Purpose: This study aimed to develop a fall prediction model for community-dwelling older adults using machine learning. Methods: The present study was conducted with a secondary data analysis that used data from the 2020 national survey of older Koreans. Among 10,097 participants, data 177 were excluded due to incompleteness and 9,920 were included in the final analysis. Because of data imbalance, upsampling was performed to increase the number of individuals who fell. Forty-five independent variables for fall prediction were selected based on the fall risk factors from previous studies and univariate statistical analysis. The data were split into training and testing sets at an 80:20 ratio. Three machine learning algorithms—logistic regression, random forest, and artificial neural network—were used to develop a fall prediction model. Results: The random forest model outperformed the others, with an area under the curve of .91, accuracy of .94, precision of .94, recall of .74, and F1 score of .83. An analysis of feature importance revealed that satisfaction with health condition, visual difficulty, instrumental activities of daily living, performance of 400m walk, and cognitive ability were the top five features for fall prediction. Conclusion The fall prediction model developed using machine learning demonstrated high model performance, implying its suitability for use as a primary screening tool for fall risk. Subjective satisfaction with one’s health should be considered as an important factor in predicting falls in community-dwelling older adults. It is necessary for community health nurses to reinforce positive health awareness by continuous disease management and physical function improvement for older adults to prevent falls.

Purpose: This study aimed to develop a fall prediction model for community-dwelling older adults using machine learning. Methods: The present study was conducted with a secondary data analysis that used data from the 2020 national survey of older Koreans. Among 10,097 participants, data 177 were excluded due to incompleteness and 9,920 were included in the final analysis. Because of data imbalance, upsampling was performed to increase the number of individuals who fell. Forty-five independent variables for fall prediction were selected based on the fall risk factors from previous studies and univariate statistical analysis. The data were split into training and testing sets at an 80:20 ratio. Three machine learning algorithms—logistic regression, random forest, and artificial neural network—were used to develop a fall prediction model. Results: The random forest model outperformed the others, with an area under the curve of .91, accuracy of .94, precision of .94, recall of .74, and F1 score of .83. An analysis of feature importance revealed that satisfaction with health condition, visual difficulty, instrumental activities of daily living, performance of 400m walk, and cognitive ability were the top five features for fall prediction. Conclusion The fall prediction model developed using machine learning demonstrated high model performance, implying its suitability for use as a primary screening tool for fall risk. Subjective satisfaction with one’s health should be considered as an important factor in predicting falls in community-dwelling older adults. It is necessary for community health nurses to reinforce positive health awareness by continuous disease management and physical function improvement for older adults to prevent falls.

Purpose: This study aimed to develop a fall prediction model for community-dwelling older adults using machine learning. Methods: The present study was conducted with a secondary data analysis that used data from the 2020 national survey of older Koreans. Among 10,097 participants, data 177 were excluded due to incompleteness and 9,920 were included in the final analysis. Because of data imbalance, upsampling was performed to increase the number of individuals who fell. Forty-five independent variables for fall prediction were selected based on the fall risk factors from previous studies and univariate statistical analysis. The data were split into training and testing sets at an 80:20 ratio. Three machine learning algorithms—logistic regression, random forest, and artificial neural network—were used to develop a fall prediction model. Results: The random forest model outperformed the others, with an area under the curve of .91, accuracy of .94, precision of .94, recall of .74, and F1 score of .83. An analysis of feature importance revealed that satisfaction with health condition, visual difficulty, instrumental activities of daily living, performance of 400m walk, and cognitive ability were the top five features for fall prediction. Conclusion The fall prediction model developed using machine learning demonstrated high model performance, implying its suitability for use as a primary screening tool for fall risk. Subjective satisfaction with one’s health should be considered as an important factor in predicting falls in community-dwelling older adults. It is necessary for community health nurses to reinforce positive health awareness by continuous disease management and physical function improvement for older adults to prevent falls.

