Umeå University's logo

Locoregional recurrences and distant metastases are major problems for patients with squamous cell carcinoma of the head and neck (SCCHN). Because SCCHN is a heterogeneous group of tumours with varying characteristics, the present study concentrated on the subgroup of squamous cell carcinoma of the oral tongue (SCCOT) to investigate the use of machine learning approaches to predict the risk of recurrence from routine clinical data available at diagnosis. The approach also identified the most important parameters that identify and classify recurrence risk. A total of 66 patients with SCCOT were included. Clinical data available at diagnosis were analysed using statistical analysis and machine learning approaches. Tumour recurrence was associated with T stage (P=0.001), radiological neck metastasis (P=0.010) and diabetes (P=0.003). A machine learning model based on the random forest algorithm and with attendant explainability was used. Whilst patients with diabetes were overrepresented in the SCCOT cohort, diabetics had lower recur‑ rence rates (P=0.015 after adjusting for age and other clinical features) and an improved 2‑year survival (P=0.025) compared with non‑diabetics. Clinical, radiological and histological data available at diagnosis were used to establish a prognostic model for patients with SCCOT. Using machine learning to predict recurrence produced a classification model with 71.2% accuracy. Notably, one of the findings of the feature importance rankings of the model was that diabetics exhibited less recur‑ rence and improved survival compared with non‑diabetics, even after accounting for the independent prognostic variables of tumour size and patient age at diagnosis. These data imply that the therapeutic manipulation of glucose levels used to treatdiabetes may be useful for patients with SCCOT regardless of their diabetic status. Further studies are warranted to investigatethe impact of diabetes in other SCCHN subtypes.

Background: Patients with squamous cell carcinoma of the head and neck (SCCHN) have a high-risk of recurrence. We aimed to develop machine learning methods to identify transcriptomic and proteomic features that provide accurate classification models for predicting risk of early recurrence in SCCHN patients.

Methods: Clinical, genomic, transcriptomic and proteomic features distinguishing recurrence risk were examined in SCCHN patients from The Cancer Genome Atlas (TCGA). Recurrence within one year after treatment was classified as high-risk and no recurrence as low-risk.

Results: No significant differences in individual clinicopathological characteristics, mutation profiles or mRNA expression patterns were seen between the groups using conventional statistical analysis. Using the machine learning algorithm, extreme gradient boosting (XGBoost), ten proteins (RAD50, 4E-BP1, MYH11, MAP2K1, BECN1, NF2, RAB25, ERRFI1, KDR, SERPINE1) and five mRNAs (PLAUR, DKK1, AXIN2, ANG and VEGFA) made the greatest contribution to classification. These features were used to build improved models in XGBoost, achieving the best discrimination performance when combining transcriptomic and proteomic data, providing an accuracy of 0.939 and an Area Under the ROC Curve (AUC) of 0.951.

Conclusions: This study highlights machine learning to identify transcriptomic and proteomic factors that play important roles in predicting risk of recurrence in patients with SCCHN and to develop such models by iterative cycles to enhance their accuracy, thereby aiding the introduction of personalized treatment regimens.

Background: This exploratory, registry-based, cross-sectional study aimed to evaluate patients' health-related quality of life (HRQOL) in a subsite of oropharyngeal cancer: cancer of the base of the tongue (CBT).

Methods: CBT patients, treated with curative intent, completed the EORTC QLQ-C30 and QLQ-H&N35 questionnaires 15 months after diagnosis. The HRQOL of CBT patients was compared to reference scores from the general population and to that of tonsillar carcinoma patients.

Results: The 190 CBT patients scored significantly worse than members of the general population on most scales. CBT patients with human papilloma virus (HPV)-positive tumors had significantly better HRQOL on 8 of 28 scales than HPV-negative patients. Compared to 405 tonsillar carcinoma patients, CBT patients had significantly worse HRQOL on 8 of the 28 scales, the majority local head and neck related problems.

