purpose: This study aims to identify the factors that influence the experience of falls among older adults living in the community. Methods: The study participants were 70,887 65-year-olds who participated in the 2021 Community Health Survey. The study employed the Rao-scott x 2 test to examine the variation in fall experiences based on the characteristics of the older adults. Multiple logistic regression analysis was conducted to investigate these characteristics' impact on older adults' fall experiences. Results: The proportion of subjects in fall experience was 16.6%. The factors influencing the subject's fall experience were sex (odds ratio [OR]=1.47, 95% confidence interval [CI]=1.37~1.57), age (OR=1.48, 95% CI=1.34~1.65), family structure (OR=1.23, 95% CI=1.15~1.31), body mass index (OR=1.13, 95% CI=1.06~1.20), diabetes (OR=1.12, 95% CI=1.06~1.20), depression experiences (OR=1.56, 95% CI=1.42~1.70), stress (OR=1.12, 95% CI=1.05~1.19), subjective health status (OR=1.77, 95% CI=1.63~1.92), life satisfaction (OR=1.57, 95% CI=1.41~1.76), and chewing discomfort (OR=1.29, 95% CI=1.21~1.38). Conclusion: Efforts should be made to effectively educate and develop various programs aimed at reducing falls among older adults. It is essential to emphasize the importance of continuous and active attention to falls in the older adult population.

• PNF and Movement
• /
• v.22 no.1
• /
• pp.43-54
• /
• 2024

Purpose: Falls among persons older than 65 years are a significant concern due to their frequency and severity. This study aimed to develop a vest-type embedded artificial intelligence (AI) system capable of detecting and predicting falls in various scenarios. Methods: In this study, we established and developed a vest-type embedded AI system to judge and predict falls in various directions and situations. To train the AI, we collected data using acceleration and gyroscope values from a six-axis sensor attached to the seventh cervical and the second sacral vertebrae of the user, considering accurate motion analysis of the human body. The model was constructed using a neural network-based AI prediction algorithm to anticipate the direction of falls using the collected pedestrian data. Results: We focused on developing a lightweight and efficient fall prediction model for integration into an embedded AI algorithm system, ensuring real-time network optimization. Our results showed that the accuracy of fall occurrence and direction prediction using the trained fall prediction model was 89.0% and 78.8%, respectively. Furthermore, the fall occurrence and direction prediction accuracy of the model quantized for embedded porting was 87.0 % and 75.5 %, respectively. Conclusion: The developed fall detection and prediction system, designed as a vest-type with an embedded AI algorithm, offers the potential to provide real-time feedback to pedestrians in clinical settings and proactively prepare for accidents.

• The Journal of the Korea Contents Association
• /
• v.15 no.2
• /
• pp.333-343
• /
• 2015

The purpose of this study is to investigate the factors that affect the fall prevention awareness of care-givers working at long-term care hospitals. A convenience sampling method was used to select care-givers who worked at 7 different long term care hospitals which were located in D city and N city. Data were collected from July 2014 to August 2014. 200 data were used for analysis out of 215 data which were collected. The hierarchical regression analysis reveals the following results: Firstly, the effects of care-givers' education level, certificate status, period of work experience and fall-related learning hours on their fall prevention awareness level were statistically significant. Secondly, among fall prevention health beliefs, perceived benefit, perceived disability, perceived sensitivity and self-efficacy were positively related to the level of fall prevention awareness. Thirdly, while such factors as perceived benefit, perceived sensitivity and self-efficacy showed positive effects on the fall prevention awareness, the period of work experience had negative effects. The regression model shows the power of explanation of 31.7 percents. In conclusion, the study suggests a fine-tuned program to improve care-givers' fall prevention awareness in a way of promoting fall prevention self-efficacy, perceived benefits and perceived sensitivity while considering the care-givers' period of work experience.

• Journal of Korean Academy of Nursing
• /
• v.45 no.4
• /
• pp.469-482
• /
• 2015

Purpose: The purpose of this study was to identify which nursing interventions are the most effective in fall prevention for hospitalized patients. Methods: From 3,675 papers searched, 34 were selected for inclusion in the meta-analysis. Number of fallers, falls, falls per 1,000 hospital-days, and injurious falls, fall protection activity, knowledge related to falls, and self-efficacy about falls were evaluated as outcome variables. Data were analyzed using the Comprehensive Meta Analysis (CMA) 2.2 Version program and the effect sizes were shown as the Odd Ratio (OR) and Hedges's g. Results: Overall effect size of nursing interventions for fall prevention was OR=0.64 (95% CI: 0.57~0.73, p <.05) and Hedges's g= - 0.24. The effect sizes (OR) of each intervention ranged from 0.34 to 0.93, and the most effective nursing intervention was the education & environment intervention (OR=0.34, 95% CI: 0.28~0.42, p<.001), followed by education intervention (OR=0.57, 95% CI: 0.50~0.67, p=.001). Subgroup analyses showed that multifaceted interventions (OR=0.76, 95% CI: 0.73~0.79, p<.001) were more effective than unifactorial interventions, and that activities for prevention of falls (OR=0.08, 95% CI: 0.05~0.15, p<.001) showed the largest effect size among outcome variables. Conclusion: Falls in hospitalized patients can be effectively prevented using the nursing interventions identified in this study. These findings provide scientific evidence for developing and using effective nursing interventions to improve the safety of hospitalized patients.