Purpose: This study aimed to develop a fall prediction model for community-dwelling older adults using machine learning. Methods: The present study was conducted with a secondary data analysis that used data from the 2020 national survey of older Koreans. Among 10,097 participants, data 177 were excluded due to incompleteness and 9,920 were included in the final analysis. Because of data imbalance, upsampling was performed to increase the number of individuals who fell. Forty-five independent variables for fall prediction were selected based on the fall risk factors from previous studies and univariate statistical analysis. The data were split into training and testing sets at an 80:20 ratio. Three machine learning algorithms—logistic regression, random forest, and artificial neural network—were used to develop a fall prediction model. Results: The random forest model outperformed the others, with an area under the curve of .91, accuracy of .94, precision of .94, recall of .74, and F1 score of .83. An analysis of feature importance revealed that satisfaction with health condition, visual difficulty, instrumental activities of daily living, performance of 400m walk, and cognitive ability were the top five features for fall prediction. Conclusion The fall prediction model developed using machine learning demonstrated high model performance, implying its suitability for use as a primary screening tool for fall risk. Subjective satisfaction with one’s health should be considered as an important factor in predicting falls in community-dwelling older adults. It is necessary for community health nurses to reinforce positive health awareness by continuous disease management and physical function improvement for older adults to prevent falls.

Purpose: This study aimed to investigate autonomic nervous function during the orthostatic challenge and its relationship with depression and fall, and to elucidate fall-associated factors, including autonomic function, executive function, and depression among institutionalized older adults with mild cognitive impairment (MCI). Methods: This study employed a descriptive cross-sectional design. Fall experiences in the current institutions were researched. Heart rate variability (HRV) during the orthostatic challenge was measured. Executive function was evaluated using the semantic verbal fluency test and clock drawing test. Depression was assessed using the Geriatric Depression Scale. Results: Of the 115 older adults, 17 (14.8%) experienced falls in the current institution. None of the HRV indices during the orthostatic challenge showed any significant changes except for the standard deviation of normal RR intervals (p = .037) in the institutionalized older adults with MCI. None of the HRV indices was significantly related to the depressive symptoms. Multivariate logistic regression analysis showed that normalized high frequency on lying was independently associated with falls (OR = 1.027, p = .049) after adjusting for other conventional fall risk factors although executive function and depressive symptoms were not significant factors for falls. Conclusions Institutionalized older adults with MCI were vulnerable to autonomic nervous modulation, especially to sympathetic modulation, during the orthostatic challenge, which was not associated with depressive symptoms. As increased resting parasympathetic activity seemed to play a key role in association with falls, autonomic nervous function assessment should be considered for fall risk evaluation.

Purpose: This study aimed to evaluate the rest-activity circadian rhythm (RAR) using data obtained from wearable actigraph devices in hospitalized older adults with mild cognitive impairment (MCI), and to investigate its relationship with salivary alpha amylase (sAA). Methods: This secondary data analysis used data from the Hospitalized Older Adults’ Cognition and Physical Activity Study. Actigraph data for 3-4 days were analyzed for RAR. RAR indices such as interdaily stability (IS), intradaily variability (IV), activity level during the most active 10-hour period and during the most least active 5-hour period, and relative amplitude (RA) were calculated. Data on sAA collected in the morning and general characteristics, including body mass index (BMI), were analyzed. Results: Data from 92 hospitalized older adults with MCI were analyzed. The IS, IV, RA were 0.23, 0.73, 0.88, respectively. The average level of sAA was 77.02 U/mL, and a higher level of sAA was significantly associated with better IS and RA in the regression analysis, while age, BMI, and cognitive level were not. BMI showed positive correlations with IS and RA. Conclusion RAR in the hospitalized older adults with MCI was attenuated, showing especially low IS, which implies they failed to maintain regular and repetitive 24-hour RAR. Increased sAA and BMI were associated with robust RAR. Nurses need to pay attention to maintain robust RAR in hospitalized older adults with MCI, and strategies should be developed to improve their RAR.

Purpose: A tobacco-free campus (TFC) is the most advanced tobacco-control policy for college campuses, but it has rarely been explored in Korea. This study aimed to explore Korean college students’ attitudes toward TFC and related factors. Methods: This cross-sectional descriptive study enrolled college students who were taking an elective course on smoking cessation and a healthy lifestyle at a university located in Incheon, Korea. Data were collected from March 1 to December 31, 2019 using a structured questionnaire, and study participants were recruited using convenience sampling. Results: Data on 309 college students were analyzed. Of those participants, 6.1% supported the TFC policy. Multiple logistic regression analysis showed that female gender (adjusted odds ratio [aOR]=5.80, 95% confidence interval [CI]=1.47-22.95), taking the course to quit smoking oneself (aOR=11.03, 95% CI=1.04-117.05), anxiety in the past month (aOR=4.27, 95% CI=1.06-17.31), and being a current smoker (aOR=0.06, 95% CI=0.01-0.70) were statistically significant independent predictors of TFC support. Conclusion Women, students taking the course to quit smoking themselves, nonsmokers, and students who felt anxious in the past month were more likely to support TFC. Further research with more representative samples is required to examine the characteristics of people who favor TFC.

