Cin-Computers Informatics Nursing最新文献

The ubiquity of electronic health records and health information exchanges has generated abundant administrative and clinical healthcare data. The vastness of this rich dataset presents an opportunity for emerging technologies (eg, artificial intelligence and machine learning) to assist clinicians and healthcare administrators with decision-making, predictive analytics, and more. Multiple studies have cited various applications for artificial intelligence and machine learning in nursing. However, what is unknown in the nursing discipline is that while greater than 90% of machine-learning implementations use a model-centric strategy, a fundamental change is occurring. Because of the limitations of this approach, the industry is beginning to pivot toward data-centric artificial intelligence. Nurses should be aware of the differences, including how each approach affects their engagement in designing human-intelligent-like technologies and their data usage, especially regarding electronic health records. Using the Norris Concept Clarification method, this article elucidates the data-centric machine learning concept for nursing. This is accomplished by (1) exploring the concept's origins in the data and computer science disciplines; (2) differentiating data- versus model-centric machine learning approaches, including introducing the machine-learning operation life cycle and process; and (3) explaining the advantages of the data-centric phenomenon, especially concerning nurses' engagement in technological design and proper data usage.

Keeping students engaged and motivated during online or class discussion may be challenging. Artificial intelligence has potential to facilitate active learning by enhancing student engagement, motivation, and learning outcomes. The purpose of this study was to develop, test usability of, and explore undergraduate nursing students' perceptions toward the Artificial Intelligence-Teaching Assistant System. The system was developed based on three main components: machine tutor intelligence, a graphical user interface, and a communication connector. They were included in the system to support contextual machine tutoring. A field-testing study design, a mixed-method approach, was utilized with questionnaires and focus group interview. Twenty-one undergraduate nursing students participated in this study, and they interacted with the system for 2 hours following the required activity checklist. The students completed the validated usability questionnaires and then participated in the focus group interview. Descriptive statistics were used to analyze quantitative data, and thematic analysis was used to analyze qualitative data from the focus group interviews. The results showed that the Artificial Intelligence-Teaching Assistant System was user-friendly. Four main themes emerged, namely, functionality, feasibility, artificial unintelligence, and suggested learning modality. However, Artificial Intelligence-Teaching Assistant System functions, user interface, and content can be improved before full implementation.

We are in a booming era of artificial intelligence, particularly with the increased availability of technologies that can help generate content, such as ChatGPT. Healthcare institutions are discussing or have started utilizing these innovative technologies within their workflow. Major electronic health record vendors have begun to leverage large language models to process and analyze vast amounts of clinical natural language text, performing a wide range of tasks in healthcare settings to help alleviate clinicians' burden. Although such technologies can be helpful in applications such as patient education, drafting responses to patient questions and emails, medical record summarization, and medical research facilitation, there are concerns about the tools' readiness for use within the healthcare domain and acceptance by the current workforce. The goal of this article is to provide nurses with an understanding of the currently available foundation models and artificial intelligence tools, enabling them to evaluate the need for such tools and assess how they can impact current clinical practice. This will help nurses efficiently assess, implement, and evaluate these tools to ensure these technologies are ethically and effectively integrated into healthcare systems, while also rigorously monitoring their performance and impact on patient care.

As of now, a model for predicting the survival of patients with out-of-hospital cardiac arrest has not been established. This study aimed to develop a model for identifying predictors of survival over time in patients with out-of-hospital cardiac arrest during their stay in the emergency department, using ensemble-based machine learning. A total of 26 013 patients from the Korean nationwide out-of-hospital cardiac arrest registry were enrolled between January 1 and December 31, 2019. Our model, comprising 38 variables, was developed using the Survival Quilts model to improve predictive performance. We found that changes in important variables of patients with out-of-hospital cardiac arrest were observed 10 minutes after arrival at the emergency department. The important score of the predictors showed that the influence of patient age decreased, moving from the highest rank to the fifth. In contrast, the significance of reperfusion attempts increased, moving from the fourth to the highest rank. Our research suggests that the ensemble-based machine learning model, particularly the Survival Quilts, offers a promising approach for predicting survival in patients with out-of-hospital cardiac arrest. The Survival Quilts model may potentially assist emergency department staff in making informed decisions quickly, reducing preventable deaths.

