Machine Learning Incorporating Host Factors for Predicting Survival in Head and Neck Squamous Cell Carcinoma Patients.

Prognostication for cancer patients is integral for patient counseling and treatment planning, yet providing accurate prediction can be challenging using existing patient-specific clinical indicators and host factors. In this work, we evaluated common machine learning models in predicting head and neck squamous cell carcinoma (HNSCC) patients' overall survival based on demographic, clinical features and host factors. We found random survival forest had best performance among the models evaluated, which achieved a C-index of 0.729 and AUROC of 0.792 in predicting two-year overall survival. In addition, we verified that host factors are independently predictive of HNSCC overall survival, which improved the C-index by a margin of 0.026 and the AUROC by 0.034. Due to the strong correlation among host factors, we showed that proper dimension reduction is an important step before their incorporation into the machine learning models, which provides a host factor score reflecting the patients' nutrition and inflammation status. The score by itself showed excellent discriminating capacity with the high-risk group having a hazard ratio of 3.76 (1.93-7.32, p < 0.0001) over the low-risk group. The hazard ratios were further improved to 7.41 (3.66-14.98, p < 0.0001) by the random survival forest model after including demographic and clinical features.

MKP-1 is required to limit myeloid-cell mediated oral squamous cell carcinoma progression and regional extension.

Mitogen-activated protein kinases (MAPKs) require MAPK phosphatases (MKPs) for deactivation of MAPK intracellular signaling. MKP-1 (encoded by Dusp1) is a key negative regulator of MAPKs and prior reports have indicated that MKP-1 regulates oral cancer-associated inflammation and leukocyte infiltration. OBJECTIVE: To determine the significance of myeloid-based expression of MKP-1 in oral cancer. METHODS: The Cancer Genome Atlas (TCGA) was used to address DUSP1 expression in oral squamous cell carcinoma (OSCC). Syngeneic and carcinogen-induced mouse models using global and myeloid-specific Dusp-1 deficient mice with immunophenotypic, histologic, and transcriptomic analyses and in vitro migration assays. RESULTS: Data from TCGA indicates the DUSP1 expression is inversely related to oral cancer burden and nodal involvement. Using murine models of OSCC, the role of MKP-1 signaling in tumor associated macrophages (TAMs) was assessed. Dusp1-deficient mice had increased tumor burden and TAM infiltrate with increased M2 macrophage polarization. Transcriptomic signatures of TAMs from Dusp1-deficent mice indicated a pro-metastatic phenotype as well as concomitant differences in myeloid-associated genes, cytokine/chemokine signaling, and Notch signaling consistent with tumor progression. In vitro and in vivo assays revealed mouse OSCC cells had a higher migration rate using TAM cell-free supernatant from Dusp1 deficiency mice compared to controls with enhanced regional cervical lymph node metastasis, respectively. To validate TAM studies using implantable mouse models, an OSCC progression model with conditional myeloid-specific Dusp-1 deficient mice demonstrated enhanced OSCC disease progression, characterized by advanced onset, histological stage, and tumor burden. CONCLUSION: Myeloid-based Dusp1-deficiency increases OSCC burden and metastasis through alteration in TAM recruitment, gene profile, and polarity suggesting that MKP-1 could be a viable target to reprogram TAM to limit local/regional OSCC extension.

Financial Counseling Is Associated with Reduced Financial Difficulty Scores in Head and Neck Cancer Patients Treated with Radiation Therapy.

