Search

Abstract 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.

PurposeAlcohol consumption increases the risk of breast cancer and promotes cancer progression. Alcohol exposure could affect both processes of the mammary carcinogenesis, namely, the cell transformation and onset of tumorigenesis as well as cancer aggressiveness including metastasis and drug resistance/recurrence. However, the cellular and molecular mechanisms underlying alcohol tumor promotion remain unclear. There are four members of the mammalian p38 mitogen-activated protein kinase (MAPK) family, namely, p38α, p38β, p38γ and p38δ. We have previously demonstrated alcohol exposure selectively activated p38γ MAPK in breast cancer cells in vitro and in vivo. Pirfenidone (PFD), an antifibrotic compound approved for the treatment of idiopathic pulmonary fibrosis, is also a pharmacological inhibitor of p38γ MAPK. This study aimed to determine whether PFD is useful to inhibit alcohol-induced promotion of breast cancer.MethodsFemale adolescent (5 weeks) MMTV-Wnt1 mice were exposed to alcohol with a liquid diet containing 6.7% ethanol. Some mice received intraperitoneal (IP) injection of PFD (100 mg/kg) every other day. After that, the effects of alcohol and PFD on mammary tumorigenesis and metastasis were examined.ResultsAlcohol promoted the progression of mammary tumors in adolescent MMTV-Wnt1 mice. Treatment of PFD blocked tumor growth and alcohol-promoted metastasis. It also significantly inhibited alcohol-induced tumorsphere formation and cancer stem cell (CSC) population.ConclusionPFD inhibited mammary tumor growth and alcohol-promoted metastasis. Since PFD is an FDA-approved drug, the current findings may be helpful to re-purpose its application in treating aggressive breast cancer and alcohol-promoted mammary tumor progression.

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. [ABSTRACT FROM AUTHOR]