The predictive value of p53, Ki-67 and angiogenetic factors in primary hypopharyngeal carcinoma

A machine learning model for predicting the three-year survival status of patients with hypopharyngeal squamous cell carcinoma using multiple parameters

OBJECTIVE

This study aimed to establish a model for predicting the three-year survival status of patients with hypopharyngeal squamous cell carcinoma using artificial intelligence algorithms.

METHOD

Data from 295 patients with hypopharyngeal squamous cell carcinoma were analysed retrospectively. Training sets comprised 70 per cent of the data and test sets the remaining 30 per cent. A total of 22 clinical parameters were included as training features. In total, 12 different types of machine learning algorithms were used for model construction. Accuracy, sensitivity, specificity, area under the receiver operating characteristic curve and Cohen's kappa co-efficient were used to evaluate model performance.

RESULTS

The XGBoost algorithm achieved the best model performance. Accuracy, sensitivity, specificity, area under the receiver operating characteristic curve and kappa value of the model were 80.9 per cent, 92.6 per cent, 62.9 per cent, 77.7 per cent and 58.1 per cent, respectively.

CONCLUSION

This study successfully identified a machine learning model for predicting three-year survival status for patients with hypopharyngeal squamous cell carcinoma that can offer a new prognostic evaluation method for the clinical treatment of these patients.

Characterization of the Expression of Angiogenic Factors in Cutaneous Squamous Cell Carcinoma of Domestic Cats

Cutaneous squamous cell carcinoma (CSCC) is a common malignant skin cancer with a significant impact on health, and it is important to determine the degree of reliance of CSCC on angiogenesis for growth and metastasis. Major regulators of angiogenesis are the vascular endothelial growth factor (VEGF) family and their associated receptors. Alternative pre-mRNA splicing produces multiple isoforms of VEGF-A and PLGF with distinct biological properties. Several studies highlight the function of VEGF-A in CSCC, but there are no studies of the different isoforms of VEGF-A and PLGF for this neoplasm. We characterized the expression of three isoforms of VEGF-A, two isoforms of PLGF, and their receptors in cat CSCC biopsies compared to normal haired skin (NHS). Although our results revealed no significant changes in transcript levels of panVEGF-A or their isoforms, the mRNA levels of PLGF I and the receptors Flt-1 and KDR were downregulated in CSCC compared to NHS. Differences were observed in ligand:receptor mRNA expression ratio, with the expression of VEGF-A relative to its receptor KDR higher in CSCC, which is consistent with our hypothesis and prior human SCC studies. Immunolocalization in tissue showed increased expression of all measured factors and receptors in tumor cells compared to NHS and surrounding vasculature. We conclude that the factors measured may play a pivotal role in CSCC growth, although further studies are needed to clarify the role of angiogenic factors in feline CSCC.

Immunohistochemical Expression of Vascular Endothelial Growth Factor and Vascular Endothelial Growth Factor Receptor Associated with Tumor Cell Proliferation in Canine Cutaneous Squamous Cell Carcinomas and Trichoepitheliomas

The expression of 5 markers associated with angiogenesis was studied in canine squamous cell carcinomas (SCCs) ( n = 19) and canine trichoepitheliomas (TCPs) ( n = 24). SCCs were assigned histologic grades, and tissue sections from both tumor types were immunohistochemially stained for the expression of vascular endothelial growth factor (VEGF), vascular endothelial growth factor receptor-2 (VEGFR-2), as well as intratumoral microvessel density (iMVD), tumor proliferation index (PI), and tumor apoptotic index (AI), using antibodies against VEGF, VEGFR-2, von Willebrand's factor, Ki-67 antigen, and the terminal deoxynucleotidyl transferase-mediated 2′-deoxyuridine 5′-triphosphate endlabeling method (TUNEL), respectively. VEGF and VEGFR-2 were detected in 17/19 (89.4%) and 19/19 (100%) SCCs and in 17/24 (70.8%) and 20/24 (83.3%) TCPs, respectively. In SCCs, there was substantial correlation between histologic grade and PI ( r = 0.51); and moderate correlation between VEGF and histologic grade ( r = 0.43), VEGFR-2 and histologic grade ( r = 0.47), VEGF and PI ( r = 0.47), and VEGFR-2 and PI ( r = 0.47) (Spearman rank correlation coefficient). In TCPs, there was substantial correlation between VEGF and PI ( r = 0.51) and a moderate correlation between VEGFR-2 and iMVD ( r = 0.36). The median iMVD of SCCs (15.5) was significantly higher than the median iMVD of TCPs (9.05) ( P value < .05). It was concluded that VEGF and VEGFR-2 may promote tumor cell proliferation in TCPs and SCCs. An autocrine pathway for VEGF probably operates in canine SCCs and TCPs, as VEGF and VEGFR-2 expression was found in most tumors and was associated with evidence for tumor cell proliferation.

Immunohistochemical expression of vascular endothelial growth factor and vascular endothelial growth factor receptor in canine cutaneous fibrosarcomas

The expression of five markers associated with tumour angiogenesis, proliferation and apoptosis was studied in 24 canine cutaneous fibrosarcomas. Tumours were assigned histological grades and were immunohistochemically evaluated for the expression of vascular endothelial growth factor (VEGF) and vascular endothelial growth factor receptor-2 (VEGFR-2). Additionally, intra-tumour microvessel density (iMVD) was assessed by immunohistochemical labelling for expression of von Willebrand factor (vWf) and tumour proliferation index (PI) was measured following labelling of Ki-67 antigen. Finally, tumour apoptotic index (AI) was determined by application of the terminal deoxynucleotidyl transferase (TdT)-mediated dUTP end-labelling method (TUNEL). VEGF and VEGFR-2 expression were detected in 22/24 (92%) and 24/24 (100%) of fibrosarcomas, respectively. There was correlation between VEGF and VEGFR-2 expression (r = 0.51) and between histological grade and PI (r = 0.82). A significant difference in PI between tumours of different histological grade was found (P < 0.05). The median PI in grade 2 and 3 tumours (30.6 and 54.7, respectively) was significantly higher than in grade 1 tumours (6.4). Therefore, only PI correlates significantly with the histological grade of canine cutaneous fibrosarcomas. The potential for autocrine activity for VEGF exists in canine cutaneous fibrosarcomas, as VEGF and VEGFR-2 expression was found in most tumours.