Background Acute kidney injury (AKI) is independently associated with morbidity and mortality in a wide range of surgical settings. Nowadays, with the increasing use of electronic health records (EHR), advances in patient information retrieval, and cost reduction in clinical informatics, artificial intelligence is increasingly being used to improve early recognition and management for perioperative AKI. However, there is no quantitative synthesis of the performance of these methods. Objective To estimate the sensitivity and specificity of artificial intelligence for the prediction of acute kidney injury during the perioperative period. Methods Pubmed, Embase, and Cochrane Library were searched to 2nd October 2021. Studies presenting diagnostic performance of artificial intelligence in the early detection of perioperative acute kidney injury were included. Two independent evaluators extracted data. The risk of bias of eligible studies was assessed using the PROBAST tool. Results Nineteen studies involving 304,076 patients were included. Quantitative random-effects meta-analysis using the Rutter and Gatsonis hierarchical summary receiver operating characteristics (HSROC) model revealed pooled sensitivity, specificity, and diagnostic odds ratio of 0.77 (95% CI: 0.73 to 0.81),0.75 (95% CI: 0.71 to 0.80), and 10.7 (95% CI 8.5 to 13.5), respectively. Threshold effect was found to be the only source of heterogeneity, and there was no evidence of publication bias. Conclusions Our review demonstrates the promising performance of artificial intelligence for early prediction of perioperative AKI. Further studies should focus on the improvement of existing models, novel biomarkers, and clinical effectiveness.

Background: Acute kidney injury (AKI) is independently associated with morbidity and mortality in a wide range of surgical settings. Nowadays, with the increasing use of electronic health records (EHR), advances in patient information retrieval, and cost reduction in clinical informatics, artificial intelligence is increasingly being used to improve early recognition and management for perioperative AKI. However, there is no quantitative synthesis of the performance of these methods.Objective: To estimate the sensitivity and specificity of artificial intelligence for the prediction of acute kidney injury during the perioperative period.Methods: Pubmed, Embase, and Cochrane Library were searched to 2nd October 2021. Studies presenting diagnostic performance of artificial intelligence in the early detection of perioperative acute kidney injury were included. Two independent evaluators extracted data. The risk of bias of eligible studies was assessed using the PROBAST tool.Results: Nineteen studies involving 304,076 patients were included. Quantitative random-effects meta-analysis using the Rutter and Gatsonis hierarchical summary receiver operating characteristics (HSROC) model revealed pooled sensitivity, specificity, and diagnostic odds ratio of 0.77 (95% CI: 0.73 to 0.81),0.75 (95% CI: 0.71 to 0.80), and 10.7 (95% CI 8.5 to 13.5), respectively. Threshold effect was found to be the only source of heterogeneity, and there was no evidence of publication bias.Conclusions: Our review demonstrates the promising performance of artificial intelligence for early prediction of perioperative AKI. Further studies should focus on the improvement of existing models, novel biomarkers, and clinical effectiveness.

Background We aimed to assess the utility of the poisoning severity score (PSS) as early prognostic predictors in patients with wasp stings, and to explore a reliable and simple predictive tool for short-term outcomes. Methods From January 2016 to December 2018, 363 patients with wasp stings in Suining Central Hospital were taken as research subjects. In the first 24h of hospital admission, the PSS and Chinese expert consensus on standardized diagnosis and treatment of wasp stings (CECC) were used as the criterion for severity classification, and their correlation was analyzed. The patients were divided into survival and death groups according to the state of discharge. The factors that affect outcome were analyzed by logistic regression analysis. A clinical prognostic model of death was constructed according to the risk factors, and 1000 times repeated sampling was done to include the data to verify the model internally. Results The mortality of wasp sting patients was 3.9%. There was a correlation between PSS and CECC (r=0.435, P<0.001) for severity classification. Sex, age, number of stings, and PSS were independent risk factors for death. Based on the 4 independent risk factors screened by the above regression analysis, a nomogram model was constructed to predict the risk of death in wasp sting patients. The predicted value C-index was 0.962, and the internally verified AUC was 0.962(95%C.I. 0.936-0.988, P<0.001). Conclusions PSS is helpful in the early classification of the severity of wasp stings. Sex, age, number of stings, and PSS were independent risk factors for death in wasp sting patients. The nomogram model established in this study can accurately predict the occurrence of the risk of death.