OBJECTIVE: This study aims to provide general information on the trends of the studies on JE as well as an overall perspective on the development of this topic by utilising a bibliometric analytic approach.
METHOD: A bibliometric evaluation was conducted in the JE field since the first publication was documented in the Scopus database. The information retrieved examines 1572 JE papers from a variety of perspectives, including citation and publishing metrics.
RESULTS: The research results pinpoint the most productive countries, universities, journals, authors, and JE articles. The study also classified the most important themes and offered some recommendations for further research.
CONCLUSION: The study provided a snapshot of JE patterns and trajectories from 1993 to 2020, which can help academics and practitioners figure out the pattern and direction of future research. To the best of our knowledge, no other study examines the bibliographic data on JE and thus this work is one of the first contributions to the literature.
OBJECTIVE: The aim of this systematic review and meta-analysis is to compare the effectiveness of amiodarone, dexmedetomidine and magnesium in preventing JET following congenital heart surgery.
METHODS: This meta-analysis was conducted according to the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) statement, where 11 electronic databases were searched from date of inception to August 2020. The incidence of JET was calculated with the relative risk of 95% confidence interval (CI). Quality assessment of the included studies was assessed using the Consolidated Standards of Reporting Trials (CONSORT) 2010 statement.
RESULTS: Eleven studies met the predetermined inclusion criteria and were included in this meta-analysis. Amiodarone, dexmedetomidine and magnesium significantly reduced the incidence of postoperative JET [Amiodarone: risk ratio 0.34; I2= 0%; Z=3.66 (P=0.0002); 95% CI 0.19-0.60. Dexmedetomidine: risk ratio 0.34; I2= 0%; Z=4.77 (P<0.00001); 95% CI 0.21-0.52. Magnesium: risk ratio 0.50; I2= 24%; Z=5.08 (P<0.00001); 95% CI 0.39-0.66].
CONCLUSION: All three drugs show promise in reducing the incidence of JET. Our systematic review found that dexmedetomidine is better in reducing the length of ICU stays as well as mortality. In addition, dexmedetomidine also has the least pronounced side effects among the three. However, it should be noted that this conclusion was derived from studies with small sample sizes. Therefore, dexmedetomidine may be considered as the drug of choice for preventing JET.
METHODS: MEDLINE and Embase databases were searched from inception up to September 2019 to identify all studies that compared the predictive performance of cystatin C- and/or creatinine-based eGFR in predicting the clearance of vancomycin. The prediction errors (PEs) (the value of eGFR equations minus vancomycin clearance) were quantified for each equation and were pooled using a random-effects model. The root mean squared errors were also quantified to provide a metric for imprecision.
RESULTS: This meta-analysis included evaluations of seven different cystatin C- and creatinine-based eGFR equations in total from 26 studies and 1,234 patients. The mean PE (MPE) for cystatin C-based eGFR was 4.378 mL min-1 (95% confidence interval [CI], -29.425, 38.181), while the creatinine-based eGFR provided an MPE of 27.617 mL min-1 (95% CI, 8.675, 46.560) in predicting clearance of vancomycin. This indicates the presence of unbiased results in vancomycin clearance prediction by the cystatin C-based eGFR equations. Meanwhile, creatinine-based eGFR equations demonstrated a statistically significant positive bias in vancomycin clearance prediction.
CONCLUSION: Cystatin C-based eGFR equations are better than creatinine-based eGFR equations in predicting the clearance of vancomycin. This suggests that utilising cystatin C-based eGFR equations could result in better accuracy and precision to predict vancomycin pharmacokinetic parameters.
METHODS: A convolutional auto-encoder (CAE) based nonlinear compression structure is implemented to reduce the signal size of arrhythmic beats. Long-short term memory (LSTM) classifiers are employed to automatically recognize arrhythmias using ECG features, which are deeply coded with the CAE network.
RESULTS: Based upon the coded ECG signals, both storage requirement and classification time were considerably reduced. In experimental studies conducted with the MIT-BIH arrhythmia database, ECG signals were compressed by an average 0.70% percentage root mean square difference (PRD) rate, and an accuracy of over 99.0% was observed.
CONCLUSIONS: One of the significant contributions of this study is that the proposed approach can significantly reduce time duration when using LSTM networks for data analysis. Thus, a novel and effective approach was proposed for both ECG signal compression, and their high-performance automatic recognition, with very low computational cost.
METHODS: We first tested ten traditional machine learning algorithms, and then the three-best performing algorithms (three types of SVM) were used in the rest of the study. To improve the performance of these algorithms, a data preprocessing with normalization was carried out. Moreover, a genetic algorithm and particle swarm optimization, coupled with stratified 10-fold cross-validation, were used twice: for optimization of classifier parameters and for parallel selection of features.
RESULTS: The presented approach enhanced the performance of all traditional machine learning algorithms used in this study. We also introduced a new optimization technique called N2Genetic optimizer (a new genetic training). Our experiments demonstrated that N2Genetic-nuSVM provided the accuracy of 93.08% and F1-score of 91.51% when predicting CAD outcomes among the patients included in a well-known Z-Alizadeh Sani dataset. These results are competitive and comparable to the best results in the field.
CONCLUSIONS: We showed that machine-learning techniques optimized by the proposed approach, can lead to highly accurate models intended for both clinical and research use.