Objective:To evaluate the effects of high versus low positive end-expiratory pressure (PEEP) for lung-protective ventilation strategies through a meta analysis.Methods:Web of Science, the Cochrane Library, PubMed, EBSCO, Embase, Medline, CNKI, Wanfang data and VIP data were searched from inception to July 15, 2019 for prospective randomized controlled trials involving comparing the effects of ventilation with different levels of PEEP for lung-protective ventilation strategies during operation.Evaluation indexes included: incidence of postoperative pulmonary complications and other complications, and incidence of intraoperative hypotension.After two reviewers independently identified the literature and conducted data extraction and quality evaluation, RevMan 5.3 software was used to analyze the data.Results:Eight prospective randomized controlled trials involving 3 324 participants were included.Compared with low PEEP group, no significant change was found in the incidence of postoperative pulmonary complications and other complications ( P>0.05), and the incidence of intraoperative hypotension was significantly increased in high PEEP group ( P<0.05). Conclusion:The effect of lung-protective ventilation strategy with high PEEP is not superior to that with low PEEP.

Objective To develop a predictive model for postoperative acute kidney injury(AKI)in elderly patients using machine learning methods.Methods The preoperative information and postopera-tive follow-up information of elderly patients who underwent surgery from June 2019 to July 2020 were col-lected,and the laboratory examination results were extracted.A total of 115 preoperative variables were in-cluded.A model of postoperative AKI was constructed using five methods:extreme gradient boosting(XGB),gradient boosting machine(GBM),random forest(RF),support vector machine(SVM),and elastic net logistic regression(ELA).The performance of the model was evaluated using area under the re-ceiver operating characteristic curve(AUROC),area under the precision recall curve(AUPRC),and Brier score.To simplify the model for clinical application,the original model was obtained and some varia-bles with low correlation were removed,and the model was evaluated again using the above method.Results This study ultimately included 5 929 elderly patients,3 359 males(56.7％)and 2 570 females(43.3％),aged 65-99 years.Among them,154 patients(2.6％)experienced postoperative AKI.Among the prediction models constructed using five machine learning methods,XGB has the highest AUROC and AU-PRC,with values of 0.798(95％CI 0.705-0.888)and 0.230(95％CI 0.079-0.374),respectively.Its Brier score is the lowest among all models,the score is 0.023(95％CI 0.014-0.029).After simplifying the XGB model,72 variables were retained.The AUROC of the simplified model was 0.790(95％CI 0.711-0.861),slightly lower than that of the original model.The AUPRC was 0.176(95％CI 0.070-0.313),and the Brier score was 0.024(95％CI 0.017-0.033),and there was no significant statistical difference,indicating that there was no significant difference in the predictive ability of the simplified model compared to the original model.Conclusion Among the five machine learning methods used to construct postoperative AKI prediction models,XGB has the best predictive performance.The simplified XGB predic-tion model still retains high predictive performance and is easier to be promoted in clinical practice.