Background Acute kidney injury (AKI) is the most common and serious complication of sepsis, accompanied by high mortality and disease burden. The early prediction of AKI is critical for timely intervention and ultimately improves prognosis. This study aims to establish and validate predictive models based on novel machine learning (ML) algorithms for AKI in critically ill patients with sepsis. Methods Data of patients with sepsis were extracted from the Medical Information Mart for Intensive Care III (MIMIC- III) database. Feature selection was performed using a Boruta algorithm. ML algorithms such as logistic regression (LR), k-nearest neighbors (KNN), support vector machine (SVM), decision tree, random forest, Extreme Gradient Boosting (XGBoost), and artificial neural network (ANN) were applied for model construction by utilizing tenfold cross-validation. The performances of these models were assessed in terms of discrimination, calibration, and clinical application. Moreover, the discrimination of ML-based models was compared with those of Sequential Organ Failure Assessment (SOFA) and the customized Simplified Acute Physiology Score (SAPS) II model. Results A total of 3176 critically ill patients with sepsis were included for analysis, of which 2397 cases (75.5%) developed AKI during hospitalization. A total of 36 variables were selected for model construction. The models of LR, KNN, SVM, decision tree, random forest, ANN, XGBoost, SOFA and SAPS II score were established and obtained area under the receiver operating characteristic curves of 0.7365, 0.6637, 0.7353, 0.7492, 0.7787, 0.7547, 0.821, 0.6457 and 0.7015, respectively. The XGBoost model had the best predictive performance in terms of discrimination, calibration, and clinical application among all models. Conclusion The ML models can be reliable tools for predicting AKI in septic patients. The XGBoost model has the best predictive performance, which can be used to assist clinicians in identifying high-risk patients and implementing early interventions to reduce mortality.

No abstract

Background. Inflammation plays a key role in the pathophysiology and progression of acute kidney injury (AKI). Red cell distribution width (RDW) to platelet ratio (RPR) is a novel inflammatory index, and its prognostic effect on critically ill patients with AKI is rarely investigated. This work is aimed at investigating the association between RPR and in-hospital mortality in these patients. Methods. Data were extracted from the Medical Information Mart for Intensive Care III database. All-cause death during hospitalization was selected as the primary outcome. Receiver operating characteristic (ROC) curve was used to determine the optimal cut-off value, and the area under the curve (AUC) was applied to compare predictive ability among different indices. Cox proportional hazard models were utilized to assess the association between RPR and in-hospital mortality. Restricted cubic spline analysis for multivariate Cox model was performed to explore the shape of the relationship between RPR and mortality. Results. A total of 24,166 critically ill patients with AKI were included. The relationship of RPR and in-hospital mortality was nonlinear with a trend to rise rapidly and then gradually. For mortality prediction, RPR had the optimal cut-off value of 0.093, of which the AUC was 0.791 (95% confidence interval (CI): 0.773–0.810), which was higher than those of RDW, platelet, sequential organ failure assessment score, simplified acute physiology score II, neutrophil to lymphocyte ratio, and platelet to lymphocytes ratio. After adjustments for various confounders, high RPR showed a significant association with increased mortality with hazard ratios of 1.46 (95% CI: 1.40–1.55) for categorical variable and 1.88 (95% CI: 1.80–1.97) for continuous variables in the fully adjusted model. Conclusions. Elevated RPR on admission is substantially associated with high risk of in-hospital mortality in critically ill patients with AKI and thus may serve as a novel predictor of prognosis for these patients.

IntroductionPrevention of the no-reflow phenomenon has a crucial role in primary percutaneous coronary intervention (P-PCI) procedures.AimTo assess the effects of early intracoronary administration of nicorandil (NIC) during P-PCI on myocardial microcirculation in patients with acute myocardial infarction (AMI).Material and methodsA total of 120 patients with first acute anterior wall ST segment elevation myocardial infarction who underwent P-PCI were randomly divided into two groups: the NIC group (A, n = 60) and the placebo group (B, n = 60). Before stent placement, NIC or normal saline was injected using a guiding catheter. The thrombolysis in myocardial infarction (TIMI) grade, TIMI myocardial perfusion grade (TMPG), resolution of ST segment elevation (defined as > 50% decrease in ST elevation) 1 h after surgery, and 99Tcm-methoxyisobutyl isocyanide (MIBI) rest myocardial perfusion imaging (MPI) via single-photon emission computed tomography (99Tcm-MIBI SPECT) findings 10 days after surgery were compared between the two groups.ResultsThe number of patients who achieved TIMI grade 3 (96.67% vs. 86.67%; p = 0.047) and TMPG 3 (95% vs. 83.33%; p = 0.040) was higher in the NIC group than in the placebo group. Resolution of ST segment elevation occurred in 95% and 81.67% of the patients in the NIC and placebo groups, respectively (p = 0.023); the MPI score of the two groups was 4.1 ±1.89 and 7.3 ±2.65, respectively (p = 0.014).ConclusionsEarly coronary administration of NIC can significantly reduce the damage in the myocardial microcirculation caused by P-PCI and the myocardial infarct size in patients with AMI.

Background. As a novel inflammatory index, the ratio of red cell distribution width (RDW) to platelet count (RPR) may have prognostic value in some critical illnesses. However, studies on the prognostic influence of RPR in patients with sepsis are few. This study is aimed at investigating the association between RPR levels and 28-day mortality in patients with sepsis. Methods. Data of patients with sepsis were obtained from the Medical Information Mart for Intensive Care III database. The best cut-off value was calculated by establishing the receiver operating characteristic curve (ROC), and the predictive ability of different indicators was compared through the area under the curve (AUC). The association between RPR levels and 28-day mortality was assessed using the Cox proportional hazards model. Restrictive cubic spline analysis was applied to the multivariable Cox model to investigate the nonlinear relationship between RPR and 28-day mortality. Results. A total of 3367 patients with sepsis were included in the study. A nonlinear relationship was observed between RPR and 28-day mortality, showing a trend of a first rapid increase and a gradual increase. For the prediction of mortality, the best cut-off value for RPR was 0.109, with an AUC of 0.728 (95% confidence interval [CI]: 0.709–0.747). The predictive capability of RPR was superior to those of RDW, platelet, SOFA score, and SAPS II score. After adjusting for various confounding factors, high RPR was significantly associated with increased mortality with adjusted hazard ratios of 1.210 (95% CI: 1.045–1.400) for categorical variables and 2.826 (95% CI: 2.025–3.944) for continuous variables. Conclusion. Elevated RPR level is significantly correlated with a high risk of 28-day mortality in patients with sepsis and can be a new predictor of patient prognosis.