Aim: This review aimed to examine and describe the published research on nursing home (NH) nurses' turnover intentions in their workplace.Design: This study is a systematic review following PRISMA guidelines.Methods: An electronic search was conducted for English and Korean articles to identify research studies published between 2009–2019 using CINAHL, PubMed, Cochrane Library, PsycINFO, RISS, and DBpia.Results: A total of six studies met the inclusion criteria and revealed NH nurses' turnover intentions. The factors influencing NH nurses' turnover intentions were identified and classified as individual and organizational factors. Among the various factors above, this study found that job satisfaction was the most influential factor in nurses' turnover intentions. Therefore, further efforts are required to increase NH nurses' job satisfaction to decrease turnover intention.

Background: A machine learning (ML) system is able to construct algorithms to continue improving predictions and generate automated knowledge through data-driven predictors or decisions. Objective: The purpose of this study was to compare six ML methods (random forest (RF), logistics regression, linear support vector machine (SVM), polynomial SVM, radial SVM, and sigmoid SVM) of predicting falls in nursing homes (NHs). Methods: We applied three representative six-ML algorithms to the preprocessed dataset to develop a prediction model (N = 60). We used an accuracy measure to evaluate prediction models. Results: RF was the most accurate model (0.883), followed by the logistic regression model, SVM linear, and polynomial SVM (0.867). Conclusions: RF was a powerful algorithm to discern predictors of falls in NHs. For effective fall management, researchers should consider organizational characteristics as well as personal factors. Recommendations for Future Research: To confirm the superiority of ML in NH research, future studies are required to discern additional potential factors using newly introduced ML methods.

This study aimed to identify the terminologies of NANDA-I, NOC, NIC, and NNN linkages that have been used for nursing home (NH) residents. This study used a retrospective descriptive design. Data accrued from 57 registered nurses (RNs) in 25 Korean NHs. The RNs randomly selected one resident and assessed for applied NANDA-I, NOC, and NIC from the previous 7 days by reviewing nursing charts and records. Finally, the data of 57 residents in 25 NHs were collected. Results: We identified seven NNN linkages: risk for falls–fall prevention behavior–fall prevention; self-care deficit: bathing/hygiene–self-care: activities of daily living (ADL)–self-care assistance: bathing/hygiene; impaired memory–memory–cognitive stimulation; chronic confusion–neurological status: consciousness–medication management; chronic confusion–memory–medication management; impaired walking–mobility–exercise promotion: strength training; and impaired walking–ambulation–exercise promotion: strength training. The identified core NANDA-I, NOC, NIC, and NNN linkages for NH residents from this study provide a scope of practice of RNs working in NHs.

Background: Machine learning (ML) can keep improving predictions and generating automated knowledge via data-driven predictors or decisions. Objective: The purpose of this study was to compare different ML methods including random forest, logistics regression, linear support vector machine (SVM), polynomial SVM, radial SVM, and sigmoid SVM in terms of their accuracy, sensitivity, specificity, negative predictor values, and positive predictive values by validating real datasets to predict factors for pressure ulcers (PUs). Methods: We applied representative ML algorithms (random forest, logistic regression, linear SVM, polynomial SVM, radial SVM, and sigmoid SVM) to develop a prediction model (N = 60). Results: The random forest model showed the greatest accuracy (0.814), followed by logistic regression (0.782), polynomial SVM (0.779), radial SVM (0.770), linear SVM (0.767), and sigmoid SVM (0.674). Conclusions: The random forest model showed the greatest accuracy for predicting PUs in nursing homes (NHs). Diverse factors that predict PUs in NHs including NH characteristics and residents’ characteristics were identified according to diverse ML methods. These factors should be considered to decrease PUs in NH residents.

The purpose of this scoping review was to map and organize the previous studies conducted among fathers whose infants experienced admission to neonatal intensive care units (NICUs) in South Korea. A scoping review was conducted based on Arksey and O'Malley using the JBI template. The review was described by PRISMA-ScR. The studies were reviewed through five electronic databases (PubMed, CINAHL, Web of Science, RISS and KMbase) since 1996. Each study was analyzed, extracted, and summarized into the following domains: general characteristics (language, design, data collection methods, intervention, data collection site, and time) and fathers' characteristics (types of fathers, mean age, variables related to the fathers, and measurements). A total of 290 studies were identified after screening titles and abstracts, and 32 full-text articles were retrieved for eligibility. Finally, 15 articles were included in the review. Four themes were derived after review: paternal stress, paternal attachment, fathers' adaptation, and fathers' support needs. Infants' hospitalization in NICUs causes stress for fathers but they overcome difficulties and play multiple roles as guardians, caregivers, and decision-makers of their spouses and infants over time. Paternal attachment increases significantly after participating in tactile and educational interventions. Fathers rely on nurses and they want to receive support from nurses. It is necessary for NICU nurses to understand and support fathers whose infants are hospitalized in NICUs. Medical institutions should provide nursing interventions and education for fathers to relieve their stress, help their adaptation, and improve attachment.