Aim Previous studies have shown that the fibrinogen to albumin ratio (FAR) is closely related to the severity and prognosis of coronary atherosclerosis. In this study, we sought to evaluate the association between FAR and the degree of coronary artery calcification (CAC) in patients with chronic kidney disease (CKD). Methods In this retrospective study, 218 patients with CKD were stratified into low, medium and high FAR groups according to the tertiles of the FAR values. The CAC scores, clinical information and laboratory test results of the three FAR groups were compared. To explore the relationship between FAR and CAC we conducted binary logistic regression and correlation analyses. Results In the low FAR group, the CAC scores were significantly lower than those in the medium and high FAR groups (P  <  0.001). There was a significant correlation between the FAR and CAC scores (r = 0.510, P  <  0.001). The FAR was an independent predictor of CAC (OR = 1.106, 95% CI [1.004–1.218], P = 0.042). Conclusion In patients with CKD, the FAR can be considered as an effective predictor of CAC.

Background This study aimed to establish and validate a machine learning (ML) model for predicting in-hospital mortality in critically ill patients with chronic kidney disease (CKD). Methods This study collected data on CKD patients from 2008 to 2019 using the Medical Information Mart for Intensive Care IV. Six ML approaches were used to build the model. Accuracy and area under the curve (AUC) were used to choose the best model. In addition, the best model was interpreted using SHapley Additive exPlanations (SHAP) values. Results There were 8527 CKD patients eligible for participation; the median age was 75.1 (interquartile range: 65.0–83.5) years, and 61.7% (5259/8527) were male. We developed six ML models with clinical variables as input factors. Among the six models developed, the eXtreme Gradient Boosting (XGBoost) model had the highest AUC, at 0.860. According to the SHAP values, the sequential organ failure assessment score, urine output, respiratory rate, and simplified acute physiology score II were the four most influential variables in the XGBoost model. Conclusions In conclusion, we successfully developed and validated ML models for predicting mortality in critically ill patients with CKD. Among all ML models, the XGBoost model is the most effective ML model that can help clinicians accurately manage and implement early interventions, which may reduce mortality in critically ill CKD patients with a high risk of death.

This study aimed to establish and validate a machine learning (ML) model for predicting in-hospital mortality in patients with sepsis-associated acute kidney injury (SA-AKI). This study collected data on SA-AKI patients from 2008 to 2019 using the Medical Information Mart for Intensive Care IV. After employing Lasso regression for feature selection, six ML approaches were used to build the model. The optimal model was chosen based on precision and area under curve (AUC). In addition, the best model was interpreted using SHapley Additive exPlanations (SHAP) values and Local Interpretable Model-Agnostic Explanations (LIME) algorithms. There were 8129 sepsis patients eligible for participation; the median age was 68.7 (interquartile range: 57.2–79.6) years, and 57.9% (4708/8129) were male. After selection, 24 of the 44 clinical characteristics gathered after intensive care unit admission remained linked with prognosis and were utilized developing ML models. Among the six models developed, the eXtreme Gradient Boosting (XGBoost) model had the highest AUC, at 0.794. According to the SHAP values, the sequential organ failure assessment score, respiration, simplified acute physiology score II, and age were the four most influential variables in the XGBoost model. Individualized forecasts were clarified using the LIME algorithm. We built and verified ML models that excel in early mortality risk prediction in SA-AKI and the XGBoost model performed best.

Background: Zinc displays an essential role in regulation of inflammation and redox oxidative stress and patients on peritoneal dialysis (PD) are prone to develop zinc deficiency due to decreased dietary intake and losses via PD effluent and urinate. This study was aimed to evaluate the prevalence rate of zinc level in Chinese patients on PD and the relationship between zinc level and total Kt/V (tKt/V) on PD; Methods: A cross-sectional study of a cohort of 116 patients with end-stage kidney disease (ESKD) receiving PD was conducted. Peritoneal dialysis Kt/V were identified and patients were grouped as high tKt/V (＞1.7) ( n=78) group and low tKt/V（＜1.7）(n=38) group. The zinc level in whole blood were measured using atomic absorption spectroscopy（AAS）; Results: The zinc level in whole blood showed significantly higher values in patients with high tKt/V than those with low tKt/V (5.47±0.47 and 5.02±0.35, p=0.031, respectively). Age, zinc, albumin and cholesterol level were identified as independent predictors of Kt/V in PD patients by multivariate analysis. The prognostic value of zinc of high tKt/V was revealed as an area under the curve (AUC) of 0.799 (95% CI :0.717-0.881, p＜0.001) with a sensitivity of 80.8% and specificity of 73.7%. Compared with albumin and cholesterol, Delong’test was empolyed and the results showed that zinc in whole can predict the better adequacy of PD significantly (p＜0.05); Conclusions: Zinc level in whole blood are low in patient undergoing peritoneal dialysis. Low zinc concentration is associated with low tKt/V in PD patients, suggesting that zinc level in whole blood may serve as an independent factor of dialysis quality of PD patients.

No abstract