Related Experiment Video
Updated: Sep 15, 2025
A Data-Driven Approach to Quantifying Immune States in Sepsis
Published on: February 7, 2025
Predicting the Requirement of Blood Purification in Sepsis Disease Population: Development and Assessment of a New
Background:
Sepsis is the leading cause of death for critically ill patients worldwide, and blood purification technology is an effective method for rapidly improving and treating sepsis. At present, there is a lack of sufficient clinical data on the timing of blood purification intervention for sepsis patients in China. This study aimed to develop an effective and straightforward tool for predicting the need for blood purification in the sepsis population using an evaluation model.
Methods:
A total of 346 patients were enrolled in the study. The patients were divided into two groups: the blood purification group (n = 80) and the non-blood purification group (n = 266). Demographic information, medical history, clinical performance, laboratory results, and treatment characteristics were extracted from the medical records of all participants. The optimal predictive risk factors were selected using the least absolute shrinkage and selection operator (LASSO) method to reduce the high-dimensional data. Multivariate logistic regression analysis and the creation of a nomogram were performed using R software (3.1.1). The model's discrimination, calibration, and clinical utility were evaluated using the C-index, calibration plot, and decision curve analysis, respectively. The 95% confidence interval (CI) for the calculated odds ratio (OR) was also estimated.
Results:
The novel predictive nomogram, developed using β2-microglobulin (BMG), urea nitrogen (BUN), acute kidney injury (AKI), neutrophil gelatinase-associated lipocalin (NGAL), uric acid (URIC), and estimated glomerular filtration rate (eGFR), could be easily applied to predict the appropriate timing for blood purification. Using the nomogram to predict the risk of requiring blood purification provided greater benefits than the standard method.
Conclusions:
Our findings provide an effective prediction model that will assist clinicians in identifying the optimal time for blood purification.
