Development and Validation of an Interpretable Machine Learning Model for Early Prognosis Prediction in ICU Patients with Malignant Tumors and Hyperkalemia.

This study aims to develop and validate a machine learning (ML) predictive model for assessing mortality in patients with malignant tumors and hyperkalemia (MTH). We extracted data on patients with MTH from the Medical Information Mart for Intensive Care-IV, version 2.2 (MIMIC-IV v2.2) database. The dataset was split into a training set (75%) and a validation set (25%). We used the Least Absolute Shrinkage and Selection Operator (LASSO) regression to identify potential predictors, which included clinical laboratory indicators and vital signs. Pearson correlation analysis tested the correlation between predictors. In-hospital death was the prediction target. The Area Under the Curve (AUC) and accuracy of the training and validation sets of 7 ML algorithms were compared, and the optimal 1 was selected to develop the model. The calibration curve was used to evaluate the prediction accuracy of the model further. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) enhanced model interpretability. 496 patients with MTH in the Intensive Care Unit (ICU) were included. After screening, 17 clinical features were included in the construction of the ML model, and the Pearson correlation coefficient was <0.8, indicating that the correlation between the clinical features was small. eXtreme Gradient Boosting (XGBoost) outperformed other algorithms, achieving perfect scores in the training set (accuracy: 1.000, AUC: 1.000) and high scores in the validation set (accuracy: 0.734, AUC: 0.733). The calibration curves indicated good predictive calibration of the model. SHAP analysis identified the top 8 predictive factors: urine output, mean heart rate, maximum urea nitrogen, minimum oxygen saturation, minimum mean blood pressure, maximum total bilirubin, mean respiratory rate, and minimum pH. In addition, SHAP and LIME performed in-depth individual case analyses. This study demonstrates the effectiveness of ML methods in predicting mortality risk in ICU patients with MTH. It highlights the importance of predictors like urine output and mean heart rate. SHAP and LIME significantly enhanced the model's interpretability.

Experimental study on the kinetic effect of N-butyl-N-methylpyrrolidinium tetrafluoroborate and poly(N-vinyl-caprolactam) on CH4 hydrate formation.

In this work, a series of experiments were carried out to study the kinetic inhibition performance of N-butyl-N-methylpyrrolidinium tetrafluoroborate ([BMP][BF4]), poly(N-vinylcaprolactam) (PVCap) and compound inhibitor systems on methane hydrate from both macroscopic and microscopic perspectives. In the macroscopic experiments, the influence of the concentration, the ratio of inhibitors, the subcooling on the induction time and gas consumption rate of methane hydrate were studied. The results indicated that [BMP][BF4] could inhibit the growth rate of CH4 hydrate, but failed to delay the nucleation. An improved inhibitory effect was observed by combining [BMP][BF4] and PVCap, and the optimal ratio of the two inhibitors was obtained to gain the best inhibition performance. Furthermore, the microstructure and morphology of methane hydrate crystals formed in different inhibitor systems were investigated through powder X-ray diffraction (PXRD), Raman spectroscopy and scanning electron cryomicroscopy (Cryo-SEM) methods. It was found that [BMP][BF4] and PVCap had different influences on the large cage occupancy by CH4 and the morphology of methane hydrate.