Conclusion: One year after treatment, CBT patients' HRQOL was significantly worse in many areas compared to that of the general population and slightly worse than that of tonsillar carcinoma patients.

Introduction: To compare data from preoperative positron emission tomography/computed tomography (PET/CT) with results of panscopy with biopsy and ultrasound with fine needle aspiration cytology (US-FNAC) on the same patients.

Methods: In this retrospective (2014-2016) study, we compared PET/CT results with the results from panscopy with biopsy and US-FNAC in patients suspected of head and neck malignancy treated at the University Hospital in Umea, Sweden.

Results: A 91.3% concordance was seen between results from PET/CT and panscopy with biopsy, whereas between PET/CT and US-FNAC the concordance was 89.1%.

Conclusions: The present data show the usefulness of PET/CT in the diagnosis of head and neck malignancies.

Studies have shown lower treatment-related morbidity when using transoral robotic surgery (TORS) compared to conventional surgery. Patients investigated for oro- and hypopharyngeal cancer (T1, T2) were compared concerning quality of life (QoL) after tonsillectomy and TORS using validated QoL questionnaires: QLQ-C30 and QLQ-H&N35. The patients treated with TORS showed a higher pain score and thus also a higher need for painkillers, whereas they had lower values on self-assessment of anxiety/depression using the Hospital Anxiety and Depression Scale score. The pre- and postoperative information given did not meet the expectations of the patients treated with conventional surgery. The present data show advantages of the TORS technique from the patients' perspective. Even if patients treated with TORS are in need of more painkilling treatment, they cope better with the long-term effects of treatment, as judged by self-assessment of anxiety and depression.

Background: The health-related quality of life (HRQOL) of tonsillar carcinoma survivors was explored to investigate any HRQOL differences associated with tumor stage and treatment. The survivors' HRQOL was also compared to reference scores from the population.

Methods: In this exploratory cross-sectional study patients were invited 15 months after their diagnosis and asked to answer two quality of life questionnaires (EORTC QLQ- C30, EORTC QLQ- HN35), 405 participated.

Results: HRQOL was associated with gender, with males scoring better than females on a few scales. Patients' HRQOL was more associated with treatment than tumor stage. Patients' HRQOL was worse than that in an age- and sex-matched reference group from the normal population, the largest differences were found for problems with dry mouth followed by problems with sticky saliva, senses, swallowing and appetite loss.

Conclusions: The tonsillar carcinoma patients had a worse HRQOL compared to the general population one year after treatment.

Objective: To use alternative quantitation approaches to clarify the clinical implication of programmed cell death ligand 1 (PD‐L1) in squamous cell carcinoma of the oral tongue (SCCOT).

Materials and Methods: Ventana SP263 immunohistochemistry assay and a multiplicative QuickScore method were applied to quantify PD‐L1 in tumor and surrounding immune cells from 101 patients with SCCOT. Tumor‐infiltrating immune cells were estimated from bulk tissue transcriptional profiles of 25 patients. Circulating PD‐L1 levels were measured in serum from 30 patients using an electrochemiluminescence assay platform.

Results: We found higher tumor cell PD‐L1 levels in females than males (p  = .019). For patients with low PD‐L1 in tumor cells, better survival was seen in males than females (overall survival p  = .021, disease‐free survival p  = .020). Tumor‐infiltrating natural killer T cells, immature dendritic cells, and M1 macrophages were positively associated with tumor cell PD‐L1 (p  < .05).

Conclusions: Our data confirmed the significance of gender on tumor cell PD‐L1 expression and demonstrated combined effects of gender and PD‐L1 levels on clinical outcome in patients with SCCOT. The data also indicated the involvement of specific immune cell types in PD‐L1‐regulated immune evasion.