Purpose: This study aimed to investigate objectively measured physical activity (PA) in institutionalized older adults with mild cognitive impairment (MCI) and to elucidate the influence of autonomic nervous function, salivary cortisol, and PA on cognitive functions based on neurovisceral integration model. Methods: Overall cognitive function was evaluated using the mini-mental state examination (MMSE) and executive function was evaluated using semantic verbal fluency test and clock drawing test. Actigraph for PA, HRV and sAA for autonomous function, and the geriatric depression scale for depression were used. Saliva specimens were collected in the morning for sAA and cortisol. Results: Ninety-eight older adults from four regional geriatric hospitals participated in the study. They took 4,499 steps per day on average. They spent 753.93 minutes and 23.12 minutes on average in sedentary and moderate-to-vigorous activity, respectively. In the multiple regression analysis, lower salivary cortisol level (β = - .33, p = .041) and greater step counts (β = .37, p = .029) significantly improved MMSE score. Greater step count (β = .27, p = .016) also exerted a significant influence on verbal fluency, and greater sAA (β = .35, p = .026) was significantly associated with a better clock drawing test result. Conclusion Salivary cortisol, sAA and physical activity were significantly associated with cognitive functions. To prevent older adults from developing dementia, strategies are needed to increase their overall PA amount by decreasing sedentary time and to decrease salivary cortisol for cognitive function, and to maintain their sympathetic nervous activity for executive function.

Purpose: This study aimed to investigate objectively measured physical activity (PA) in institutionalized older adults with mild cognitive impairment (MCI) and to elucidate the influence of autonomic nervous function, salivary cortisol, and PA on cognitive functions based on neurovisceral integration model. Methods: Overall cognitive function was evaluated using the mini-mental state examination (MMSE) and executive function was evaluated using semantic verbal fluency test and clock drawing test. Actigraph for PA, HRV and sAA for autonomous function, and the geriatric depression scale for depression were used. Saliva specimens were collected in the morning for sAA and cortisol. Results: Ninety-eight older adults from four regional geriatric hospitals participated in the study. They took 4,499 steps per day on average. They spent 753.93 minutes and 23.12 minutes on average in sedentary and moderate-to-vigorous activity, respectively. In the multiple regression analysis, lower salivary cortisol level (β = - .33, p = .041) and greater step counts (β = .37, p = .029) significantly improved MMSE score. Greater step count (β = .27, p = .016) also exerted a significant influence on verbal fluency, and greater sAA (β = .35, p = .026) was significantly associated with a better clock drawing test result. Conclusion Salivary cortisol, sAA and physical activity were significantly associated with cognitive functions. To prevent older adults from developing dementia, strategies are needed to increase their overall PA amount by decreasing sedentary time and to decrease salivary cortisol for cognitive function, and to maintain their sympathetic nervous activity for executive function.

Purpose: This study aimed to evaluate the correlation and agreement of physical activity (PA) between data obtained from wearable Actigraph devices and self-reporting questionnaires, and to investigate the relationship between psychological state (depression, anxiety, and fatigue) and PA. Methods: A descriptive study was conducted using physical measurements and surveys. PA was measured through both the International Physical Activity Questionnaire (IPAQ) and the Actigraph GT3X+ device. The demographic characteristics of the subjects, as well as their depression, anxiety, and fatigue scores, were collected with structured questionnaires. The Spearman’s rank correlation coefficient and the Bland-Altman plot method were employed. Results: Data from 36 healthy adults were analyzed. The overall levels of PA measured using the IPAQ and the Actigraph were 1,891.69 MET min/week and 669.96 MET/ day, respectively. Total levels of PA did not show a significant correlation between the two measurement methodologies. However, the moderate-intensity PA resulting from the IPAQ scores showed a significant positive correlation with the light-intensity PA recorded by the Actigraph. The Bland-Altman plot analysis demonstrated that the levels of PA as measured by the two different methods did not match. In addition, PA measured using the Actigraph showed a significant negative correlation with depression and anxiety whereas PA measured using the IPAQ showed a significant positive correlation with fatigue. Conclusion The conclusion of this study is that the data obtained from the subjective self-reporting questionnaire and the wearable Actigraph do not correlate or match in healthy adults. Future research should investigate the relationship between depression and PA intensity through the Actigraph, or other wearable devices equipped with smartphone apps.