A machine learning approach for predicting radiation-induced hypothyroidism in patients with nasopharyngeal carcinoma undergoing tomotherapy.

The purpose of this study was to establish an integrated predictive model that combines clinical features, DVH, radiomics, and dosiomics features to predict RIHT in patients receiving tomotherapy for nasopharyngeal carcinoma. Data from 219 patients with nasopharyngeal carcinoma were randomly divided into a training cohort (n = 175) and a test cohort (n = 44) in an 8:2 ratio. RIHT is defined as serum thyroid-stimulating hormone (TSH) greater than 5.6 µU/mL, with or without a decrease in free thyroxine (FT4). Clinical features, 27 DVH features, 107 radiomics features and 107 dosiomics features were extracted for each case and included in the model construction. The least absolute shrinkage and selection operator (LASSO) regression method was used to select the most relevant features. The eXtreme Gradient Boosting (XGBoost) was then employed to train separate models using the selected features from clinical, DVH, radiomics and dosiomics data. Finally, a combined model incorporating all features was developed. The models were evaluated using receiver operating characteristic (ROC) curves and decision curve analysis. In the test cohort, the area under the receiver operating characteristic curve (AUC) for the clinical, DVH, radiomics, dosiomics and combined models were 0.798 (95% confidence interval [CI], 0.656-0.941), 0.673 (0.512-0.834), 0.714 (0.555-0.873), 0.698 (0.530-0.848) and 0.842 (0.724-0.960), respectively. The combined model exhibited higher AUC values compared to other models. The decision curve analysis demonstrated that the combined model had superior clinical utility within the threshold probability range of 1% to 79% when compared to the other models. This study has successfully developed a predictive model that combines multiple features. The performance of the combined model is superior to that of single-feature models, allowing for early prediction of RIHT in patients with nasopharyngeal carcinoma after tomotherapy.

PYHIN1 correlates with CD8+ T cells infiltration and confers good patient survival in oral cancer.

BACKGROUND/PURPOSE: Immunotherapy has become a research hotspot and is used for head and neck cancer treatment. This research aims to explore the prognostic value of PYHIN1 in oral cancer and the relationship between PYHIN1 and cancer immunity. MATERIALS AND METHODS: The expression of PYHIN1 in clinical specimens was evaluated by bioinformatics analyses and immunohistochemistry. RESULTS: Gene ontology term enrichment analyses and gene set enrichment analyses showed the involvement of PYHIN1 in the modulation of adaptive immunity-associated signaling according to The Cancer Genome Atlas database and Gene Expression Omnibus dataset. Interestingly, the correlation analyses in The Cancer Genome Atlas database revealed a positive correlation between PYHIN1 expression and activated CD8+ T cells infiltration and a negative correlation between PYHIN1 expression and tumor purity. Moreover, activated CD8+ T cells infiltration predicted good patient survival and was negatively correlated with tumor purity. Importantly, PYHIN1 expression was negatively correlated with the pathological stage and was positively associated with a good prognosis in patients with oral cancer. The data obtained from the Gene Expression Omnibus dataset and immunohistochemistry confirmed the positive association between PYHIN1 and CD8+ T cells infiltration in oral cancer tissues. CONCLUSION: We conclude that PYHIN1 is an indicator of cancer immunity, and is an independent prognostic factor that may be an alternative target for oral cancer treatment.