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.

Role of Postoperative Radiotherapy on High-Risk Stage pIIIA-N2 Non-Small Cell Lung Cancer Patients After Complete Resection and Adjuvant Chemotherapy: A Retrospective Cohort Study.

Background: The aim of the study was to assess the effectiveness of postoperative radiotherapy in high-risk patients with stage pIIIA-N2 non-small cell lung cancer (NSCLC) following complete resection and adjuvant chemotherapy. Methods: Data from NSCLC patients within the Surveillance, Epidemiology, and End Results (SEER) database were analyzed. The study examined the association between lymph node ratio (LNR) and both cancer-specific survival (CSS) and overall survival (OS) using restricted cubic spline curves. Patients were categorized into high- and low-risk groups based on established LNR cut-off values, and survival outcomes were compared between those receiving postoperative radiotherapy and those who did not within the high-risk group. Results: The study included 1,690 patients. An LNR threshold of 0.29 was identified for both CSS and OS. Patients with an LNR ≥ 0.29 demonstrated significantly worse CSS (hazard ratio (HR) = 1.56, 95% confidence interval (CI): 1.37 - 1.78; P < 0.001) and OS (HR = 1.44, 95% CI: 1.28 - 1.62; P < 0.001) compared to those with an LNR < 0.29. In the high-risk group (LNR ≥ 0.29), postoperative radiotherapy did not significantly affect CSS (HR = 0.98, 95% CI: 0.82 - 1.17; P = 0.809) or OS (HR = 0.95, 95% CI: 0.81 - 1.11; P = 0.533). Conclusions: LNR is a significant prognostic factor in patients with stage pIIIA-N2 NSCLC post complete resection and adjuvant chemotherapy. A higher LNR (≥ 0.29) is associated with poorer CSS and OS. However, postoperative radiotherapy does not confer survival benefits in these high-risk patients. Our findings suggest that postoperative radiotherapy should not be routinely performed in this subgroup. Further research is required to explore effective treatment strategies for these patients.

Volatile Methylsiloxanes in Complex Samples: Recent Updates on Pretreatment and Analysis Methods.

Volatile methylsiloxanes (VMSs) are massively produced chemicals having applications in industry and home because of their physical and chemical characteristics. They are used in personal care products such as cosmetics, household coatings, cleaners, skin care products, and others. Resultantly, large number of VMSs are discharged into air where they can be subjected to atmospheric migrations over long distances causing toxic and estrogenic effects, persistence, and bioaccumulations. Many institutions have taken measures to control VMSs. They require accurate, rapid, and sensitive pretreatment and analysis methods for diverse samples. Herein, the pretreatment and determination methods of VMSs as reported in recent years are reviewed and summarized. Pretreatments include commonly methods such as membrane-assisted solvent extraction, liquid-liquid extraction, and others, while novel methods are solid phase extraction, solid phase microextraction, diverse liquid phase microextraction and others. Analyses are made through gas chromatography-based methods. In addition, the advantages, and disadvantages of techniques are compared, and the prospects of pretreatment and analysis methods are discussed.

Pros and cons of different pretreatment and detection methods for VMSs were discussed.Different novel pretreatment techniques for VMSs were discussed.High-resolution mass spectrometry (HRMS) for the determination of VMSs was discussed.

Association of polymorphisms in PATE1 gene with idiopathic asthenozoospermia in Sichuan, China.

PURPOSE: Idiopathic Asthenozoospermia (AZS) is a common symptom of male infertility described as reduced forward motility or absence of sperm motility. The PATE1 is generally expressed in male genital tract and related to sperm development, maturation and fertilization. However, the single nucleotide polymorphisms (SNPs) of the PATE1 gene which contribute to AZS were still unknown. For this reason, the possible association between the single nucleotide polymorphisms of the PATE1 gene and idiopathic asthenozoospermia was investigated in this research. METHODS: 108 idiopathic asthenozoospermia were screened by karyotype analysis, detection of Y microdeletions and mutations in 5 other genes from 140 clinical AZS. The sequence analyses of the PATE1 gene were conducted in 108 idiopathic asthenozoospermia and 106 fertile men with normospermic parameters in Sichuan, China. RESULTS: In this study, a total 108 patients without chromosomal abnormalities, Y microdeletions and selected genes mutation were confirmed. The 1423G (odds ratio [OR] 1.939, 95% confidence interval [CI] 1.320-2.848, P=0.001) was found to be increased significantly in idiopathic asthenozoospermic patients compared with their fertile counterparts. This mutation substitutes a highly conserved glutamic to arginine at the position of the 47th amino acid which was shown to be located on the flank of the pleated sheet domain in PATE1 protein by the 3D model given by the Protein Model Portal (PMP). Moreover, PolyPhen-2 analysis predicted that this variant was "probably damaging". CONCLUSIONS: These results suggested that PATE1 variant (A1423G) was probably one of the high risk genetic factors for idiopathic asthenozoospermia among males in Sichuan, China.