Prediction of radiation pneumonia after radiotherapy for esophageal cancer using a unified fractional dosiomics combined model.

OBJECTIVE: This study aimed to construct an optimal model to predict radiation pneumonia (RP) after radiotherapy for esophageal cancer using unified fractional dosiomics and to investigate the improvements in the prediction efficiency of each model for RP. METHODS: The clinical data, DVH, pre-treatment CT, and dose distribution of 182 patients were retrospectively analyzed.The independent risk factors were screened using univariate and multivariate logistic regression. The mutual information (MI),least absolute shrinkage and selection operator (LASSO), and recursive feature elimination (RFE) methods were used to screen the omics features. The AUC values of ROC, calibration curves, and clinical decision curves were calculated to evaluate the efficacy and trends of each model. RESULTS: The AUC of dosiomics model were 0.783 and 0.760 in the training and test cohorts, higher than 0.585 and 0.579 in the training and test cohorts of the DVH model. The AUC value of the R + D combination was the highest, reaching 0.833. The combined R + D model had a better calibration degree than the other models (mean absolute error = 0.018) and better net benefit in clinical decision-making. CONCLUSIONS: The radiomics combined dosiomics model was the best combined model to predict RP after radiotherapy for esophageal cancer. The dosiomics model could cover the efficiency of the DVH model and significantly improve the efficiency of the combined model.In the future, we will include other centers for further verification. ADVANCES IN KNOWLEDGE: For the first time, this study used CT images combined dose distribution to predict the occurrence of radiation pneumonitis after radiotherapy for esophageal cancer.

Synchronous triple primary malignant tumours in the bladder, prostate, and lung harbouring TP53 and MEK1 mutations accompanied with severe cardiovascular diseases: A case report.

Although the incidence of multiple primary malignancies (MPMs) is increasing, synchronous triple primary malignant tumours with prostate, bladder and lung is rarely reported. Gene mutation is thought to be a reason for MPMs, and severe cardiovascular diseases may interrupt the cancer treatment. Here we reported a 64-year-old male patient with synchronous triple primary malignant tumours of the bladder urothelial carcinoma, prostate adenocarcinoma, and non-small cell lung cancer (NSCLC) with mutations in TP53 and MEK1, all the three malignancies were diagnosed within 10 days. Although being interrupted by severe cardiovascular diseases (including myocardial infarction, venous thrombosis, and aneurism of the aortic root), he was successfully treated with radical cystoprostatectomy, chemotherapy plus pembrolizumab (a PD-1 antibody), and radiotherapy of the lung lesion, followed by maintenance monotherapy of pembrolizumab, overall survival was more than 26 months. In conclusion, a patient of synchronous triple primary malignant tumours with prostate, bladder, and lung harbouring TP53 and MEK1 mutations accompanied with severe cardiovascular diseases was treated successfully, which may suggest that comprehensive treatment, especially radical treatment such as operation and radiation, is very important for MPMs.