Cin-Computers Informatics Nursing最新文献

Background: Since the onset of the COVID-19 pandemic, healthcare workers around the world have experimented with technologies to facilitate communication and care for patients and their care partners.

Methods: Our team reviewed the literature to examine best practices in utilizing technology to support communication between nurses, patients, and care partners while visitation is limited. We searched four major databases for recent articles on this topic, conducted a systematic screening and review of 1902 articles, and used the Johns Hopkins Nursing Evidence-Based Practice for Nurses and Healthcare Professionals Model & Guidelines to appraise and translate the results of 23 relevant articles.

Results: Our evaluation yielded three main findings from the current literature: (1) Virtual contact by any technological means, especially video visitation, improves satisfaction, reduces anxiety, and is well-received by the target populations. (2) Structured video rounding provides effective communication among healthcare workers, patients, and offsite care partners. (3) Institutional preparation, such as a standardized checklist and dedicating staff to roles focused on facilitating communication, can help healthcare workers create environments conducive to therapeutic virtual communication.

Discussion: In situations that require healthcare facilities to limit visitation between patients and their care partners, the benefits of virtual visitation are evident. There is variance in the types of technologies used to facilitate virtual visits, but across all of them, there are consistent themes demonstrating the benefits of virtual visits and virtual rounding. Healthcare institutions can prepare for future limited-visitation scenarios by reviewing the current evidence and integrating virtual visitation into modern healthcare delivery.

Adequate nurse staffing is crucial for quality healthcare, necessitating accurate predictions of patient arrival rates. These forecasts can be determined using supervised machine learning methods. Optimization of machine learning methods is largely about minimizing the prediction error. Existing models primarily utilize data such as historical patient visits, seasonal trends, holidays, and calendars. However, it is unclear what other features reduce the prediction error. Our systematic literature review identifies studies that use supervised machine learning to predict patient arrival numbers using nontemporal features, which are features not based on time or dates. We scrutinized 26 284 studies, eventually focusing on 27 relevant ones. These studies highlight three main feature groups: weather data, internet search and usage data, and data on (social) interaction of groups. Internet data and social interaction data appear particularly promising, with some studies reporting reduced errors by up to 33%. Although weather data are frequently used, its utility is less clear. Other potential data sources, including smartphone and social media data, remain largely unexplored. One reason for this might be potential data privacy challenges. In summary, although patient arrival prediction has become more important in recent years, there are still many questions and opportunities for future research on the features used in this area.

This descriptive study aims to investigate the content, quality, and reliability of YouTube videos containing content related to endotracheal tube aspiration. The study was scanned using the keywords "endotracheal aspiration" and "endotracheal tube aspiration," and 22 videos were included in the study. The contents of the selected videos were measured using the Endotracheal Tube Aspiration Skill Form, their reliability was measured using the DISCERN Survey, and their quality was measured using the Global Quality Scale. Of the 22 videos that met the inclusion criteria, 18 (81.8%) were educational, and four (18.2%) were product promotional videos. When pairwise comparisons were made, the coverage score of open aspiration videos was higher for educational videos than for product promotion videos (P < .005). Useful videos had higher reliability and quality scores than misleading videos (P < .05). In addition, the reliability and quality scores of videos uploaded by official institutions were significantly higher than those of videos uploaded by individual users (P < .05). This study found that the majority of endotracheal tube aspiration training videos reviewed in the study were published by individual users, and a significant proportion of these videos had low levels of reliability and quality.

All disciplines, including nursing, may be experiencing significant changes with the advent of free, publicly available generative artificial intelligence tools. Recent research has shown the difficulty in distinguishing artificial intelligence-generated text from content that is written by humans, thereby increasing the probability for unverified information shared in scholarly works. The purpose of this study was to determine the extent of generative artificial intelligence usage in published nursing articles. The Dimensions database was used to collect articles with at least one appearance of words and phrases associated with generative artificial intelligence. These articles were then searched for words or phrases known to be disproportionately associated with large language model-based generative artificial intelligence. Several nouns, verbs, adverbs, and phrases had remarkable increases in appearance starting in 2023, suggesting use of generative artificial intelligence. Nurses, authors, reviewers, and editors will likely encounter generative artificial intelligence in their work. Although these sophisticated and emerging tools are promising, we must continue to work toward developing ways to verify accuracy of their content, develop policies that insist on transparent use, and safeguard consumers of the evidence they generate.

This study aimed to use wearable technology to predict the sleep quality of family caregivers of people with dementia among underrepresented groups. Caregivers of people with dementia often experience high levels of stress and poor sleep, and those from underrepresented communities face additional burdens, such as language barriers and cultural adaptation challenges. Participants, consisting of 29 dementia caregivers from underrepresented populations, wore smartwatches that tracked various physiological and behavioral markers, including stress level, heart rate, steps taken, sleep duration and stages, and overall daily wellness. The study spanned 529 days and analyzed data using 70 features. Three machine learning algorithms-random forest, k nearest neighbor, and XGBoost classifiers-were developed for this purpose. The random forest classifier was shown to be the most effective, boasting an area under the curve of 0.86, an F1 score of 0.87, and a precision of 0.84. Key findings revealed that factors such as wake-up stress, wake-up heart rate, sedentary seconds, total distance traveled, and sleep duration significantly correlated with the caregivers' sleep quality. This research highlights the potential of wearable technology in assessing and predicting sleep quality, offering a pathway to creating targeted support measures for dementia caregivers from underserved groups. The study suggests that such technology can be instrumental in enhancing the well-being of these caregivers across diverse populations.

