RESUMEN
BACKGROUND: Serious games have emerged as an innovative educational strategy with the potential to significantly enhance the quality and effectiveness of cardiopulmonary resuscitation (CPR) training. Despite their promise, there remains a degree of controversy when comparing the advantages of serious games with traditional CPR training methods. This study seeks to provide a comprehensive assessment of the impact of serious games on CPR training and education by systematically analyzing the results of previous research. OBJECTIVE: This study aimed to assess the effect of serious games on CPR training and education by summarizing and pooling the results of previous studies. METHODS: We conducted a thorough and systematic search across 9 prominent web-based databases, encompassing the period from the inception of these databases until April 1, 2023. The databases included in our search were PubMed, Cochrane Library, Wiley Online Library, EBSCO (PsycInfo), SpringerLink, Chinese Biology Medicine Disc, Vip Journal Integration Platform, Wanfang Database, and Chinese National Knowledge Infrastructure. The studies selected adhered to the following criteria: (1) being a randomized controlled trial comparing serious games and traditional methods for CPR training; (2) having participants aged 12 years or older in CPR; (3) having an experimental group using serious games and a control group using nongame methods for CPR instruction; and (4) having outcomes including theoretical and skill assessments, compression depth, and rate. The Cochrane risk of bias assessment tool was used to evaluate the risk of bias. Data analysis was performed using RevMan (version 5.3; Cochrane Training), and mean differences (MDs) and standardized mean differences (SMDs) with 95% CIs were used to calculate continuous variables. RESULTS: A total of 9 articles were included, involving 791 study participants, of whom 395 in the experimental group taught CPR training using serious games and 396 in the control group taught CPR training using traditional methods. The results of our meta-analysis indicate that the use of serious games in CPR training yields outcomes that are comparable in effectiveness to traditional training methods across several key areas. Specifically, serious games demonstrated equivalence to traditional formats in theory assessment (SMD -0.22, 95% CI - 0.96 to 0.51; P=.55), skill assessment (SMD -0.49, 95% CI -1.52 to 0.55; P=.36), compression depth (MD -3.17, 95% CI -0.18 to 6.53; P=.06), and compression rate (MD -0.20, 95% CI -7.29 to 6.89; P=.96). CONCLUSIONS: In summary, serious games offer a viable and effective CPR education approach, yielding results comparable to traditional formats. This modality is a valuable addition to CPR training methodologies. However, caution is warranted in interpreting these findings due to limited controlled trials, small sample sizes, and low-quality meta-analyzed evidence.
RESUMEN
Background: Pressure injury has always been a focus and difficulty of nursing. With the development of nursing informatization, a large amount of structured and unstructured data has been generated, and it is difficult for traditional methods to utilize these data. With the intersection of artificial intelligence and nursing, it has become a new trend to apply machine learning algorithms to build pressure injury prediction models to manage pressure injuries. However, there is no evidence on the effectiveness of the method and which of a large number of algorithms for machine learning is more applicable to pressure injuries. Objective: This review aims to systematically synthesize existing evidence to determine the effectiveness of applying machine learning algorithms for pressure injury management, to further evaluate and compare pressure injury prediction models constructed by numerous machine learning algorithms, and to derive evidence for the best algorithms for predicting and managing pressure injuries. Design: Systematic review and network meta-analysis. Methods: A systematic electronic search was conducted in the EBSCO, Embase, PubMed, and Web of Science databases. We included all retrospective diagnostic accuracy trials and prospective diagnostic accuracy trials constructing a predictive model by machine learning for pressure injuries up to December 2021. Two review authors independently selected relevant studies and extracted data using the Cochrane handbook for systematic reviews of diagnostic test accuracy. The network meta-analysis was conducted using statistical software R and STATA. The certainty of the evidence was rated using the QUADAS-2 tool. Result: Twenty-five clinical diagnostic trials with a total of 237397 participants were identified in this review. The results of our study revealed that pressure injury machine learning models can effectively predict these injuries. Combining the algorithms separately yields the main results: decision trees (sensitivity: 0.66, 95% CI: 0.42 to 0.84, specificity: 0.90, 95% CI: 0.78 to 0.96, diagnostic odds ratio [DOR]: 18, 95% CI: 7 to 49, AUC: 0.88, 95% CI: 0.85 to 0.91), logistic regression (sensitivity: 0.71, 95% CI: 0.60 to 0.80, specificity: 0.83, 95% CI: 0.75 to 0.89, DOR: 12, 95% CI: 9 to 17, AUC: 0.84, 95% CI: 0.81 to 0.87), neural networks (sensitivity: 0.73, 95% CI: 0.55 to 0.86, specificity: 0.78, 95% CI: 0.65 to 0.87, DOR: 9, 95% CI: 5 to 19, AUC: 0.82, 95% CI: 0.79 to 0.85), random forests (sensitivity: 0.72, 95% CI: 0.26 to 0.95, specificity: 0.96, 95% CI: 0.80 to 0.99, DOR: 56, 95% CI: 3 to 1258, AUC: 0.95, 95% CI: 0.93 to 0.97), support vector machines (sensitivity: 0.81, 95% CI: 0.69 to 0.90, specificity: 0.81, 95% CI: 0.59 to 0.93, DOR: 19, 95% CI: 6 to 54, AUC: 0.88, 95% CI: 0.85 to 0.90). According to the analysis of ROC and AUC values, random forest is the best algorithm for the prediction model of pressure injury. Conclusions: This review revealed that machine learning algorithms are generally effective in predicting pressure injuries, and after data merging, the random forest algorithm is the best algorithm for pressure injury prediction. Further well-designed diagnostic controlled trials are recommended to strengthen the current evidence. Registration number PROSPERO: CRD42021276993.
RESUMEN
BACKGROUND: One of the major challenges in nursing and medical education is to foster the critical thinking ability and autonomous learning ability for students. But the effect of different teaching methods on these abilities of nursing or medical students has not been conclusive, and few studies have directly compared the differences in the effects of different teaching methods. As a result, it is necessary for students to evaluate the impact of different teaching methods on critical thinking ability and autonomous learning ability. METHODS: A systematic search will be performed using Chinese National Knowledge Infrastructure, Wanfang Data (Chinese database), VIP Information (Chinese database), Chinese Biomedical Literature, and English language databases, including PubMed and Embase, Web of Science, CINAHL Complete (EBSCO0, Cochrane library to identify relevant studies from inception to July 10, 2020. We will include random controlled trials that evaluated the different teaching methods. The Quality Assessment of Diagnostic Accuracy Studies 2 quality assessment tool will be used to assess the risk of bias in each study. Standard pairwise meta-analysis and network meta-analysis will be performed using STATA V.12.0, MetaDiSc 1.40, and R 3.4.1 software to compare the diagnostic efficacy of different hormonal biomarkers. RESULTS: The results of this study will be published in a peer-reviewed journal. CONCLUSION: This study will summarize the direct and indirect evidence to determine the effectiveness of different teaching methods for medical or nursing students and attempt to find the most effective teaching method. ETHICS AND DISSEMINATION: Ethics approval and patient consent are not required, because this study is a meta-analysis based on published studies. INPLASY REGISTRATION NUMBER: INPLASY202070017.