MATERIALS AND METHODS: Randomized controlled comparing MIE versus OE were searched from PubMed and other electronic databases between January 1991 and March 2019. Thirteen outcome variables were analyzed. Random effects model was used to calculate the effect size. The meta-analysis was prepared in accordance with PRISMA guidelines.
RESULTS: Four randomized controlled trials totaling 569 patients were analyzed. For MIE, there was a significantly reduction of 67% in the odds of pulmonary complications. For operating time, MIE was nonsignificantly 29 minutes longer. MIE was associated with nonsignificantly less blood loss of 443.98 mL. There was nonsignificant 60% reduction in the odds of total complications and 51% reduction in the odds of medical complications favoring MIE group. For delayed gastric emptying, there was a nonsignificant reduction of 75% in the odds ratio favoring the MIE group. For postoperative anastomotic leak, there was a nonsignificant increase of 48% in the odds ratio for MIE group. For gastric necrosis, chylothorax, reintervention and 30-day mortality, no difference was observed for both groups. There was a nonsignificant reduction in the length of hospital stay of 7.98 days and intensive care unit stay of 2.7 days favoring MIE.
CONCLUSIONS: MIE seems to be superior to OE for only pulmonary complications. All the other perioperative variables were comparable however, the trend is favoring the MIE. Therefore, the routine use of MIE presently may only be justifiable in high volume esophagogastric units.
METHODS: This study used available under-five nutritional secondary data from the Demographic and Health Surveys performed in sub-Saharan African countries. The research used bagging, boosting, and voting algorithms, such as random forest, decision tree, eXtreme Gradient Boosting, and k-nearest neighbors machine learning methods, to generate the MVBHE model.
RESULTS: We evaluated the model performances in contrast to each other using different measures, including accuracy, precision, recall, and the F1 score. The results of the experiment showed that the MVBHE model (96%) was better at predicting malnutrition than the random forest (81%), decision tree (60%), eXtreme Gradient Boosting (79%), and k-nearest neighbors (74%).
CONCLUSIONS: The random forest algorithm demonstrated the highest prediction accuracy (81%) compared with the decision tree, eXtreme Gradient Boosting, and k-nearest neighbors algorithms. The accuracy was then enhanced to 96% using the MVBHE model. The MVBHE model is recommended by the present study as the best way to predict malnutrition in under-five children.