Exploratory data analysis involves observing data in graphical formats before making any assumptions. If interesting relationships or patterns among variables are identified, hypotheses are developed for further testing. This study aimed to identify significant differences in the levels of exhaustion, resilience, sleep quality, and sleep hygiene according to the personal characteristics of middle-aged women transitioning into menopause or postmenopause through exploratory data analysis. A total of 200 women aged 44 to 55 years were recruited online in August 2023. Data were collected using valid instruments and analyzed through data visualization, pattern identification in the visualized data, and hypothesis establishment based on the visualized patterns. Hypotheses were tested through the independent-samples t test, analysis of variance, and the Kruskal-Wallis test. A total of 11 patterns and corresponding hypotheses were identified. According to the statistically supported pattern-based hypotheses, middle-aged women who were in their perimenopausal period perceived themselves as unhealthy, had professional occupations, and had the highest level of exhaustion and the lowest levels of resilience, sleep quality, and sleep hygiene. This study demonstrated that data visualization is an efficient way to explore relationships or patterns between data. Data visualization should be considered an informatics solution that can provide insight in the field of healthcare.

Today's healthcare landscape is becoming increasingly data-centric, with artificial intelligence and advanced computer algorithms becoming inextricably embedded in patient care. Although these technologies promise to make care more efficient and effective, they heighten the risk for unintended consequences. Using Walker and Avant's framework for concept analysis, we propose and explicate the emerging concept of iatrogenic data trauma, or ways in which the collection, storage, and use of sensitive and potentially stigmatizing patient data can cause harm. We conducted a careful and exhaustive review of traditional academic publications, as well as nontraditional digital sources to generate a rich and intersectional corpus of information pertaining to data justice, digital rights, and potential risks associated with the "datafication" of individuals. Using evidence synthesis and practical examples, we discuss how flawed data processes in healthcare settings can lead to data trauma among patients and explore how its presence can perpetuate health disparities, marginalization, loss of privacy, and breach of trust in patient-provider relationships. We discuss how this phenomenon arises and manifests across the healthcare continuum and is an important issue for professionals in multiple disciplines. We conclude by suggesting future opportunities for research through a trauma-informed lens.

Online learning has transitioned from being optional to a mandatory experience in nursing education. Consequently, it is crucial to understand nursing students' satisfaction and the factors influencing it to create and implement a successful online learning environment. This study aimed to examine the roles of system acceptance and community feeling in predicting nursing students' online learning satisfaction. The sample of the relational and cross-sectional study consisted of 451 nursing students studying online in the two universities in Western Turkey. Data were collected using the Personal Information Form, Online Learning Systems Acceptance, Community Feeling Scale, and Satisfaction Scale. A positive correlation was found between the perceived ease and benefit variables and satisfaction levels of nursing students in the study within the scope of online learning systems acceptance. A positive correlation was found between the actional and affective components of community feeling and satisfaction levels of nursing students in the study. Besides, the affective component was found to be the most significant factor in explaining satisfaction with online learning. The learning environment can be improved by increasing the diversity and interaction of nursing students with methods or instruments such as online collaborative learning approaches and online community building.

A nurse-led interprofessional clinic adopted the use of remote patient monitoring (RPM) for glucose monitoring to better serve their patient population of uninsured patients with uncontrolled diabetes. The adoption of the RPM system required an infrastructure design to connect multiple data points and adapt to the needs of the clinic's unique patient population for a seamless provider and patient experience. Implementation requirements were addressed in three phases: protocol adaptation, enrollment workflow, and clinic management of RPM patients.

Nursing shortages are a significant problem that affects healthcare access, outcomes, and costs and challenges the delivery of care in hospitals. The virtual nursing delivery model enables the provision of expert nursing care from a remote location, using technology such as audio/video communication, remote monitoring devices, and access to the electronic health record. However, little is known about the structure and processes supporting the implementation of virtual nursing in healthcare systems. This study examined the requirements for implementing a virtual nursing care team by characterizing the structure and processes of virtual nursing, using the Donabedian framework. The study conducted an observational and qualitative evaluation of a virtual nursing care team at a major Southeastern health center in the United States. The study found that key aspects for implementing a virtual nursing program include the number of available virtual nurses per shift, the availability of appropriate virtual nursing equipment, the physical layout of the virtual nursing center, the training of virtual nursing nurses on best practices of virtual encounters, simultaneous use of electronic health record, creation, and training of nurses on policies and procedures such as escalation of technical issues, and available support resources for problem resolution. The study provides valuable insights into the structure and processes of virtual nursing care that can be used to improve healthcare delivery and address nursing shortages.