Aspirin is associated with improved outcomes in patients with sepsis-induced myocardial injury: An analysis of the MIMIC-IV database.

BACKGROUND: The effectiveness of aspirin treatment in septic patients remains a subject of debates. OBJECTIVE: To explore the association between aspirin usage and the prognosis of patients with sepsis-induced myocardial injury (SIMI), as well as the timing of aspirin administration. METHODS: Patients with SIMI were screened in the MIMIC-IV database and categorized into aspirin and non-aspirin groups based on their medications during intensive care unit (ICU) stay, and propensity matching analysis (PSM) was subsequently performed to reduce bias at baseline between the groups. The primary outcome was 28-day all-cause mortality. Cox multivariate regression analysis was conducted to evaluate the impact of aspirin on the prognosis of patients with SIMI. RESULTS: The pre-PSM and post-PSM cohorts included 1170 and 1055 patients, respectively. In the pre-PSM cohort, the aspirin group is older, has a higher proportion of chronic comorbidities, and lower SOFA and SAPS II scores when compared to the non-aspirin group. In the PSM analysis, most of the baseline characterization biases were corrected, and aspirin use was also associated with lower 28-day mortality (hazard ratio [HR] = 0.51, 95 % confidence interval [CI]: 0.42-0.63, P < 0.001), 90-day mortality (HR = 0.58, 95 % CI: 0.49-0.69, P < 0.001) and 1-year mortality (HR = 0.65, 95 % CI: 0.56-0.76, P < 0.001), irrespective of aspirin administration timing. A sensitivity analysis based on the original cohort confirmed the robustness of the findings. Additionally, subsequent subgroup analysis revealed that the use of vasopressin have a significant interaction with aspirin's efficacy. CONCLUSION: Aspirin was associated with decreased mortality in SIMI patients, and this beneficial effect persisted regardless of pre-ICU treatment.

Early prognosis prediction for non-variceal upper gastrointestinal bleeding in the intensive care unit: based on interpretable machine learning.

INTRODUCTION: This study aims to construct a mortality prediction model for patients with non-variceal upper gastrointestinal bleeding (NVUGIB) in the intensive care unit (ICU), employing advanced machine learning algorithms. The goal is to identify high-risk populations early, contributing to a deeper understanding of patients with NVUGIB in the ICU. METHODS: We extracted NVUGIB data from the Medical Information Mart for Intensive Care IV (MIMIC-IV, v.2.2) database spanning from 2008 to 2019. Feature selection was conducted through LASSO regression, followed by training models using 11 machine learning methods. The best model was chosen based on the area under the curve (AUC). Subsequently, Shapley additive explanations (SHAP) was employed to elucidate how each factor influenced the model. Finally, a case was randomly selected, and the model was utilized to predict its mortality, demonstrating the practical application of the developed model. RESULTS: In total, 2716 patients with NVUGIB were deemed eligible for participation. Following selection, 30 out of a total of 64 clinical parameters collected on day 1 after ICU admission remained associated with prognosis and were utilized for developing machine learning models. Among the 11 constructed models, the Gradient Boosting Decision Tree (GBDT) model demonstrated the best performance, achieving an AUC of 0.853 and an accuracy of 0.839 in the validation cohort. Feature importance analysis highlighted that shock, Glasgow Coma Scale (GCS), renal disease, age, albumin, and alanine aminotransferase (ALP) were the top six features of the GBDT model with the most significant impact. Furthermore, SHAP force analysis illustrated how the constructed model visualized the individualized prediction of death. CONCLUSIONS: Patient data from the MIMIC database were leveraged to develop a robust prognostic model for patients with NVUGIB in the ICU. The analysis using SHAP also assisted clinicians in gaining a deeper understanding of the disease.

Machine learning-based prediction model of acute kidney injury in patients with acute respiratory distress syndrome.

BACKGROUND: Acute kidney injury (AKI) can make cases of acute respiratory distress syndrome (ARDS) more complex, and the combination of the two can significantly worsen the prognosis. Our objective is to utilize machine learning (ML) techniques to construct models that can promptly identify the risk of AKI in ARDS patients. METHOD: We obtained data regarding ARDS patients from the Medical Information Mart for Intensive Care III (MIMIC-III) and MIMIC-IV databases. Within the MIMIC-III dataset, we developed 11 ML prediction models. By evaluating various metrics, we visualized the importance of its features using Shapley additive explanations (SHAP). We then created a more concise model using fewer variables, and optimized it using hyperparameter optimization (HPO). The model was validated using the MIMIC-IV dataset. RESULT: A total of 928 ARDS patients without AKI were included in the analysis from the MIMIC-III dataset, and among them, 179 (19.3%) developed AKI after admission to the intensive care unit (ICU). In the MIMIC-IV dataset, there were 653 ARDS patients included in the analysis, and among them, 237 (36.3%) developed AKI. A total of 43 features were used to build the model. Among all models, eXtreme gradient boosting (XGBoost) performed the best. We used the top 10 features to build a compact model with an area under the curve (AUC) of 0.850, which improved to an AUC of 0.865 after the HPO. In extra validation set, XGBoost_HPO achieved an AUC of 0.854. The accuracy, sensitivity, specificity, positive prediction value (PPV), negative prediction value (NPV), and F1 score of the XGBoost_HPO model on the test set are 0.865, 0.813, 0.877, 0.578, 0.957 and 0.675, respectively. On extra validation set, they are 0.724, 0.789, 0.688, 0.590, 0.851, and 0.675, respectively. CONCLUSION: ML algorithms, especially XGBoost, are reliable for predicting AKI in ARDS patients. The compact model maintains excellent predictive ability, and the web-based calculator improves clinical convenience. This provides valuable guidance in identifying AKI in ARDS, leading to improved patient outcomes.

[Research progress of in-hospital mortality risk model in patients with acute myocardial infarction].

The incidence of in-hospital death in acute myocardial infarction (AMI) is high, which seriously threatens the life and health of patients. At present, many countries and regions have established a variety of objective assessment models for predicting the in-hospital mortality of patients with AMI, providing important decision-making support for patients with different risk levels when formulating treatment plans. With the rise of artificial intelligence, many new modeling methods also show certain advantages over the traditional models. This article systematically introduces the commonly used and newly constructed risk prediction models for in-hospital mortality of AMI, in order to provide help for medical staff to assist decision-making in clinical practice, and provide reference for the establishment of a safe and more effective risk prediction model in the future.