Comparative Analysis of Machine Learning Models for Prediction of Acute Liver Injury in Sepsis Patients.

Introduction: Acute liver injury (ALI) is a common complication of sepsis and is associated with adverse clinical outcomes. We aimed to develop a model to predict the risk of ALI in patients with sepsis after hospitalization. Methods: Medical records of 3196 septic patients treated at the Lishui Central Hospital in Zhejiang Province from January 2015 to May 2023 were selected. Cohort 1 was divided into ALI and non-ALI groups for model training and internal validation. The initial laboratory test results of the study subjects were used as features for machine learning (ML), and models built using nine different ML algorithms were compared to select the best algorithm and model. The predictive performance of model stacking methods was then explored. The best model was externally validated in Cohort 2. Results: In Cohort 1, LightGBM demonstrated good stability and predictive performance with an area under the curve (AUC) of 0.841. The top five most important variables in the model were diabetes, congestive heart failure, prothrombin time, heart rate, and platelet count. The LightGBM model showed stable and good ALI risk prediction ability in the external validation of Cohort 2 with an AUC of 0.815. Furthermore, an online prediction website was developed to assist healthcare professionals in applying this model more effectively. Conclusions: The Light GBM model can predict the risk of ALI in patients with sepsis after hospitalization.

Application of interpretable machine learning algorithms to predict acute kidney injury in patients with cerebral infarction in ICU.

BACKGROUND: Acute kidney injury (AKI) is not only a complication but also a serious threat to patients with cerebral infarction (CI). This study aimed to explore the application of interpretable machine learning algorithms in predicting AKI in patients with cerebral infarction. METHODS: The study included 3920 patients with CI admitted to the Intensive Care Unit and Emergency Medicine of the Central Hospital of Lishui City, Zhejiang Province. Nine machine learning techniques, including XGBoost, logistics, LightGBM, random forest (RF), AdaBoost, GaussianNB (GNB), Multi-Layer Perceptron (MLP), support vector machine (SVM), and k-nearest neighbors (KNN) classification, were used to develop a predictive model for AKI in these patients. SHapley Additive exPlanations (SHAP) analysis provided visual explanations for each patient. Finally, model effectiveness was assessed using metrics such as average precision (AP), sensitivity, specificity, accuracy, F1 score, precision-recall (PR) curve, calibration plot, and decision curve analysis (DCA). RESULTS: The XGBoost model performed better in the internal validation set and the external validation set, with an AUC of 0.940 and 0.887, respectively. The five most important variables in the model were, in order, glomerular filtration rate, low-density lipoprotein, total cholesterol, hemiplegia and serum kalium. CONCLUSION: This study demonstrates the potential of interpretable machine learning algorithms in predicting CI patients with AKI.

Real-Time Camera Image-Guided Nasoenteric Tube Placement in Prone COVID-19 ICU Patients: A Single-Center Study.

Background & Aims: This study aims to assess the application value of the real-time camera image-guided nasoenteric tube placement in critically ill COVID-19 patients undergoing endotracheal intubation and prone position ventilation therapy. Methods: We enrolled 116 COVID-19 patients receiving endotracheal intubation and prone position ventilation therapy in the intensive care unit (ICU). Patients were randomly divided into the real-time camera image-guided nasoenteric tube placement (n = 58) and bedside blind insertion (n = 58) groups. The success rate, placement time, complications, cost, heart rate, respiratory rate, Glasgow Coma Scale (GCS), and Acute Physiology and Chronic Health Evaluation II (APACHE-II) scores were compared between the 2 groups. Results: For ICU patients with COVID-19 undergoing prone position ventilation therapy, the success rate and cost were significantly higher in the real-time camera image-guided group compared to the bedside blind group (P < .05). The placement time and complication incidence were significantly lower in the real-time camera image-guided group (P < .05). The differences in heart rate, respiratory rate, GCS scores, and APACHE-II scores were insignificant (P > .05). Conclusions: The real-time camera image-guided nasoenteric tube placement system had advantages for ICU COVID-19 patients undergoing prone position ventilation therapy, including a high success rate, short placement time, and no impact on patient position during tube placement. Real-time camera image-guided nasoenteric tube placement can be performed in any position, and demonstrates high efficiency, safety, and accuracy.