Risk stratification models in human papillomavirus-associated oropharyngeal squamous cell carcinoma: the Nova Scotia distribution

Spatially-aware clustering improves AJCC-8 risk stratification performance in oropharyngeal carcinomas

OBJECTIVE

Evaluate the effectiveness of machine learning tools that incorporate spatial information such as disease location and lymph node metastatic patterns-of-spread, for prediction of survival and toxicity in HPV+ oropharyngeal cancer (OPC).

MATERIALS & METHODS

675 HPV+ OPC patients that were treated at MD Anderson Cancer Center between 2005 and 2013 with curative intent IMRT were retrospectively collected under IRB approval. Risk stratifications incorporating patient radiometric data and lymph node metastasis patterns via an anatomically-adjacent representation with hierarchical clustering were identified. These clusterings were combined into a 3-level patient stratification and included along with other known clinical features in a Cox model for predicting survival outcomes, and logistic regression for toxicity, using independent subsets for training and validation.

RESULTS

Four groups were identified and combined into a 3-level stratification. The inclusion of patient stratifications in predictive models for 5-yr Overall survival (OS), 5-year recurrence free survival, (RFS) and Radiation-associated dysphagia (RAD) consistently improved model performance measured using the area under the curve (AUC). Test set AUC improvements over models with clinical covariates, was 9 % for predicting OS, and 18 % for predicting RFS, and 7 % for predicting RAD. For models with both clinical and AJCC covariates, AUC improvement was 7 %, 9 %, and 2 % for OS, RFS, and RAD, respectively.

CONCLUSION

Including data-driven patient stratifications considerably improve prognosis for survival and toxicity outcomes over the performance achieved by clinical staging and clinical covariates alone. These stratifications generalize well to across cohorts, and sufficient information for reproducing these clusters is included.

Pretreatment pain predicts perineural invasion in patients with head and neck squamous cell carcinoma

OBJECTIVES

Perineural invasion (PNI) in head and neck cancer (HNC) is a distinct pathological feature used to indicate aggressive tumor behavior and drive treatment strategies. Our study examined the prevalence and predictors of PNI in HNC patients stratified by tumor site.

STUDY DESIGN AND METHODS

A retrospective analysis of head and neck squamous cell carcinoma (HNSCC) patients who underwent surgical resection at the University of Pittsburgh Medical Center between 2015 and 2018 was performed. Pretreatment pain was assessed at least 1 week before surgery using the Functional Assessment of Cancer Therapy-Head and Neck (FACT-H&N). Demographics, clinical characteristics, and concomitant medications were obtained from medical records. Patients with cancers at the oropharynx and non-oropharynx (i.e., cancer at oral cavity, mandible, larynx) sites were separately analyzed. Tumor blocks were obtained from 10 patients for histological evaluation of intertumoral nerve presence.

RESULTS

A total of 292 patients (202 males, median age = 60.94 ± 11.06) were assessed. Pain and PNI were significantly associated with higher T stage (p < 0.001) and tumor site (p < 0.001); patients with non-oropharynx tumors reported more pain and had a higher incidence of PNI compared to oropharynx tumors. However, multivariable analysis identified pain as a significant variable uniquely associated with PNI for both tumor sites. Evaluation of nerve presence in tumor tissue showed 5-fold higher nerve density in T2 oral cavity tumors compared to oropharyngeal tumors.

CONCLUSIONS

Our study finds that PNI is associated with pretreatment pain and tumor stage. These data support the need for additional research into the impact of tumor location when investigating targeted therapies of tumor regression.