Purpose:To analyze the AI research in the field of nursing, to explore the current situation, hot topics, and prospects of AI research in the field of nursing, and to provide a reference for researchers to carry out related studies.Methods: We used the VOSviewer 1.6.17, SciMAT, and CiteSpace 5.8.R3 to generate visual cooperation network maps for the country, organizations, authors, citations, and keywords and perform burst detection, theme evolution, and so forth. Findings: A total of 9318 articles were obtained from the Web of Science Core Collection database. Four hundred and thirty-one AI research related to the field of nursing was published by 855 institutions from 54 countries. CIN-Computers Informatics Nursing was the top productive journal. The United States was the dominant country. The transnational cooperation between authors from developed countries was closer than that between authors from developing countries. The main hot topics included nurse rostering, nursing diagnosis, nursing decision support, disease risk factor prediction, nursing big data management, expert system, support vector machine, decision tree, deep learning, natural language processing, and nursing education. Machine learning represented one of the cutting-edge and most applicable branches of artificial intelligence in the field of nursing, and deep learning was the hottest technology among many machine learning methods in recent years. One of the most cited papers was published by Burke in 2004 and cited 500 times, which critically evaluated AI methods to deal with nurse scheduling problems. Conclusions:Although AI has been paid more and more attention to the field of nursing, there is still a lack of high-yielding authors who have been engaged in this field for a long time. Most of the high contribution authors and institutions came from developed countries; therefore, more transnational and multi-disciplinary cooperation is needed to promote the development of AI in the nursing field. This bibliometric analysis not only provided a comprehensive overview to help researchers to understand the important articles, journals, potential collaborators, and institutions in this field but also analyzed the history, hot spots, and future trends of the research topic to provide inspiration for researchers to choose research directions.
Background: Many rare events meta-analyses of randomized controlled trials (RCTs) have lower statistical power, and real-world evidence (RWE) is becoming widely recognized as a valuable source of evidence. The purpose of this study is to investigate methods for including RWE in a rare events meta-analysis of RCTs and the impact on the level of uncertainty around the estimates. Methods: Four methods for the inclusion of RWE in evidence synthesis were investigated by applying them to two previously published rare events meta-analyses: the naïve data synthesis (NDS), the design-adjusted synthesis (DAS), the use of RWE as prior information (RPI), and the three-level hierarchical models (THMs). We gauged the effect of the inclusion of RWE by varying the degree of confidence placed in RWE. Results: This study showed that the inclusion of RWE in a rare events meta-analysis of RCTs could increase the precision of the estimates, but this depended on the method of inclusion and the level of confidence placed in RWE. NDS cannot consider the bias of RWE, and its results may be misleading. DAS resulted in stable estimates for the two examples, regardless of whether we placed high- or low-level confidence in RWE. The results of the RPI approach were sensitive to the confidence level placed in RWE. The THM was effective in allowing for accommodating differences between study types, while it had a conservative result compared with other methods. Conclusion: The inclusion of RWE in a rare events meta-analysis of RCTs could increase the level of certainty of the estimates and enhance the decision-making process. DAS might be appropriate for inclusion of RWE in a rare event meta-analysis of RCTs, but further evaluation in different scenarios of empirical or simulation studies is still warranted.
Background: Danhong injection is widely used for treating ischemic stroke in China. However, its effects on ischemic stroke patients when given along with Western medicines (i.e., the add-on effect) were not well-established.Methods: We searched PubMed, Embase, Cochrane Central Register of Controlled Trials (CENTRAL), and three Chinese databases from inception to 20 July 2020 to identify randomized controlled trials (RCTs) that assessed the effects of Danhong injection as add-on therapy in patients with ischemic stroke. Pairs of trained reviewers independently screened for eligible studies, assessed risk of bias, and extracted the data. The outcomes were the National Institutes of Health Stroke Scale Score (NIHSS), Barthel index, activities of daily living (ADL), total cholesterol, and homocysteine (Hcy).Results: Sixty-seven RCTs of 6594 patients with varying risk of bias were included. Compared with Western medicine alone, the addition of Danhong injection to Western medicine significantly lowered the NIHSS score (45 RCTs with 4565 patients; MD −4.21, 95% CI −4.96 to −3.46), total cholesterol (10 trials with 1019 patients; MD −1.14 mmol/L, 95% CI −1.57 to −0.72), and Hcy (four trials with 392 patients; MD −3.54 μmol/L, 95% CI −4.38 to −2.07). The addition of Danhong also increased the Barthel index (14 trials with 1270 patients; MD 8.71, 95% CI 3.68–13.74) and ADL (12 trials with 1114 patients; MD 14.48, 95% CI 9.04–19.92) scores. Subgroup analyses showed differential effects in the average cerebral blood flow rate by mean age of patients (<60 years: MD 0.74 cm/s, 95% CI 0.29–1.19; ≥60 years: MD 4.09 cm/s, 95% CI 2.02–6.16; interaction p = 0.002) and the NIHSS score by type of baseline Western medicines (interaction p < 0.00001).Conclusion: The addition of Danhong injection to Western medicine may improve neurological function, self-care ability, and blood lipid level of ischemic stroke patients. However, given most included trials with unclear risk of bias, current evidence is not definitive, and more carefully designed and conducted trials are warranted to confirm our findings.Systematic Review Registration: [https://www.crd.york.ac.uk/PROSPERO/], identifier [CRD42022298628].
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.