As the awareness on violent deaths from guns, drugs, and suicides emerges as a public health crisis in the United States, attempts to prevent injury and mortality through nursing research are critical. The National Violent Death Reporting System provides public health surveillance of US violent deaths; however, understanding the National Violent Death Reporting System's research utility is limited. The purpose of our rapid review of the 2019-2023 literature was to understand to what extent artificial intelligence methods are being used with the National Violent Death Reporting System. We identified 16 National Violent Death Reporting System artificial intelligence studies, with more than half published after 2020. The text-rich content of National Violent Death Reporting System enabled researchers to center their artificial intelligence approaches mostly on natural language processing (50%) or natural language processing and machine learning (37%). Significant heterogeneity in approaches, techniques, and processes was noted across the studies, with critical methods information often lacking. The aims and focus of National Violent Death Reporting System studies were homogeneous and mostly examined suicide among nurses and older adults. Our findings suggested that artificial intelligence is a promising approach to the National Violent Death Reporting System data with significant untapped potential in its use. Artificial intelligence may prove to be a powerful tool enabling nursing scholars and practitioners to reduce the number of preventable, violent deaths.

The last-minute cancellation of surgeries profoundly affects patients and their families. This research aimed to forecast these cancellations using EMR data and meteorological conditions at the time of the appointment, using a machine learning approach. We retrospectively gathered medical data from 13 440 pediatric patients slated for surgery from 2018 to 2021. Following data preprocessing, we utilized random forests, logistic regression, linear support vector machines, gradient boosting trees, and extreme gradient boosting trees to predict these abrupt cancellations. The efficacy of these models was assessed through performance metrics. The analysis revealed that key factors influencing last-minute cancellations included the impact of the coronavirus disease 2019 pandemic, average wind speed, average rainfall, preanesthetic assessments, and patient age. The extreme gradient boosting algorithm outperformed other models in predicting cancellations, boasting an area under the curve value of 0.923 and an accuracy of 0.841. This algorithm yielded superior sensitivity (0.840), precision (0.837), and F1 score (0.838) relative to the other models. These insights underscore the potential of machine learning, informed by EMRs and meteorological data, in forecasting last-minute surgical cancellations. The extreme gradient boosting algorithm holds promise for clinical deployment to curtail healthcare expenses and avert adverse patient-family experiences.

New nurses must acquire accurate knowledge of medication administration, as it directly affects patient safety. This study aimed to develop a microlearning-based self-directed learning chatbot on medication administration for novice nurses. Furthermore, the study had the objective of evaluating the chatbot feasibility. The chatbot covered two main topics: medication administration processes and drug-specific management, along with 21 subtopics. Fifty-eight newly hired nurses on standby were asked to use the chatbot over a 2-week period. Moreover, we evaluated the chatbot's feasibility through a survey that gauged changes in their confidence in medication administration knowledge, intrinsic learning motivation, satisfaction with the chatbot's learning content, and usability. After using the chatbot, participants' confidence in medication administration knowledge significantly improved in all topics ( P < .001) except "Understanding a concept of 5Right" ( P = .077). Their intrinsic learning motivation, satisfaction with the learning content, and usability scored above 5 out of 7 in all subdomains, except for pressure/tension (mean, 2.12; median, 1.90). They scored highest on ease of learning (mean, 6.69; median, 7.00). A microlearning-based chatbot can help new nurses improve their knowledge of medication administration through self-directed learning.

This study aimed to identify the main themes from exit interviews of adult patients with type 2 diabetes after completion of a diabetes education program. Eighteen participants with type 2 diabetes completed an exit interview regarding their program experience and satisfaction. Semistructured interview questions were used, and the interviews were auto-recorded. The interview transcripts were preprocessed and analyzed using four natural language processing-based text-mining techniques. The top 30 words from the term frequency and term frequency-inverse document frequency each were derived. In the N-gram analysis, the connection strength of "diabetes" and "education" was the highest, and the simultaneous connectivity of word chains ranged from a maximum of seven words to a minimum of two words. Based on the CONvergence of iteration CORrelation (CONCOR) analysis, three clusters were generated, and each cluster was named as follows: participation in a diabetes education program to control blood glucose, exercise, and use of digital devices. This study using text mining proposes a new and useful approach to visualize data to develop patient-centered diabetes education.