Background The incidence of squamous cell carcinoma of the oral tongue (SCCOT) is increasing in people under age 40. There is an urgent need to identify prognostic markers that help identify young SCCOT patients with poor prognosis in order to select these for individualized treatment. Materials and methods To identify genetic markers that can serve as prognostic markers for young SCCOT patients, we first investigated four young (<= 40 years) and five elderly patients (>= 50 years) using global RNA sequencing and whole-exome sequencing. Next, we combined our data with data on SCCOT from the cancer genome atlas (TCGA), giving a total of 16 young and 104 elderly, to explore the correlations between genomic variations and clinical outcomes. Results In agreement with previous studies, we found that SCCOT from young and elderly patients was transcriptomically and also genomically similar with no significant differences regarding cancer driver genes, germline predisposition genes, or the burden of somatic single nucleotide variations (SNVs). However, a disparate copy number variation (CNV) was found in young patients with distinct clinical outcome. Combined with data from TCGA, we found that the overall survival was significantly better in young patients with low-CNV (n = 5) compared to high-CNV (n = 11) burden (P = 0.044). Conclusions Copy number variation burden is a useful single prognostic marker for SCCOT from young, but not elderly, patients. CNV burden thus holds promise to form an important contribution when selecting suitable treatment protocols for young patients with SCCOT.

Immune cells and cytolytic activity within the tumor microenvironment are being intensively studied. Through transcriptome profiling, immune cell enumeration using the xCell tool and cytolytic activity quantification according to granzyme A (GZMA) and perforin (PRF1) mRNA levels, we investigated immunoreactivity in tumor and/or tumor‐free tongue tissue samples from 31 patients with squamous cell carcinoma of the oral tongue and 14 healthy individuals (control tongue tissues). We found significantly altered immune cell compositions (p < 0.001) and elevated cytolytic activity (p < 0.001) in tumor compared to tumor‐free samples, and altered infiltration of a subset of immune cells (e.g. CD8⁺ T cells, p < 0.01) as well as increased cytolytic activity (p < 0.001) in tumor‐free compared to control samples. Controlling for patient age at diagnosis and tumor stage, Cox regression analysis showed that high cytolytic activity in tumor‐free samples associated with improved disease‐free survival (hazard ratio= 4.20, 95% CI = 1.09–16.20, p = 0.037). However, the degree of cytolytic activity in tumor samples did not provide prognostic information. Taken together, our results show the presence of cancer‐related immune responses in clinically tumor‐free tongue in patients with squamous cell carcinoma of the oral tongue. Measuring cytolytic activity in tumor‐free tongue samples contralateral to tumor might thus be an effective approach to predict clinical outcome.

Objectives: As tumour spread is a complicating event for malignant salivary gland tumours, we decided to study factors related to cell adhesion and lymph vessel formation in two of the three most common malignant salivary gland tumours, mucoepidermoid carcinoma (MEC) and adenoid cystic carcinoma (ACC), to clarify the clinical relevance and potential usefulness of these factors. We also included a group of polymorphous adenocarcinoma (PAC) as this tumour, in common with ACC often shows perineural growth, but in contrast to ACC has an overall good prognosis.

Material and methods: Eighteen patients with ACC, 15 with MEC, and six with PAC were included. Protein expression of podoplanin and E‐cadherin was evaluated as percentage of cells expressing the protein and intensity of expression. Ki‐67 expression was included in the study as a marker of proliferative activity.

Results: Looking at podoplanin, significantly more ACCs were high expressing compared with both MECs (P = .001) and PACs (P = .028). Also when looking at Ki‐67 expression, significantly more ACCs were high expressing compared with MECs (P = .003). Significantly better survival was also seen for ACCs with high podoplanin (P = .022) and low E‐cadherin expression (P = .021), respectively.

Conclusions: Our findings show that ACCs express significantly higher levels of podoplanin compared with both MECs and PACs and that high levels are correlated to better survival. Even though the group of PACs analysed was small, these tumours, despite their tendency to perineural spread, which they have in common with ACC, differ from ACCs concerning expression of factors with a known connection to tumour spread.