Development and validation of a predictive model for in-hospital mortality in patients with sepsis-associated liver injury

Abstract

Background: Sepsis is often accompanied by organ dysfunction and acute organ failure, among which the liver is commonly involved. Sepsis patients suffering from liver injury have a greater risk of mortality than patients suffering from general sepsis. As of now, there are no tools that are specifically designed for assessing the prognosis of such patients. This study aimed to develop and validate a model to predict the risk of inhospital mortality in patients with sepsis-associated liver injury (SALI).Methods: Data were obtained from the Medical Information Mart for Intensive Care (MIMIC)-IV database. In the analysis, all patients with SALI who met the inclusion and exclusion criteria were included.A primary outcome was in-hospital mortality, and clinical data were extracted for these patients. In a ratio of 8:2, the data were divided into training and validation groups at random. Least absolute shrinkage and selection operator (LASSO) regression was used for data dimension reduction and feature selection, and independent factors related to prognosis were identified through multi-factor logistics analysis. A nomogram was developed to visualize the model, and the performance of the model was evaluated by the area under the curve (AUC) as well as calibration and decision curve analysis (DCA) through internal verification.Results: A total of 616 and 154 patients with SALI were included in the training and validation cohorts, respectively. The LASSO regression and logistic multivariate analysis showed that nine factors were associated with in-hospital mortality in patients with SALI. Both the training and validation cohorts had higher AUCs than sequential organ failure assessment (SOFA) and simplified acute physiology score 2 (SAPS2): 0.753 (95% CI: 0.715-0.791) and 0.783 (95% CI: 0.749-0.817), respectively. Both the training and validation cohorts showed good calibration results for the prediction model. In terms of clinical practicability, DCA of the predictive model demonstrated greater net benefits than the SOFA and SAPS2 scores. Conclusions:We developed a predictive model that can effectively predict the in-hospital mortality of SALI patients, with satisfactory performance and clinical practicability. This model can assist clinicians in the early identification of high-risk patients and provide a reference for clinical treatment strategies.

Development of a nomogram for predicting 90-day mortality in patients with sepsis- associated liver injury: a clinical study of the MIMIC-IV database

“…The results of our research reported a morbidity rate of 7.91% (1039 of 12129 patients) and mortality rate of 44.10% (458 of 1039 patients) in patients with SALI, suggesting a lower incidence and higher death rate than the Liu Y et al 15 and Kobashi et al 26 clinical reports. We found that Liu Y's team used the older data version 1.0 of MIMIC-IV, which only included liver function indicators in the SALI diagnostic criteria and did not include the more novel combined liver function and coagulation criteria, while that allowed the inclusion of SALI diagnosed any time within 48 hours of hospitalization, but our study only included the rst 24 hours of ICU MIMIC-IV in version 2.0.…”

“…Additionally, among subjects who were at or over 40 years of age, these percentages were 51.5%, 15.9%, and 32.6%, respectively 26 . In a recent study, a scholar referred to age as an important component of mortality involved in SALI patients 15 . With the increasing severity of sepsis disease, a large proportion of patients have circulatory instability and require ascending agents to maintain hemodynamic stability [36][37][38] , yet the inclusion of vasopressors and mean arterial pressure were rst reported in sepsisassociated liver injury in our study.…”

“…Blood lactate, an indicator of tissue perfusion, is often used to provide feedback on survival in patients with sepsis 39,40 , and some high-quality studies on the effect of lactate on mortality in SALI patients have been identi ed only in children 41,42 ; this is the rst report in adult SALI patients. Some of the other variables, such as TBIL, albumin, RDW and APTT, which are frequently used in research to predict sepsis and sepsis-associated injury 14,17,18,43,44 , are rarely mentioned in studies of sepsis-associated liver injury, especially in adult reports 15 . Our ndings suggest that all of these variables independently predict mortality from sepsis-associated liver injury.…”

“…The SOFA score, LODS score and SAPS II score are widely used in mortality risk analysis and prognosis assessment of patients with sepsis 17,44,51,52 . It is rare to use a model to predict both sepsis and liver injury at the same time, except in the few reports where the level of evidence is not high 15 .…”

“…The SOFA score, LODS score and SAPS II score often have a considerable ability to predict sepsis in patients but rarely in SALI patients 15 . The high mortality of SALI patients may be related to the lack of available diagnostic tools, especially those capable of accounting for the predictive factors of sepsis and early-onset liver injury 15 . The nomogram has been widely used as a visualization tool for clinical prognostic studies in survival studies of critically ill patients [16][17][18] .…”