BACKGROUND: Financial toxicity (FT) can be devastating to cancer patients, and solutions are urgently needed. We investigated the impact of financial counseling (FC) on FT in head and neck cancer (HNC) patients. METHODS: Via a single-institution database, we reviewed the charts of HNC patients who underwent definitive or post-operative radiotherapy, from October 2013 to December 2020. Of these patients, 387 had provided baseline and post-treatment information regarding financial difficulty. In July 2018, a dedicated financial counselor was provided for radiation therapy patients and we subsequently examined the impact of FC on financial difficulty scores. RESULTS: Following the hiring of a dedicated financial counselor, there was a significant increase in the proportion of patients receiving FC (5.3% vs. 62.7%, p < 0.0001). Compared with baseline scores, patients who did not undergo FC had a significant increase in reported financial difficulty at the end of treatment (p = 0.002). On the other hand, there was no difference in pre- and post-treatment scores in patients who had received FC (p = 0.588). After adjusting for gender and nodal status with a multiple linear regression model, FC was significantly associated with change in financial difficulty (ß = -0.204 ± 0.096, p = 0.035). On average, patients who received FC had a 0.2 units lower change in financial difficulty score as compared with those with the same gender and nodal stage but without FC. CONCLUSIONS: Providing a dedicated financial counselor significantly increased the proportion of HNC receiving FC, resulting in the stabilization of financial difficulty scores post-treatment. Based on a multiple linear regression model, FC was independently associated with reduced financial difficulty. The employment of a financial counselor may be a viable, hospital-based approach to begin to address FT in HNC.

Matched pair analysis for comparison of survival outcome of alternative regimens to standard three-weekly cisplatin-based concurrent chemoradiation of head and neck cancer.

BACKGROUND: To compare head and neck cancer (HNC) patients treated with three-weekly versus weekly cisplatin-based or other chemotherapy-based concurrent chemoradiation (CRT) and CRT with versus without induction chemotherapy (ICT) to investigate differences in overall survival (OS) and cancer-specific survival (CSS). METHODS: HNC patients treated with definitive or adjuvant CRT at Roswell Park Comprehensive Cancer Center between 2003 and 2017 were retrospectively reviewed. Propensity score matching was performed to obtain three sets of balanced matched pairs: three-weekly and weekly cisplatin CRT, three weekly and non-cisplatin CRT, CRT with and without ICT. Multivariate Cox regression and Kaplan-Meier analyses were used to estimate and compare survival outcomes. RESULTS: A total of 623 patients received either definitive (81%) or post-operative (19%) RT. Of these, 283 patients concurrently received three-weekly cisplatin (45%); 189 patients (30%) received weekly cisplatin; 151 patients (24%) received non-cisplatin regimen. Median follow-up was 55.4 months (interquartile range, 38.0-88.7). Patients who received CRT alone and those who received ICT and CRT had no difference in 5-year OS (51.5% and 41.0% respectively, P=0.53) and CSS (64.9% and 49.7% respectively, P=0.21). Compared to patients who received three-weekly cisplatin, patients who received weekly cisplatin had no difference in 5-year OS (59.3% vs. 54.1%, P=0.35) and CSS (70.3% vs. 62.4%, P=0.09); patients who received non-cisplatin CRT also had no difference in 5-year OS (54.5% vs. 58.3%, P=0.51) and CSS (67.5% vs. 64.7%, P=0.45). CONCLUSIONS: No significant difference in OS and CSS was observed in any of the three pairs of CRT regimens. ICT prior to CRT did not improve survival of CRT alone. Non-cisplatin and weekly cisplatin regimens did not prove to be inferior to the standard three-weekly cisplatin.

Matched pair analysis to evaluate weight loss during radiation therapy for head and neck cancer as a prognostic factor for survival.

BACKGROUND: One frequent consequence of radiation therapy (RT) for head and neck cancer (HNC) is weight loss (WL). HNC patients reportedly lose about 9% of their weight during treatment, regardless of pre-treatment WL and nutritional support. We investigated whether high WL during RT has an association with overall (OS) and cancer-specific survival (CSS). METHODS: We retrospectively reviewed weight during RT in HNC patients treated at Roswell Park Comprehensive Cancer Center between 2003 and 2017. High WL was defined as greater than or equal to the median WL. Logistic regression analysis was performed to identify predictors for WL during RT. Multivariate Cox regression and Kaplan-Meier analyses were used to estimate survival outcomes. Propensity score matching was performed to obtain balanced matched-pairs and compare survival outcomes. RESULTS: A total of 843 patients received either definitive (71%) or post-operative (29%) RT. Median follow-up was 53.6 months [interquartile range (IQR) 35.7-88.9]. Median WL was 5.8% (IQR 0.24-10.6) from baseline weight. Patients with high WL had better OS [hazard ratio (HR) 0.75, 95% confidence interval (CI), 0.61-0.93, P=0.01] and CSS (HR 0.71, 95% CI, 0.55-0.93, P=0.01). 258 matched-pairs were analyzed. Median follow-up was 54.8 months (IQR 35.8-90.4). Median OS was 39.2 months (IQR 21.4-75.7) for high WL versus 36.7 months (IQR 14.6-61.7) for low WL cohorts (P=0.047). CONCLUSIONS: Different from previous reports, this study shows that patients with less WL have worse OS. WL during RT may not be a reliable marker for worse prognosis. A better way to evaluate malnutrition in patients undergoing RT is warranted.

