Functionally impactful TP53 mutations are associated with increased risk of extranodal extension in clinically advanced oral squamous cell carcinoma.

BACKGROUND: The treatment of advanced oral squamous cell carcinoma (OSCC) is a clinical challenge because it is unclear which therapeutic approaches are the best for this highly heterogeneous group of patients. Because TP53 mutations are the most common genetic event in these tumors, the authors investigated whether they could represent an ancillary biomarker in the management of advanced OSCC. METHODS: The TP53 gene was sequenced in 78 samples from patients with advanced OSCC who received treatment at 2 institutions located in the United States and Brazil. TP53 mutations were classified according to an in-silico impact score (the evolutionary action score of p53 [EAp53]), which identifies mutations that have greater alterations of p53 protein function (high-risk). Associations between TP53 mutation status/characteristics and clinicopathologic characteristics were investigated. The relevant findings were validated in silico by analyzing 197 samples from patients with advanced OSCC from The Cancer Genome Atlas. RESULTS: No differences in clinical outcomes were detected between patients with TP53-mutant and wild-type TP53 disease. However, patients who had tumors carrying high-risk TP53 mutations had a significantly increased risk of developing extranodal extension (ENE) compared with those who had wild-type TP53-bearing tumors. The increased chances of detecting ENE among patients who had high-risk TP53 mutations was validated among patients with advanced OSCC from The Cancer Genome Atlas cohort. CONCLUSIONS: High-risk TP53 mutations are associated with an increased chance of detecting ENE in patients with advanced OSCC. Because ENE is 1 of the major factors considered for OSCC patient management, TP53 mutation status may represent a potential ancillary biomarker for treatment decisions regarding postoperative adjuvant therapy.

Machine learning and magnetic resonance imaging radiomics for predicting human papilloma virus status and prognostic factors in oropharyngeal squamous cell carcinoma.

BACKGROUND: We attempted to predict pathological factors and treatment outcomes using machine learning and radiomic features extracted from preoperative magnetic resonance imaging (MRI) of oropharyngeal squamous cell carcinoma (OPSCC) patients. METHODS: The medical records and imaging data of 155 patients who were diagnosed with OPSCC were analyzed retrospectively. RESULTS: The logistic regression model showed that the area under the receiver operating characteristic curve (AUC) of the model was 0.792 in predicting human papilloma virus (HPV) status. The LightGBM model showed an AUC of 0.8333 in predicting HPV status. The performance of the logistic model in predicting lymphovascular invasion, extracapsular nodal spread, and metastatic lymph nodes showed AUC values of 0.7871, 0.6713, and 0.6638, respectively. In predicting disease recurrence, the LightGBM model showed an AUC of 0.8571. In predicting patient death, the logistic model showed an AUC of 0.8175. CONCLUSIONS: A machine learning model using MRI radiomics showed satisfactory performance in predicting pathologic factors and treatment outcomes of OPSCC patients.