Search

This study aims to develop and validate a prediction model in-hospital mortality in critically ill patients with sepsis-associated acute kidney injury (SA-AKI) based on machine learning algorithms. Patients who met the criteria for inclusion were identified in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and divided according to the validation (n = 2440) and development (n = 9756, 80%) queues. Ensemble stepwise feature selection method was used to screen for effective features. The prediction models of short-term mortality were developed by seven machine learning algorithms. Ten-fold cross-validation was used to verify the performance of the algorithm in the development queue. The area under the receiver operating characteristic curve (ROC-AUC) was used to evaluate the differentiation accuracy and performance of the prediction model in the validation queue. The best-performing model was interpreted by Shapley additive explanations (SHAP). A total of 12,196 patients were enrolled in this study. Eleven variables were finally chosen to develop the prediction model. The AUC of the random forest (RF) model was the highest value both in the Ten-fold cross-validation and evaluation (AUC: 0.798, 95% CI: 0.774–0.821). According to the SHAP plots, old age, low Glasgow Coma Scale (GCS) score, high AKI stage, reduced urine output, high Simplified Acute Physiology Score (SAPS II), high respiratory rate, low temperature, low absolute lymphocyte count, high creatinine level, dysnatremia, and low body mass index (BMI) increased the risk of poor prognosis. The RF model developed in this study is a good predictor of in-hospital mortality for patients with SA-AKI in the intensive care unit (ICU), which may have potential applications in mortality prediction. [ABSTRACT FROM AUTHOR]

Marek’s disease virus (MDV) and avian leucosis virus (ALV) are known to cause tumours in egg-laying hens. Here, we investigated the aetiology of tumours in a flock of egg-laying hens vaccinated against MDV. We carried out gross pathology and histopathological examinations of the diseased tissues, identified virus antigen and sequenced viral oncogenes to elucidate the cause of death in 21–22-week-old hens. At necropsy, diseased hens had distinctly swollen livers, spleens, and proventriculus, and white tumour nodules in the liver. The spleen and liver had been infiltrated by lymphoid tumour cells, while the proventriculus had been infiltrated by both lymphoid tumour cells and myeloblastic cells. Subtype J ALV (ALV-J) and MDV were widely distributed in the proventricular gland cells, and the lymphoid tumour cells in the liver and the spleen. In addition, positive ALV-J signals were also observed in parts of the reticular cells in the spleen. MDV and ALV-J antigens were observed in the same foci of the proventricular gland cells; however, the two antigens were not observed in the same foci from the spleen and liver. The amino acid sequence of the AN-1 (the representative liver tumour tissue that was positive for both ALV-J and MDV) Meq protein was highly similar to the very virulent MDV QD2014 from China. Compared to the ALV-J HPRS-103 reference strain, 10 amino acids (224-CTTEWNYYAY-233) were deleted from the gp85 protein of AN-1. We concluded that concurrent infection with MDV and ALV-J contributed to the tumorigenicity observed in the flock. [ABSTRACT FROM PUBLISHER]