Role of Repeat PET/CT Imaging in Head and Neck Cancer Following Initial Incomplete PET/CT Response to Chemoradiation.

Despite waiting 13 weeks to perform a PET/CT scan after completion of chemoradiation for head and neck squamous cell carcinoma (HNSCC), equivocal findings are often found that make assessing treatment response difficult. This retrospective study examines the utility of a repeat PET/CT scan in HNSCC patients following an incomplete response on initial post-treatment imaging. For this cohort of 350 patients, initial PET/CT was performed 13 weeks after completion of treatment. For select patients with an incomplete response, repeat PET/CT was performed a median of 91 days later. Primary endpoints were conversion rate to complete response (CR) and the predictive values of repeat PET/CT imaging. Of 179 patients who did not have an initial complete response, 57 (32%) received a repeat PET/CT scan. Among these patients, 26 of 57 (48%) had a CR on repeat PET/CT. In patients with CR conversion, there were no cases of disease relapse. The sensitivity, specificity, PPV, and NPV for the repeat PET/CT for locoregional disease were 100%, 59%, 42%, and 100%. Repeat PET/CT in HNSCC patients with an incomplete post-treatment scan can be valuable in obtaining diagnostic clarity. This can reduce the incidence of unnecessary biopsies and neck dissections.

A Principal Component of Quality of Life Measures Is Associated with Survival for Head and Neck Cancer Patients Treated with Radiation Therapy.

BACKGROUND: Health-related quality of life (HRQOL) metrics can be associated with survival in head and neck cancer (HNC); however, the impact of HRQOL recovery and the relevant HRQOL domains regarding outcome are unclear. METHODS: Using a single-institution database, we retrospectively reviewed HNC patients treated with definitive or postoperative radiation therapy between 2013 and 2018. The recovery of individual HRQOL domains were determined by the ratio of the post-treatment to baseline scores. Univariate and Multivariate Cox regression were used to analyze survival outcomes. Principal component analysis was used to adjust for multicollinearity of HRQOL domains. RESULTS: In 218 HNC patients who received radiation therapy, median follow-up was 24.8 months (interquartile range (IQR) 14.5-32.0). Principal component analysis evaluating the recovery of HRQOL domains revealed two independent principal components (PC), PC1 and PC2. PC1, which received contributions from the functional domains; physical (PF), role (RF), emotional (EF), cognitive (CF), and global health status (GQOL) was significantly associated with disease-free (HR = 0.77, 95% CI 0.61-0.98, p = 0.034) and overall survival (HR = 0.76, 95% CI 0.65-0.91, p = 0.004) on multivariate analysis and PC2, had no correlation with outcome and was mainly represented by social functioning. Unplanned hospitalization was significantly associated with lower PC1 scores (ß = -0.997, Std. Error = 0.244, p < 0.001). CONCLUSION: Our study provides evidence that post-treatment recovery of HRQOL domains were associated with overall survival (OS) in HNC. PC1 is an attractive clinical tool to assess the recovery across multiple different HRQOL and the relationship with survival. Future prospective studies may identify patients who could benefit from additional rehabilitation based on PC1 score.

Association of significant financial burden with survival for head and neck cancer patients treated with radiation therapy.

