A novel clinical prediction model for in-hospital mortality in sepsis patients complicated by ARDS: A MIMIC IV database and external validation study.

Background: Sepsis complicated by ARDS significantly increases morbidity and mortality, underscoring the need for robust predictive models to enhance patient management. Methods: We collected data on 6390 patients with ARDS-complicated sepsis from the MIMIC IV database. Following rigorous data cleaning, including outlier management, handling missing values, and transforming variables, we conducted univariate analysis and logistic multivariate regression. We employed the LASSO machine learning algorithm to identify risk factors closely associated with patient outcomes. These factors were then used to develop a new clinical prediction model. The model underwent preliminary assessment and internal validation, and its performance was further tested through external validation using data from 225 patients at a major tertiary hospital in China. This validation assessed the model's discrimination, calibration, and net clinical benefits. Results: The model, illustrated by a concise nomogram, demonstrated significant discrimination with an area under the curve (AUC) of 0.711 in the internal validation set and 0.771 in the external validation set, outperforming conventional severity scores such as the SOFA and SAPS II. It also showed good calibration and net clinical benefits. Conclusions: Our model serves as a valuable tool for identifying sepsis patients with ARDS at high risk of in-hospital mortality. This could enable the implementation of personalized treatment strategies, potentially improving patient outcomes.

Peripheral artery disease mediating the effect of metabolic syndrome related diseases on lower limb ulcers: Mendelian randomization analysis.

Background: Previous observational studies have demonstrated a correlation between metabolic syndrome related diseases and an elevated susceptibility to ulcers of lower limb. It has been suggested that this causal relationship may be influenced by the presence of peripheral artery disease (PAD). Nevertheless, the precise contribution of these factors as determinants of ulcers of lower limb remains largely unexplored. Method: This research incorporated information on hypertension, BMI, hyperuricemia, type 2 diabetes, PAD, and ulcers of lower limb sourced from the GWAS database. Univariate Mendelian randomization (SVMR) and multivariate Mendelian randomization (MVMR) methods were employed to assess the association between metabolic syndrome related diseases, including hypertension, obesity, hyperuricemia, and type 2 diabetes, as well as to investigate whether this association was influenced by PAD. Results: Univariate Mendelian randomization analysis showed that genetically predicted hypertension, BMI, and type 2 diabetes were associated with an increased risk of PAD and ulcers of lower limb, and PAD was associated with an increased risk of ulcers of lower limb, but there is no causal relationship between hyperuricemia and ulcers of lower limb. The results of multivariate Mendelian randomization showed that PAD mediated the causal relationship between hypertension, obesity and ulcers of lower limb, but the relationship between type 2 diabetes and ulcers of lower limb was not mediated by PAD. Conclusion: Hypertension, BMI and type 2 diabetes can increase the risk of ulcers of lower limb, and PAD can be used as a mediator of hypertension and obesity leading to ulcers of lower limb, These findings may inform prevention and intervention strategies directed toward metabolic syndrome and ulcers of lower limb.

Establishment of skin cutaneous melanoma prognosis model based on vascular mimicry risk score.

Studies have indicated that Vascular mimicry (VM) could contribute to the unfavorable prognosis of skin cutaneous melanoma (SKCM). Thus, the objective of this study was to identify therapeutic targets associated with VM in SKCM and develop a novel prognostic model. Gene expression data from The Cancer Genome Atlas (TCGA) and Genotype-Tissue Expression (GTEx) were utilized to identify differentially expressed genes (DEGs). By intersecting these DEGs with VM genes, we acquired VM-related DEGs specific to SKCM, and then identified prognostic-related VM genes. A VM risk score system was established based on these prognosis-associated VM genes, and patients were then categorized into high- and low-score groups using the median score. Subsequently, differences in clinical characteristics, gene set enrichment analysis (GSEA), and other analyses were further presented between the 2 groups of patients. Finally, a novel prognostic model for SKCM was established using the VM score and clinical characteristics. 26 VM-related DEGs were identified in SKCM, among the identified DEGs associated with VM in SKCM, 5 genes were found to be prognostic-related. The VM risk score system, comprised of these genes, is an independent prognostic risk factor. There were significant differences between the 2 patient groups in terms of age, pathological stage, and T stage. VM risk scores are associated with epithelial biological processes, angiogenesis, regulation of the SKCM immune microenvironment, and sensitivity to targeted drugs. The novel prognostic model demonstrates excellent predictive ability. Our study identified VM-related prognostic markers and therapeutic targets for SKCM, providing novel insights for clinical diagnosis and treatment.

Interpretable machine learning based on CT-derived extracellular volume fraction to predict pathological grading of hepatocellular carcinoma.

PURPOSE: To develop a non-invasive auxiliary assessment method based on CT-derived extracellular volume (ECV) to predict the pathological grading (PG) of hepatocellular carcinoma (HCC). METHODS: The study retrospectively analyzed 238 patients who underwent HCC resection surgery between January 2013 and April 2023. Six machine learning algorithms were employed to construct predictive models for HCC PG: logistic regression, extreme gradient boosting, Light Gradient Boosting Machine (LightGBM), random forest, adaptive boosting, and Gaussian naive Bayes. Model performance was evaluated using receiver operating characteristic curve analysis, including area under the curve (AUC), sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and F1 score. Calibration plots were used for visual evaluation of model calibration. Clinical decision curve analysis was performed to assess potential clinical utility by calculating net benefit. RESULTS: 166 patients from Hospital A were allocated to the training set, while 72 patients from Hospital B (constituting 30.25% of the total sample) were assigned to the test set. The model achieved an AUC of 1.000 (95%CI: 1.000-1.000) in the training set and 0.927 (95%CI: 0.837-0.999) in the validation set, respectively. Ultimately, the model achieved an AUC of 0.909 (95%CI: 0.837-0.980) in the test set, with an accuracy of 0.778, sensitivity of 0.906, specificity of 0.789, negative predictive value of 0.556, and F1 score of 0.908. CONCLUSION: This study successfully developed and validated a non-invasive auxiliary assessment method based on CT-derived ECV to predict the HCC PG, providing important supplementary information for clinical decision-making.