• Journal of muscle and joint health
• /
• v.19 no.2
• /
• pp.131-141
• /
• 2012

Purpose: The purpose of this study was to test the change of study variables (knowledge, efficacy, and fatigue) related to using orthosis and fear of falling in fracture patients wearing the leg orthosis after fall prevention education in terms of educational method and frequency. Methods: Participants were 87 fracture patients wearing the leg orthosis. Experimental I group (n=30) and experimental II group (n=27) received the fall prevention education once and three times respectively with leaflets. Experimental III group (n=30) received video training once. Results: The level of the subjects' knowledge was significantly increased in experimental I and II groups rather than in experimental III group. In case of experimental I and experimental II group, fear of falling was decreased when compared to experimental III group. However, there were no significant changes in efficacy and fatigue related to using orthosis among three groups. Conclusion: The fall prevention education using leaflets was more effective than video training method. Only one education with leaflets was effective enough. Therefore, it is recommended that the education with leaflets or pamphlets should be developed systematically according to the characteristics of fracture patients wearing the leg orthosis.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.2
• /
• pp.336-342
• /
• 2015

Fall-related injuries are the most common cause of accidental death for the elderly and the most frequent work-related injuries in construction sites. Due to the growing popularity of smartphones, there has been a number of research work related to the use of sensors embedded in the smartphone for fall detection. Falls can be detected easily by measuring the magnitude and direction of acceleration vectors. In general, the direction of the acceleration vector does not show the object movement, but the velocity vector directly indicates the tangential direction in which the object is moving. In this paper, we proposed a new method for computing the fall direction based on the characteristics of the velocity vector extracted from the accelerometer.

• Physical Therapy Rehabilitation Science
• /
• v.7 no.2
• /
• pp.54-60
• /
• 2018

Objective: Persons with chronic stroke fall more often than healthy elderly individuals. The Timed Up and Go test (TUG) is used as a fall prediction tool, but only provides a result for the total measurement time. This study aimed to determine the optimal cut-off values for each of the 6 components of the TUG. Design: Retrospective study. Methods: Thirty persons with chronic stroke participated in the study. TUG evaluation was performed using a wearable miniaturized inertial sensor. Sensitivity, specificity, and predictive values were calculated using the Receiver Operating Characteristic (ROC) curve analysis for the measured values in each section. Optimal values for fall risk classification were determined. Logistic regression analysis was used to investigate the risk of future falls based on TUG. Results: The cut-off values of the 6 sections of the TUG were determined, as follows: sit-to-stand >2.00 seconds (p<0.05), forward gait >4.68 seconds (p<0.05), mid-turn >3.82 seconds (p<0.05), return gait >4.81 seconds (p<0.05), end-turn >2.95 seconds (p<0.05), and stand-to-sit >2.13 seconds (p<0.05). The risk of falling increased by 2.278 times when the mid-turn value was >3.82 seconds (p<0.05). Conclusions: The risk of falls increased by 2.28 times when the value of the mid-turn interval exceeded 3.82 seconds. Therefore, when interpreting TUG results, the predictive accuracy for falls will be higher when the measurement time for each section is analyzed, together with the total time for TUG.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.13 no.1
• /
• pp.60-67
• /
• 2006

Purpose: To identify the relationship between medication use and falls among hospitalized stroke patients. Method: The medical records of 472 patients with strokes were reviewed using a questionnaire on falling developed by the authors. Frequencies, percentages, means, standard deviations, and t-test and ${\chi}^2$-test, multiple logistic regression analysis were done using the SAS program. Results: The rate for falls by the patients during their stay in the hospital was 14.0%. The length of stay was longer and the morbidity duration of stroke shorter in the fall group than in the non-fall group. The use of sedatives, laxatives, and antidepressants was a significant predictor of falls and was associated with increase likelihood of falling(1.82, 1.81, 1.75 times respectively). Conclusion: In hospitalized stroke patients, there was a significant association between the use of sedatives, laxatives, antidepressants and falls. The number and kinds of ingested drugs was also associated with falls. It is necessary to further analyze the causes of falls based on results of the present study.

• Journal of Korean Clinical Nursing Research
• /
• v.23 no.2
• /
• pp.202-210
• /
• 2017

Purpose: In this study an investigation was done of injuries from inpatient falls and diagnostic tests and treatment after falls to identify what factors affect the occurrence of injury from inpatient falls in a tertiary hospital. Methods: Data for this cross-sectional study were retrieved for 428 fall events from data reported between January 1 and December 31, 2015 and were retrieved from the patient-safety reporting system in the hospital's electronic health records. A multivariate logistic regression model was developed with STATA 13.0. Results: Of the patients, 197 (46.0%) had physical injuries due to falls, 119 (27.8%) were given further diagnostic tests, and 358 (83.6%) received treatment including close observation after inpatient falls. Logistic-regression results identified that age, department, and risk factors had significant impact on injuries from falls. Conclusion: Findings indicate that to reduce the severity of injury after inpatient falls, each hospital should regularly evaluate identified factors, design fall-prevention practices specialized for elders and vulnerable patients, and initiate environmental and equipment innovations.