RESUMEN
OBJECTIVE: This study seeks to construct a machine learning model that merges clinical characteristics with ultrasound radiomic analysis-encompassing both the intratumoral and peritumoral-to predict the status of axillary lymph nodes in patients with early-stage breast cancer. METHODS: The study employed retrospective methods, collecting clinical information, ultrasound data, and postoperative pathological results from 321 breast cancer patients (including 224 in the training group and 97 in the validation group). Through correlation analysis, univariate analysis, and Lasso regression analysis, independent risk factors related to axillary lymph node metastasis in breast cancer were identified from conventional ultrasound and immunohistochemical indicators, and a clinical feature model was constructed. Additionally, features were extracted from ultrasound images of the intratumoral and its 1-5 mm peritumoral to establish a radiomics feature formula. Furthermore, by combining clinical features and ultrasound radiomics features, six machine learning models (Logistic Regression, Decision Tree, Support Vector Machine, Extreme Gradient Boosting, Random Forest, and K-Nearest Neighbors) were compared for diagnostic efficacy, and constructing a joint prediction model based on the optimal ML algorithm. The use of Shapley Additive Explanations (SHAP) enhanced the visualization and interpretability of the model during the diagnostic process. RESULTS: Among the 321 breast cancer patients, 121 had axillary lymph node metastasis, and 200 did not. The clinical feature model had an AUC of 0.779 and 0.777 in the training and validation groups, respectively. Radiomics model analysis showed that the model including the Intratumor +3 mm peritumor area had the best diagnostic performance, with AUCs of 0.847 and 0.844 in the training and validation groups, respectively. The joint prediction model based on the XGBoost algorithm reached AUCs of 0.917 and 0.905 in the training and validation groups, respectively. SHAP analysis indicated that the Rad Score had the highest weight in the prediction model, playing a significant role in predicting axillary lymph node metastasis in breast cancer. CONCLUSION: The predictive model, which integrates clinical features and radiomic characteristics using the XGBoost algorithm, demonstrates significant diagnostic value for axillary lymph node metastasis in breast cancer. This model can provide significant references for preoperative surgical strategy selection and prognosis evaluation for breast cancer patients, helping to reduce postoperative complications and improve long-term survival rates. Additionally, the utilization of SHAP enhancing the global and local interpretability of the model.
Asunto(s)
Axila , Neoplasias de la Mama , Ganglios Linfáticos , Metástasis Linfática , Aprendizaje Automático , Humanos , Neoplasias de la Mama/diagnóstico por imagen , Neoplasias de la Mama/patología , Metástasis Linfática/diagnóstico por imagen , Femenino , Persona de Mediana Edad , Ganglios Linfáticos/diagnóstico por imagen , Ganglios Linfáticos/patología , Estudios Retrospectivos , Adulto , Valor Predictivo de las Pruebas , Anciano , Ultrasonografía Mamaria/métodos , RadiómicaRESUMEN
Background: Ferroptosis is an iron-dependent cell death, which is distinct from the other types of regulated cell death. Considerable studies have demonstrated that ferroptosis is involved in the biological process of various cancers. However, the role of ferroptosis in cervical cancer (CC) remains unclear. This study aims to explore the ferroptosis-related prognostic genes (FRPGs) expression profiles and their prognostic values in CC. Methods: The ferroptosis-related genes (FRGs) were obtained from The Cancer Genome Atlas (TCGA) and FerrDb databases. Core FRGs were determined by the Search Tool for the Retrieval of Interacting Genes (STRING) website. FRPGs were identified using univariate and multivariate Cox regressions, and the ferroptosis-related prognostic model was constructed. FRPGs were verified in clinical specimens. The relationship between FRPGs and tumor infiltrating immune cells were assessed through the CIBERSORT algorithm and the LM22 signature matrix. Bioinformatics functions of FRPGs were explored with the Database for Annotation, Visualization, and Integrated Discovery (DAVID). Results: Thirty-three significantly up-regulated and 28 down-regulated FRGs were screened from databases [P<0.05; false discovery rate (FDR) <0.05; and |log2 fold change (FC)| ≥2]. Twenty-four genes were found closely interacting with each other and regarded as hub genes (degree ≥3). Solute carrier family 2 member 1 (SLC2A1), carbonic anhydrases IX (CA9), and dual oxidase 1 (DUOX1) were identified as independent prognostic signatures for overall survival (OS) in a Cox regression. Time-dependent receiver operating characteristic (ROC) curves showed the predictive ability of the ferroptosis-related prognostic model, especially for 1-year OS [area under the curve (AUC) =0.76]. Consistent with the public data, our experiments demonstrated that the mRNA levels of SLC2A1 and DUOX1, and the protein levels of SLC2A1, DUOX1, and CA9 were significantly higher in the tumor tissues. Further analysis showed that there was a significant difference in the proportion of tumor infiltrating immune cells between the low- and high-risk group based on our prognostic model. The function enrichment of FRPGs was explored by applying Gene Ontology (GO) enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses. Conclusions: In this study, the features of FRPGs in CC were pictured. The results implicated that targeting ferroptosis may be a new reliable biomarker and an alternative therapy for CC.
RESUMEN
Three new neo-5,10-seco-clerodane diterpenoids (1-3), four previously undescribed ethoxy/methoxy acetal analogues (4-7), one new etherified labdane diterpenoid (8), and seven known diterpenoids (9-15) were isolated from the whole plant of Schnabelia terniflora. Their structures were established on the basis of extensive spectroscopic analysis, single-crystal X-ray diffraction data, calculated electronic circular dichroism (ECD), and Mo2(OAc)4-induced circular dichroism. Compounds 2 and 3 represent the first examples of neo-5,10-seco-clerodane diterpenoids containing a 1H-pyrrole-2,5-dione and a pyrrolidine-2,5-dione moiety, respectively. A plausible biosynthetic pathway for 1-3 is proposed. All diterpenoids were evaluated for their cytotoxic activity against non-small-cell lung cancer lines (A549 and H460) and gastric cancer lines (HGC27 and AGS). Among them, 2 and 14 showed moderate cytotoxicity against four cell lines.