ABSTRACT
BACKGROUND@#The basis of individualized treatment should be individualized mortality risk predictive information. The present study aimed to develop an online individual mortality risk predictive tool for acute-on-chronic liver failure (ACLF) patients based on a random survival forest (RSF) algorithm.@*METHODS@#The current study retrospectively enrolled ACLF patients from the Department of Infectious Diseases of The First People's Hospital of Foshan, Shunde Hospital of Southern Medical University, and Jiangmen Central Hospital. Two hundred seventy-six consecutive ACLF patients were included in the present study as a model cohort (n = 276). Then the current study constructed a validation cohort by drawing patients from the model dataset based on the resampling method (n = 276). The RSF algorithm was used to develop an individual prognostic model for ACLF patients. The Brier score was used to evaluate the diagnostic accuracy of prognostic models. The weighted mean rank estimation method was used to compare the differences between the areas under the time-dependent ROC curves (AUROCs) of prognostic models.@*RESULTS@#Multivariate Cox regression identified hepatic encephalopathy (HE), age, serum sodium level, acute kidney injury (AKI), red cell distribution width (RDW), and international normalization index (INR) as independent risk factors for ACLF patients. A simplified RSF model was developed based on these previous risk factors. The AUROCs for predicting 3-, 6-, and 12-month mortality were 0.916, 0.916, and 0.905 for the RSF model and 0.872, 0.866, and 0.848 for the Cox model in the model cohort, respectively. The Brier scores were 0.119, 0.119, and 0.128 for the RSF model and 0.138, 0.146, and 0.156 for the Cox model, respectively. The nonparametric comparison suggested that the RSF model was superior to the Cox model for predicting the prognosis of ACLF patients.@*CONCLUSIONS@#The current study developed a novel online individual mortality risk predictive tool that could predict individual mortality risk predictive curves for individual patients. Additionally, the current online individual mortality risk predictive tool could further provide predicted mortality percentages and 95% confidence intervals at user-defined time points.
Subject(s)
Humans , Acute-On-Chronic Liver Failure , Prognosis , Proportional Hazards Models , ROC Curve , Retrospective StudiesABSTRACT
Objective Establish a laboratory quality control system to ensure accurate and reliable test data and to contrapose the influence of error factors in current detection methods for urinary iodine measurement. Methods The results of reagent blank absorbance value and uric iodine standard materials were collected, then their relevant technical indexes such as mean, standard deviation, control limit, auxiliary line were worked out. Then the quality control chart of blank test and the relative error control chart were made base on these technical indexes. And different iodine concentrations (high, middle and low concentration) were tested and their mean,relative reduction difference value, weighted mean value and critical limit Rc value were calculated, and then critical limit Rc value precision control chart was made. Results The range of absorbance of blank control test was 1.183 to 1.553. And the limit of the accuracy control Rc value was 0.0883, 0.0572, respectively, when the concentrations of urinary iodine was 0~ < 150 μg/L and 150 ~ 300 μg/L. The control limit of the relative error was 9.3%. Conclusions The method of quality control chart could be satisfactorily applied to identify the quality of the analytical results of urine iodine, and ensure the results of the urine iodine reliable and authentic.