Daily Sepsis Research Analysis

BACKGROUND: Sepsis is characterized by organ dysfunction as a response to infection and is one of the leading causes of mortality and loss of health. The heterogeneous nature of sepsis, along with ethnic differences in susceptibility, challenges a thorough understanding of its etiology. This study aimed to propose prediction models by leveraging genetic-risk scores and clinical variables that can assist in risk stratification of patients. METHODS: A total of 1,403 patients from Taiwan, diagnosed with sepsis, were utilized. Genome-wide survival analysis was conducted, with death within 28 days from sepsis onset, as the primary event to report significantly associated SNPs. A polygenic risk score (PRS-sepsis) was constructed via clumping and thresholding method which was added to clinical-only models to generate better performing prognostic models for identifying high-risk patients. Kaplan-Meier analysis was conducted using PRS-sepsis. RESULTS: A total of five single-nucleotide-polymorphisms (SNPs) reached genome-wide significance (p < 5e-8), and 86 SNPs reached suggestive significance (p < 1e-5). The prognostic model using PRS-sepsis showed significantly improved performance with c-index [confidence interval (CI)] of 0.79 [0.62-0.96] and area under receiver operating characteristic curve (AUROC) [CI] of 0.78 [0.75-0.80], in comparison to clinical-only prognostic models (c-index [CI] = 0.63 [0.45- 0.81], AUROC [CI] = 0.61 [0.58-0.64]). The ethnic specificity was established for our proposed models by comparing it with models generated using significant SNPs from prior European studies (c-index [CI] = 0.63 [0.42-0.85], AUROC [CI] = 0.60 [0.58-0.63]). Kaplan-Meier plots showed that patient groups with higher PRSs have inferior survival probability compared to those with lower PRSs. CONCLUSIONS: This study proposed genetic-risk models specific for Taiwanese populations that outperformed clinical-only models. Also it established a strong racial-effect on the underlying genetics of sepsis-related mortality. The model can potentially be used in real clinical setting for deciding precise treatment courses for patients at high-risk thereby reducing the possibility of worse outcomes.

OBJECTIVES: Estimated glomerular filtration rate is more accurate with combined creatinine and cystatin C equations (eGFR cr-cys ) than creatinine alone. This study created and evaluated a cefepime dosing nomogram based on eGFR cr-cys for initial dosing in the critically ill. DESIGN: Pharmacokinetic modeling and simulation study. SETTING: Academic medical center. PATIENTS: Critically ill adults treated with cefepime. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Data from 120 patients with baseline cystatin C and follow-up cefepime levels were used to develop a nomogram based on eGFR cr-cys and weight for initial cefepime dosing. The predicted proportion of patients who achieved a free cefepime concentration above the minimum inhibitory concentration of the organism for 100% of the dosing interval in the first 24 hours (100% ƒT > MIC at 24 hr) was compared between administered doses and those predicted by the nomogram doses. Overall drug exposure was estimated with the free area under the concentration time curve from 0 to 24 hours (ƒAUC 0-24 ) and compared between administered and nomogram doses. Achievement of 100% ƒT > MIC at 24 hours was predicted to be significantly better with the nomogram compared with the administered dose (76% vs. 38%; p < 0.001). The median ƒAUC 0-24 as

OBJECTIVE: This study developed and validated a stacked ensemble machine learning model to predict the risk of acute kidney injury in patients with acute pancreatitis complicated by sepsis. DESIGN: A retrospective study based on patient data from public databases. PARTICIPANTS: This study analysed 1295 patients with acute pancreatitis complicated by septicaemia from the US Intensive Care Database. METHODS: From the MIMIC database, data of patients with acute pancreatitis and sepsis were obtained to construct machine learning models, which were internally and externally validated. The Boruta algorithm was used to select variables. Then, eight machine learning algorithms were used to construct prediction models for acute kidney injury (AKI) occurrence in intensive care unit (ICU) patients. A new stacked ensemble model was developed using the Stacking ensemble method. Model evaluation was performed using area under the receiver operating characteristic curve (AUC), precision-recall (PR) curve, accuracy, recall and F1 score. The Shapley additive explanation (SHAP) method was used to explain the models. MAIN OUTCOME MEASURES: AKI in patients with acute pancreatitis complicated by sepsis. RESULTS: The final study included 1295 patients with acute pancreatitis complicated by sepsis, among whom 893 cases (68.9%) developed acute kidney injury. We established eight base models, including Logit, SVM, CatBoost, RF, XGBoost, LightGBM, AdaBoost and MLP, as well as a stacked ensemble model called Multimodel. Among all models, Multimodel had an AUC value of 0.853 (95% CI: 0.792 to 0.896) in the internal validation dataset and 0.802 (95% CI: 0.732 to 0.861) in the external validation dataset. This model demonstrated the best predictive performance in terms of discrimination and clinical application. CONCLUSION: The stack ensemble model developed by us achieved AUC values of 0.853 and 0.802 in internal and external validation cohorts respectively and also demonstrated excellent performance in other metrics. It serves as a reliable tool for predicting AKI in patients with acute pancreatitis complicated by sepsis.