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.

Evaluation of the circulating MicroRNA-495 and Stat3 as prognostic and predictive biomarkers for lower extremity deep venous thrombosis.

This study aims to elucidate the prognostic and predictive biomarker of miR-495 and Stat3 in peripheral blood in relation to lower extremity deep venous thrombosis (DVT). Patients with lower limb fractures were assigned into case and control groups. Rats were allocated into blank (normal rats), sham (normal rats), DVT, miR-495 mimic, miR-495 inhibitor, over-Stat3, and si-Stat3 groups. ELISA was used to detect levels of prothrombin time (PT), endothelin-1 (ET-1), Human Fibrinogen (FIB), D-Dimer, blood coagulation factors V and VIII, tissue type plasminogen activator (t-PA), platelet activating factor (PAF), protein C and Stat3. qRT-PCR was employed for the evaluation of the expressions of miR-495 and Stat3, while receiver operating characteristic (ROC) curve was constructed to assess the predictive value of miR-495 and Stat3 as well as the treatment outcomes of patients with lower limb fractures. Logistic regression analyses were conducted in order to correlate indexes and lower extremity DVT. miR-495 overexpression, t-PA, PAF, and protein C were confirmed to be protective factors, while Stat3 overexpression, PT, ET-1, FIB, D-Dimer, blood coagulation factor V, and VIII were all ultimately considered to be risk factors of lower extremity DVT. Stat3 was confirmed to be the target gene of miR-495. Compared with the blank group, the length and weight of the thrombus as well as the ratio between length and weight, mRNA and protein expression of Stat3 were reduced in the miR-495 mimic and si-Stat3 groups. Our findings suggest that through the suppression of Stat3 expression, miR-495 prohibits lower extremity DVT in peripheral blood.

MMP-3-1612 polymorphism - a risk factor for deep venous thrombosis formation.

BACKGROUND: We investigated the association of the 5A/6A polymorphism in the promoter region at -1612 of the matrix metalloproteinase-3 gene (MMP-3-1612) and deep venous thrombosis (DVT). PATIENTS, MATERIALS AND METHODS: The distribution of the MMP-3 (-1612 5A/6A) polymorphism in the case and control groups was detected by polymerase chain reaction-restriction fragment length polymorphism (PCR-RFLP). Serum MMP-3 level of two groups was detected using enzyme-linked immunosorbent assay (ELISA). HepG2 cells containing MMP-3-1612 recombinant plasmid were cultured in vitro and the MMP-3 level was defined by luminescence intensity of luciferase. A DVT rat model was built. Serum MMP-3 level in the rats' wounded vein at different time points was detected by ELISA and recorded for investigation of the association between MMP-3 and DVT. Statistical data analysis was conducted with SPSS18.0. RESULTS: On the basis of the observation of MMP-3-1612 genotype frequency and allele frequency in the case and control groups, we identified significantly higher MMP-3-1612 5A allele frequency and higher serum MMP-3 level in the case group than in the control group (both P < 0.05). According to in vitro luciferase measurements, the 5A allele had higher transcriptional activity than the 6A allele. As observed in the rat model, serum MMP-3 level increased with time passing and thrombosis formation after modelling. CONCLUSIONS: The MMP-3-1612 5A/6A polymorphism may effect serum MMP-3 level and over-expression of serum MMP-3 level may be a risk factor for DVT formation.

An unprecedented 2D copper(i)-cyanide complex with 20-membered metal rings: the effect of the co-ligand 4,5-diazafluoren-9-one.

A hydrothermal reaction of CuCl2·2H2O, 4,5-diazafluoren-9-one (L) and K3[Fe(CN)6], which is used as an environment friendly cyanide source, produces a two-dimensional copper cyanide complex Cu10(CN)10L4 (1). In the complex, the L ligands act as corner and bridge ligands simultaneously. With the help of the corner ligands, infinite Cu(CN)∞ chains are formed. The chains are further bridged by another type of L ligand forming a 2D layer with a Cu20(CN)18L2 macrocycle, which shows blue photoluminescence related to centered π-π* transitions of the L ligand.

MDCT Evaluation of Costal Bone Lesions: Comparison of Axial, Multiplanar, and 3D Volume-Rendered Images: A Retrospective Study.

The aim of this retrospective study was to compare accuracies of axial, multiplanar, and volume-rendered 3-dimensional (3D) images in the diagnosis of costal bone lesions.Forty-one patients, aged from 10 to 72-years old, with costal bone lesions underwent multidetector CT (MDCT). Axial, multiplanar, and 3D-volume-rendered images were reviewed by 3 reviewers for the property of the lesions (fracture, tumor, and tumor-like lesions or inflammation). In case of fracture, the diagnosis was demonstrated with the location of the fracture and the amounts of the costal bone involved. In case of a tumor or tumor-like lesions, the diagnosis was demonstrated pathological property. Final diagnosis was determined by biopsy or surgery. Diagnostic accuracy and interreviewers agreement were evaluated.For the diagnosis of fractures, average accuracy was 77%, 100%, and 100% for axial, multiplanar, and 3D-volume-rendered images, respectively. For the diagnosis of tumor and tumor-like lesions, average accuracy was 90% for axial, 96% for multiplanar, and 99% for 3D-volume-rendered images. For the diagnosis of inflammation lesions, average accuracy was 100% for all the 3 image formats. Interobserver agreement independence of imaging formats was high.Multiplanar and 3D-volume-rendered images were superior to axial images in diagnosis of fracture, tumor, and tumor-like lesions; however, for the evaluation of inflammation lesions, there were no difference by 3 image formats.