Search

Abstract Objective Sepsis-induced coagulopathy (SIC) is extremely common in individuals with sepsis, significantly associated with poor outcomes. This study attempted to develop an interpretable and generalizable machine learning (ML) model for early predicting the risk of 28-day death in patients with SIC. Methods In this retrospective cohort study, we extracted SIC patients from the Medical Information Mart for Intensive Care III (MIMIC-III), MIMIC-IV, and eICU-CRD database according to Toshiaki Iba's scale. And the overlapping in the MIMIC-IV was excluded for this study. Afterward, only the MIMIC-III cohort was randomly divided into the training set, and the internal validation set according to the ratio of 7:3, while the MIMIC-IV and eICU-CRD databases were considered the external validation sets. The predictive factors for 28-day mortality of SIC patients were determined using recursive feature elimination combined with tenfold cross-validation (RFECV). Then, we constructed models using ML algorithms. Multiple metrics were used for evaluation of performance of the models, including the area under the receiver operating characteristic curve (AUROC), area under the precision recall curve (AUPRC), accuracy, sensitivity, specificity, negative predictive value, positive predictive value, recall, and F1 score. Finally, Shapley Additive Explanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME) were employed to provide a reasonable interpretation for the prediction results. Results A total of 3280, 2798, and 1668 SIC patients were screened from MIMIC-III, MIMIC-IV, and eICU-CRD databases, respectively. Seventeen features were selected to construct ML prediction models. XGBoost had the best performance in predicting the 28-day mortality of SIC patients, with AUC of 0.828, 0.913 and 0.923, the AUPRC of 0.807, 0.796 and 0.921, the accuracy of 0.785, 0.885 and 0.891, the F1 scores were 0.63, 0.69 and 0.70 in MIMIC-III (internal validation set), MIMIC-IV, and eICU-CRD databases. The importance ranking and SHAP analyses showed that initial SOFA score, red blood cell distribution width (RDW), and age were the top three critical features in the XGBoost model. Conclusions We developed an optimal and explainable ML model to predict the risk of 28-day death of SIC patients 28-day death risk. Compared with conventional scoring systems, the XGBoost model performed better. The model established will have the potential to improve the level of clinical practice for SIC patients. Graphical Abstract

Background: Shenfu (SF) injection, a traditional Chinese medication, would improve microcirculation in cardiogenic shock and infectious shock. This study was aimed to explore the therapeutic potential of the SF injection in gut ischemia-reperfusion (I/R) injury after severe hemorrhagic shock (SHS) and resuscitation. Furthermore, we also investigated the optimal adm？ inistration timing. Methods: Twenty-four male SD rats were randomly divided into four groups: Sham group (sham, n = 6), Control group (n = 6), SF injection group (SF, n = 6), and Delayed Shenfu injection administration group (SF-delay, n = 6). In SHS and resuscitation model, rats were induced by blood draw to a mean arterial pressure (MAP) of 40 ± 5 mmHg within 1 h and then maintained for 40 min; HR, MAP ‘were recorded, microcirculation index [De Backer score, perfused small vessel density (PSVD), total vessel density (TVD), microcirculation flow index score (MFI), flow heterogeneity index (HI)] were analyzed. The blood gas index was detected, interleukin-6 (IL-6), tumor necrosis factor-α (TNF-α), diamine oxidase (DAO), malondialdehyde (MDA) were measured by ELISA; ZO-1, and claudin-1 were measured by Western blotting. In addition, hematoxylin-eosin (HE) and periodic acid schiff (PAS) staining pathological sections of the intestinal mucosal tissues were also performed. Results: SF injection increased the MAP, relieved the metabolic acidosis degree associated with the hypoperfusion, and improved the intestinal microcirculatory density and perfusion quality after I/R injury. The expression of DAO, MDA in intestinal tissue, and plasma IL-6, TNF-α significantly decreased in the SF injection group compared to the control group. The concentration of ZO-1 and claudin-1 is also higher in the SF injection group. In addition, the HE and PAS staining results also showed that SF injection could decrease mucosal damage and maintain the structure. In the SF-delay group, the degree of intestinal tissue damage was intermediate between that of the control group and SF injection group. Conclusions: SF injection protect the intestine from I/R injury induced by SHS and resuscitation, the mechanism of which might be through improving intestinal microcirculation, reducing the excessive release of inflammatory factors and increasing intestinal mucosal permeability. Furthermore, the protection effect is more pronounced if administration during the initial resuscitation phase.

BackgroundCarbapenem-resistant microorganism (CRO) transmission in the medical setting confers a global threat to public health. However, there is no established risk prediction model for infection due to CRO in ICU patients. This study aimed to develop a nomogram to predict the risk of acquiring CRO infection in patients with the first ICU admission and to determine the length of ICU stay (ICU-LOS) and 28-day survival.MethodsPatient data were retrieved from the Medical Information Mart for Intensive Care (MIMIC-IV) database based on predetermined inclusion and exclusion criteria. A CRO was defined as a bacterium isolated from any humoral microbial culture that showed insensitivity or resistance to carbapenems. The characteristics of CRO and non-CRO patients in the first ICU admission were compared. Propensity score matching was applied to balance the differences between the CRO and non-CRO cohorts. Kaplan–Meier curves were constructed to determine the 28-day survival rate and ICU-LOS. Furthermore, after randomization of the CRO cohort into the training and validation sets, a predictive nomogram was constructed based on LASSO regression and Logistic regression analysis, and its performance was verified by internal validation.ResultsOverall, 4531 patients who had first ICU admission as recorded in MIMIC-IV were enrolled, 183 (4.04%) of whom were diagnosed with CRO infection. Moreover, CRO infection was independently associated with 28-day survival and ICU-LOS in ICU patients. Parameters eligible for inclusion in this nomogram were male sex, hemoglobin-min, temperature-max, use of a peripherally inserted central catheter line, dialysis treatment, and use of carbapenems. This nomogram showed a better performance as indicated by the area under the receiver operating characteristic curve values of 0.776 (95% confidence interval [CI] 0.667-0.750) and 0.723 (95% CI 0.556-0.855) in the training and validation sets, respectively, in terms of predicting the risk of acquiring CRO infection.ConclusionsCRO infection was independently associated with ICU-LOS and 28-day survival in patients with first ICU admission. The nomogram showed the best prediction of the risk of acquiring CRO infection in ICU patients. Based on the nomogram-based scoring, we can management the risk factors and guide individualized prevention and control of CRO.

Fructans and oligofructose are usually used as prebiotics without any limitation in functional food or food ingredients. The degree of polymerization (DP) of polysaccharides affects the utilization of probiotics. Garlic is rich in fructans. The objective of this study was to extract and purify polysaccharides from garlic, analyze its composition, hydrolyze them using HCl, and then evaluate the prebiotic potential of the garlic neutral polysaccharides (GPs) before and after hydrolysis. GPs were 6.57 × 103 Da with a composition of fructose and glucose at a ratio of 4:1. After acid hydrolysis, low molecular weight fraction in garlic oligofructose (GOs) may be eliminated through ultrafiltration. The content of oligosaccharides with an average DP < 10 increased from 15 to 75%. GPs and GOS had a stronger resistance to acid conditions in human stomach than fructooligosaccharide, and GOs showed better prebiotic properties on the growth of lactobacilli than GPs. This study evaluates the prebiotic potential of the garlic frutctans and oligosaccharides mixtures obtained by acid hydrolysis, which may be used as an ingredient in functional food and nutraceutical products.