OBJECTIVE: To assess the association between financial toxicity and survival in patients with head and neck cancer (HNC). MATERIALS AND METHODS: Using a single-institution database, we retrospectively reviewed HNC patients treated at Roswell Park Comprehensive Cancer Center treated with definitive or postoperative radiation therapy between 2013 and 2017. Kaplan-Meier method and log-rank tests were used to analyze survival outcomes. Propensity score matching on all clinically relevant baseline characteristics was performed to address selection bias. All statistical tests were two-sided and those less than 0.05 were considered statistically significant. RESULTS: Of a total of 284 HNC patients (age: median 61 years, IQR 55-67; 220 [77.5%] men), 204 patients (71.8%) received definitive radiation and 80 patients (28.2%) received adjuvant radiation. There were 41 patients (14.4%) who reported high baseline financial toxicity. Chemotherapy was used in 237 patients (83.5%). On multivariable analysis, those with high financial toxicity exhibited worse overall survival (hazards ratio [HR] 1.75, 95% confidence interval [CI] 1.05-2.94, p = 0.03) and cancer specific survival (HR 2.28, 95% CI 1.31-3.96, p = 0.003). On matched pair analysis of 66 patients, high financial toxicity remained associated with worse OS (HR 2.72, 95% CI 1.04-7.09, p = 0.04) and CSS (HR 3.75, 95% CI 1.22-11.5, p = 0.02). CONCLUSION: HNC patient reported baseline financial toxicity was significantly correlated with both decreased overall and cancer specific survival. These significant correlations held after match pairing. Further research is warranted to investigate the impact of financial toxicity in HNC and mitigate its risk.

Matched pair analysis to evaluate the impact of hospitalization during radiation therapy as an early marker of survival in head and neck cancer patients.

BACKGROUND: Complications from radiotherapy (RT) alone or combined with surgery and/or chemotherapy for head and neck cancer (HNC) sometimes necessitate hospitalization. Our aim was to evaluate the frequency, cause, and survival outcomes associated with hospitalizations in patients undergoing RT for HNC. PATIENTS AND METHODS: Using a retrospective single-institution database, we reviewed hospitalization records of HNC patients treated at Roswell Park Comprehensive Cancer Center with definitive or post-operative RT between 2003 and 2017. Patients who were admitted during treatment and within 90-days post-RT were identified. Multivariate analyses, Kaplan-Meier statistics, and analysis on propensity score matching were performed to obtain matched-pair, after matching baseline characteristics, such as age, gender, smoking, tumor staging, p16 status, and treatments received. RESULTS: 839 patients were eligible for analysis. Median follow-up was 34.8 months (Interquartile range [IQR] 15.6-64.8). 595 (71%) received definitive RT and 244 (29%) received adjuvant RT. Chemotherapy was used in 671 patients (80%). 171 patients (20%) had at least one hospitalization. Dehydration (40%) and fever (29%) were the most frequent causes of admission. Hospitalized patients had significantly worse overall survival (OS) (Hazards ratio [HR] 1.61, 95% CI 1.26-2.07, p < 0.001) and cancer-specific survival (CSS) (HR 1.45, 95% CI 1.07-1.95, p = 0.02). 163 matched pairs had median follow-up of 58.6 months (IQR 37.6-85.0). Median OS was 34.5 months (IQR 13.3-58.0) for hospitalized versus 44.2 months (IQR 20.3-78.7) for non-hospitalized patients (p = 0.01). CONCLUSION: This study reveals significantly worse OS and CSS for patients hospitalized during RT for HNC. Hospitalization may be an early marker for worse survival.

Ewing sarcoma of the thyroid: report of 2 cases and review of the literature.

BACKGROUND: Neuroendocrine tumors of the thyroid encompass a wide differential diagnosis. The most common is medullary thyroid carcinoma. One must consider other possibilities when a neuroendocrine thyroid tumor is calcitonin negative. We report 2 cases of Ewing sarcoma of the thyroid and discuss the differential diagnosis and workup of a calcitonin-negative neuroendocrine tumor of the thyroid. METHODS/RESULTS: This is a retrospective review of 2 patients diagnosed with Ewing sarcoma of the thyroid and a review of the literature. CONCLUSIONS: Ewing sarcoma of the thyroid is an exceedingly rare diagnosis, but should be included in the differential diagnosis for a thyroidal neuroendocrine lesion (especially in the absence of calcitonin). The use and interpretation of immunohistochemistry (IHC) and fluorescent in situ hybridization are essential in making the correct diagnosis.