Application of interpretable machine learning algorithms to predict distant metastasis in ovarian clear cell carcinoma.

BACKGROUND: Ovarian clear cell carcinoma (OCCC) represents a subtype of ovarian epithelial carcinoma (OEC) known for its limited responsiveness to chemotherapy, and the onset of distant metastasis significantly impacts patient prognoses. This study aimed to identify potential risk factors contributing to the occurrence of distant metastasis in OCCC. METHODS: Utilizing the Surveillance, Epidemiology, and End Results (SEER) database, we identified patients diagnosed with OCCC between 2004 and 2015. The most influential factors were selected through the application of Gaussian Naive Bayes (GNB) and Adaboost machine learning algorithms, employing a Venn test for further refinement. Subsequently, six machine learning (ML) techniques, namely XGBoost, LightGBM, Random Forest (RF), Adaptive Boosting (Adaboost), Support Vector Machine (SVM), and Multilayer Perceptron (MLP), were employed to construct predictive models for distant metastasis. Shapley Additive Interpretation (SHAP) analysis facilitated a visual interpretation for individual patient. Model validity was assessed using accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, and the area under the receiver operating characteristic curve (AUC). RESULTS: In the realm of predicting distant metastasis, the Random Forest (RF) model outperformed the other five machine learning algorithms. The RF model demonstrated accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, and AUC (95% CI) values of 0.792 (0.762-0.823), 0.904 (0.835-0.973), 0.759 (0.731-0.787), 0.221 (0.186-0.256), 0.974 (0.967-0.982), 0.353 (0.306-0.399), and 0.834 (0.696-0.967), respectively, surpassing the performance of other models. Additionally, the calibration curve's Brier Score (95%) for the RF model reached the minimum value of 0.06256 (0.05753-0.06759). SHAP analysis provided independent explanations, reaffirming the critical clinical factors associated with the risk of metastasis in OCCC patients. CONCLUSIONS: This study successfully established a precise predictive model for OCCC patient metastasis using machine learning techniques, offering valuable support to clinicians in making informed clinical decisions.

Expression of nerve growth factor carried by pseudotyped lentivirus improves neuron survival and cognitive functional recovery of post-ischemia in rats.

AIMS: Nerve growth factor (NGF) has been reported to prevent neuronal damage and contributes to the functional recovery in animal brain injury models and human ischemic disease as well. We aimed to investigate a potential therapeutic effect of NGF gene treatment in ischemic stroke and to estimate the functional recovery both at the cellular and cognitive levels in an ischemia rat model. METHODS: After microinjection of pseudolentivirus-delivered ß-NGF into an established ischemic stroke model in rats (tMCAO), we estimated neuronal cell apoptosis with TUNEL labeling and neurogenesis by cell proliferation marker Ki67 staining in both ischemic core and penumbra of striatum. Furthermore, we used behavioral functional tests, Morris water maze performance, to evaluate cognitive functional recovery in vivo and propose a potential underlying mechanism. RESULTS: We found that pseudolentivirus-mediated delivery of ß-NGF gene into the brain induced high expression in striatum of the infarct core area after ischemia in rats. The ß-NGF overexpression in the striatal infarction core after ischemia not only improved neuronal survival by reducing cell apoptosis and increasing cell proliferation, but also rescued cognitive functional impairment through upregulation of GAP-43 protein expression in tMCAO rat model of ischemia. CONCLUSION: This study demonstrates a potential ß-NGF gene therapy by utilization of pseudolentivirus in ischemia and indicates future applications of NGF gene treatment in ischemic patients.

[The effect of simvastatin on the regeneration of sciatic nerve with crush injury in rats].

AIM: To explore the effect of Simvastatin on the regeneration of sciatic nerve with crush injury in rats. METHODS: Animals were randomized into the following experimental groups: Simvastatin-treated, vehicle and sham-operated groups. Sciatic nerves with crush injury were performed. After surgery, the functional evaluation of nerve recovery, electrophysiologic assessment, histological assessment, serum IL-6 and lipid were performed. RESULTS: The toe spread index of Simvastatin-treated rats after operation was higher significantly than vehicle rats at 5 d and 8 d (P<0.05). CMAP was higher and NCV was faster (P < 0.05). The serum IL-6 at 5 d of post-operation was significant lower (P < 0.05). Total serum cholesterol of Simvastatin-treated animals was higher than that of other animals (P < 0.05) at 2 weeks of post-operation. The histological analysis showed that the numbers of myelinated axons and the thickness of myelin sheath of Simvastatin-treated crush injury animals at 4 weeks of post-operation were more than that of vehicle animals. CONCLUSION: The present study showed that Simvastatin could promote the regeneration of the sciatic nerve after crush injury in rats, partly through inhibiting immune and inflammatory responses and making the balance of serum cholesterol during these processes.