Cin-Computers Informatics Nursing最新文献

Fall is a common adverse event among older adults. This study aimed to identify essential fall factors and develop a machine learning-based prediction model to predict the fall risk category among community-dwelling older adults, leading to earlier intervention and better outcomes. Three prediction models (logistic regression, random forest, and naive Bayes) were constructed and evaluated. A total of 459 people were involved, including 156 participants (34.0%) with high fall risk. Seven independent predictors (frail status, age, smoking, heart attack, cerebrovascular disease, arthritis, and osteoporosis) were selected to develop the models. Among the three machine learning models, the logistic regression model had the best model fit, with the highest area under the curve (0.856) and accuracy (0.797) and sensitivity (0.735) in the test set. The logistic regression model had excellent discrimination, calibration, and clinical decision-making ability, which could aid in accurately identifying the high-risk groups and taking early intervention with the model.

This study aimed to examine if exposure to undergraduate nursing informatics educational modalities (ie, lecture, laboratory, and clinical experiences) made a difference in the acceptance of information and communication technologies among nurses in the practice setting. Also, to examine if there was a relationship between selected demographic characteristics and nurses' acceptance of information and communication technologies, a cross-sectional design was used for this study. The Technology Acceptance Model was the theoretical framework for this study. The modified Nursing Acceptance Survey was used to collect data based on the Technology Acceptance Model. The results indicated that exposure to undergraduate informatics education significantly influenced nurses' acceptance of information and communication technologies. The results identified laboratory and clinical as educational modalities influencing nurses' acceptance of information and communication technologies. Demographic characteristics have no statistically significant relationship to nurses' acceptance of information and communication technologies. The results showed that undergraduate informatics education statistically influences nurses' acceptance of information and communication technologies. Findings provide insight into that undergraduate informatics education is important for accepting information and communication technologies among nurses in the practice setting. Also, the findings recognized laboratory and clinical experiences as effective learning modalities for accepting information and communication technologies.

Background and objectives: Mental health disorders, including anxiety and depression, are the leading causes of global health-related burden and have increased dramatically since the 1990s. Delivering mental healthcare using artificial intelligence chatbots may be one option for closing the gaps in mental healthcare access. The overall aim of this scoping review was to describe the use, efficacy, and advantages/disadvantages of using an artificial intelligence chatbot for mental healthcare (stress, anxiety, depression).

Methods: PubMed, PsycINFO, CINAHL, and Web of Science databases were searched. When possible, Medical Subject Headings terms were searched in combination with keywords. Two independent reviewers reviewed a total of 5768 abstracts.

Results: Fifty-four articles were chosen for further review, with 10 articles included in the final analysis. Regarding quality assessment, the overall quality of the evidence was lower than expected. Overall, most studies showed positive trends in improving anxiety, stress, and depression.

Discussion: Overall, using an artificial intelligence chatbot for mental health has some promising effects. However, many studies were done using rudimentary versions of artificial intelligence chatbots. In addition, lack of guardrails and privacy issues were identified. More research is needed to determine the effectiveness of artificial intelligence chatbots and to describe undesirable effects.

Nurses faced numerous challenges during the pandemic, particularly with the increased burden of electronic documentation. Surges in patient volume and visits led to rapid changes in nursing documentation, prompting diverse responses from regulatory and healthcare organizations. Nurses expressed safety concerns and struggled with changes, calling for national standards and regulatory support. Policy relaxations, such as the 1135 Waiver, sparked debate on the future of nursing care plan documentation. Using mixed-methods exploratory design, the study identified modifications of nursing documentation during crises, commonalities in documentation burden reduction for applicability beyond pandemics, and consensus on the definition of "surge." Documentation patterns were assessed from February to November 2022, involving 175 North American nurse leaders and informaticists. Data analysis included descriptive statistics, thematic analysis, and Pearson correlation coefficient. Significant differences were found between rural and urban settings ( P = .02), with urban areas showing higher odds of changes to care plans (odds ratio, 4.889; 95% confidence interval, 1.27-18.78). Key findings highlighted the persistence of postcrisis documentation changes and varied definitions of surge criteria based on organizational leadership, policy, and mandates. The study yielded insights for modifying documentation, offering policy recommendations, and emphasizing ongoing collaboration and evidence-based approaches for future nursing practices.

The integration of artificial intelligence such as ChatGPT into educational frameworks marks a pivotal transformation in teaching. This quasi-experimental study, conducted in September 2023, aimed to evaluate the effects of artificial intelligence-assisted learning on nursing students' ethical decision-making and clinical reasoning. A total of 99 nursing students enrolled in a pediatric nursing course were randomly divided into two groups: an experimental group that utilized ChatGPT and a control group that used traditional textbooks. The Mann-Whitney U test was employed to assess differences between the groups in two primary outcomes: ( a ) ethical standards, focusing on the understanding and applying ethical principles, and ( b ) nursing processes, emphasizing critical thinking skills and integrating evidence-based knowledge. The control group outperformed the experimental group in ethical standards and demonstrated better clinical reasoning in nursing processes. Reflective essays revealed that the experimental group reported lower reliability but higher time efficiency. Despite artificial intelligence's ability to offer diverse perspectives, the findings highlight that educators must supplement artificial intelligence technology with strategies that enhance critical thinking, careful data selection, and source verification. This study suggests a hybrid educational approach combining artificial intelligence with traditional learning methods to bolster nursing students' decision-making processes and clinical reasoning skills.

Patient education and self-management are essential for patients with liver cirrhosis. Based on Fisher and Fisher's Information-Motivation-Behavior Skills model, a Cirrhosis Care App was developed to support the education and self-management of these patients. To evaluate the effectiveness of the application, a randomized controlled trial was conducted with patients having liver cirrhosis who were being followed up in the outpatient area of ​​a medical center in Taiwan. The experimental group used the app for 1 month, whereas a control group continued to receive conventional patient education. A pretest and posttest questionnaire was used to evaluate the app's effectiveness in improving the knowledge and practice of self-care. In addition, a questionnaire was developed based on the Technology Acceptance Model to understand satisfaction with the app. Results showed that following the implementation of the Cirrhosis Care App, patients' self-care knowledge and ability to promote self-care practice improved. User satisfaction with the app was measured and reflected in its frequency of use. This study confirmed that the Cirrhosis Care App, based on the Information-Motivation-Behavior Skills model, can improve patient knowledge and self-care practice and be actively promoted to benefit patients with cirrhosis.

The innate complexity of medical topics often makes it challenging to produce educational content for the public. Although there are resources available to help authors appraise the complexity of their content, there are woefully few resources available to help authors reduce that complexity after it occurs. In this case study, we evaluate using ChatGPT to reduce the complex language used in health-related educational materials. ChatGPT adapted content from the SmartSHOTS mobile application, which is geared toward caregivers of children aged 0 to 24 months. SmartSHOTS helps reduce barriers and improve adherence to vaccination schedules. ChatGPT reduced complex sentence structure and rewrote content to align with a third-grade reading level. Furthermore, using ChatGPT to edit content already written removes the potential for unnoticed, artificial intelligence-produced inaccuracies. As an editorial tool, ChatGPT was effective, efficient, and free to use. This article discusses the potential of ChatGPT as an effective, time-efficient, and open-source method for editing health-related educational materials to reflect a comprehendible reading level.