Construction of a predictive model for in-hospital mortality of sepsis patients in intensive care unit based on machine learning / 中华危重病急救医学

OBJECTIVE@#To analyze the risk factors of in-hospital death in patients with sepsis in the intensive care unit (ICU) based on machine learning, and to construct a predictive model, and to explore the predictive value of the predictive model.@*METHODS@#The clinical data of patients with sepsis who were hospitalized in the ICU of the Affiliated Hospital of Jining Medical University from April 2015 to April 2021 were retrospectively analyzed,including demographic information, vital signs, complications, laboratory examination indicators, diagnosis, treatment, etc. Patients were divided into death group and survival group according to whether in-hospital death occurred. The cases in the dataset (70%) were randomly selected as the training set for building the model, and the remaining 30% of the cases were used as the validation set. Based on seven machine learning models including logistic regression (LR), K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost) and artificial neural network (ANN), a prediction model for in-hospital mortality of sepsis patients was constructed. The receiver operator characteristic curve (ROC curve), calibration curve and decision curve analysis (DCA) were used to evaluate the predictive performance of the seven models from the aspects of identification, calibration and clinical application, respectively. In addition, the predictive model based on machine learning was compared with the sequential organ failure assessment (SOFA) and acute physiology and chronic health evaluation II (APACHE II) models.@*RESULTS@#A total of 741 patients with sepsis were included, of which 390 were discharged after improvement, 351 died in hospital, and the in-hospital mortality was 47.4%. There were significant differences in gender, age, APACHE II score, SOFA score, Glasgow coma score (GCS), heart rate, oxygen index (PaO2/FiO2), mechanical ventilation ratio, mechanical ventilation time, proportion of norepinephrine (NE) used, maximum NE, lactic acid (Lac), activated partial thromboplastin time (APTT), albumin (ALB), serum creatinine (SCr), blood urea nitrogen (BUN), blood uric acid (BUA), pH value, base excess (BE), and K+ between the death group and the survival group. ROC curve analysis showed that the area under the curve (AUC) of RF, XGBoost, LR, ANN, DT, SVM, KNN models, SOFA score, and APACHE II score for predicting in-hospital mortality of sepsis patients were 0.871, 0.846, 0.751, 0.747, 0.677, 0.657, 0.555, 0.749 and 0.760, respectively. Among all the models, the RF model had the highest precision (0.750), accuracy (0.785), recall (0.773), and F1 score (0.761), and best discrimination. The calibration curve showed that the RF model performed best among the seven machine learning models. DCA curve showed that the RF model exhibited greater net benefit as well as threshold probability compared to other models, indicating that the RF model was the best model with good clinical utility.@*CONCLUSIONS@#The machine learning model can be used as a reliable tool for predicting in-hospital mortality in sepsis patients. RF models has the best predictive performance, which is helpful for clinicians to identify high-risk patients and implement early intervention to reduce mortality.

Construction of a predictive model for early acute kidney injury risk in intensive care unit septic shock patients based on machine learning / 中华危重病急救医学

Objective:To analyze the risk factors of acute kidney injury (AKI) in patients with septic shock in intensive care unit (ICU), construct a predictive model, and explore the predictive value of the predictive model.Methods:The clinical data of patients with septic shock who were hospitalized in the ICU of the Affiliated Hospital of Jining Medical College from April 2015 to June 2019 were retrospectively analyzed. According to whether the patients had AKI within 7 days of admission to the ICU, they were divided into AKI group and non-AKI group. 70% of the cases were randomly selected as the training set for building the model, and the remaining 30% of the cases were used as the validation set. XGBoost model was used to integrate relevant parameters to predict the risk of AKI in patients with septic shock. The predictive ability was assessed through receiver operator characteristic curve (ROC curve), and was correlated with acute physiology and chronic health evaluationⅡ(APACHEⅡ), sequential organ failure assessment (SOFA), procalcitonin (PCT) and other comparative verification models to verify the predictive value.Results:A total of 303 patients with septic shock were enrolled, including 153 patients with AKI and 150 patients without AKI. The incidence of AKI was 50.50%. Compared with the non-AKI group, the AKI group had higher APACHEⅡscore, SOFA score and blood lactate (Lac), higher dose of norepinephrine (NE), higher proportion of mechanical ventilation, and tachycardiac. In the XGBoost prediction model of AKI risk in septic shock patients, the top 10 features were serum creatinine (SCr) level at ICU admission, NE use, drinking history, albumin, serum sodium, C-reactive protein (CRP), Lac, body mass index (BMI), platelet count (PLT), and blood urea nitrogen (BUN) levels. Area under the ROC curve (AUC) of the XGBoost model for predicting the risk of AKI in patients with septic shock was 0.816, with a sensitivity of 73.3%, a specificity of 71.7%, and an accuracy of 72.5%. Compared with the APACHEⅡscore, SOFA score and PCT, the performance of the model improved significantly. The calibration curve of the model showed that the goodness of fit of the XGBoost model was higher than the other scores (the calibration curve had the lowest score, with a score of 0.205).Conclusion:Compared with the commonly used clinical scores, the XGBoost model can more accurately predict the risk of AKI in patients with septic shock, which helps to make appropriate diagnosis, treatment and follow-up strategies while predicting the prognosis of patients.