Interpretable Machine Learning Model to Predict Bone Cement Leakage in Percutaneous Vertebral Augmentation for Osteoporotic Vertebral Compression Fracture Based on SHapley Additive exPlanations.

STUDY DESIGN: Retrospective study. OBJECTIVES: Our objective is to create comprehensible machine learning (ML) models that can forecast bone cement leakage in percutaneous vertebral augmentation (PVA) for individuals with osteoporotic vertebral compression fracture (OVCF) while also identifying the associated risk factors. METHODS: We incorporated data from patients (n = 425) which underwent PVA. To predict cement leakage, we devised six models based on a variety of parameters. Evaluate and juxtapose the predictive performances relied on measures of discrimination, calibration, and clinical utility. SHapley Additive exPlanations (SHAP) methodology was used to interpret model and evaluate the risk factors associated with cement leakage. RESULTS: The occurrence rate of cement leakage was established at 50.4%. A binary logistic regression analysis identified cortical disruption (OR 6.880, 95% CI 4.209-11.246), the basivertebral foramen sign (OR 2.142, 95% CI 1.303-3.521), the fracture type (OR 1.683, 95% CI 1.083-2.617), and the volume of bone cement (OR 1.198, 95% CI 1.070-1.341) as independent predictors of cement leakage. The XGBoost model outperformed all others in predicting cement leakage in the testing set, with AUC of .8819, accuracy of .8025, recall score of .7872, F1 score of .8315, and a precision score of .881. Several important factors related to cement leakage were drawn based on the analysis of SHAP values and their clinical significance. CONCLUSION: The ML based predictive model demonstrated significant accuracy in forecasting bone cement leakage for patients with OVCF undergoing PVA. When combined with SHAP, ML facilitated a personalized prediction and offered a visual interpretation of feature importance.

Germanicol induces selective growth inhibitory effects in human colon HCT-116 and HT29 cancer cells through induction of apoptosis, cell cycle arrest and inhibition of cell migration.

PURPOSE: The main aim of this research was to evaluate the anticancer and apoptotic effects of germanicol - a natural triterpene - in HCT-116 and HT29 human colon cancer cells and deciphering its mode of action by studying its effect on the cell cycle and cell migration. METHODS: Cell cytotoxicity was evaluated by MTT assay, while cell death was assessed by LDH assay. Fluorescence microscopy, using DAPI and acridine orange/ethidium bromide (AO-ETBR), was carried out to evaluate the effect of germanicol on cellular morphology and apoptosis induction. Apoptosis quantification was performed by Annexin V-FITC assay, while cell cycle analysis was performed by flow cytometry using propidium iodide (PI). RESULTS: The results revealed that germanicol showed selective, potent and dose-dependent cytotoxicity in HCT-116 and HT29 human colon cancer cells, while it showed lower cytotoxicity in normal colon cells (human colon fibroblast, CCD-18Co). LDH assay also showed that germanicol induced dose-dependent cell death in HCT-116 and HT29 cells. Fluorescence microscopy revealed that germanicol induced apoptosis via chromatin condensation and DNA damage in HCT-116 colon cancer cells. It also revealed that the percentage of cells with orange and red fluorescence increased when adding a germanicol dose, indicating apoptosis. Germanicol also inhibited cancer cell migration. CONCLUSION: The current findings reveal that germanicol exhibits selective antiproliferative activity against two human colon cancer cells. The normal cell line was less affected by the drug, as compared to the two cancer cell lines, indicating that germanicol will not target normal living cells. The antiproliferative effect was shown to be mediated through the induction of apoptosis and suppression of cell migration.

Simultaneous operative treatment of patients with primary liver cancer associated with portal hypertension.

OBJECTIVE: To explore the operative procedure for patients with primary liver cancer associated with portal hyper tension (PLCPH). METHODS: We analyzed retrospectively the effect of operative procedure for 9 patients with PLCPH complicated by severe esophageal varicosity and hypersplenism. RESULTS: All patients underwent liver resection and pericardiac devascularization with splenectomy. Of the 9 patients, 2 died from liver cancer recurrence separately 13 and 16 months after operation, and 1 died from massive duodenal ulcer bleeding and multiple organs failure. Six patients survived 3, 4, 8, 10, 12 and 25 months after operation. CONCLUSIONS: The patients with PLCPH undergoing simultaneous operation could acquire curative effect as compared with those who underwent liver resection. This operation is beneficial to the patients with poor liver function.