Individualized risk prediction of outcomes for oral cavity cancer patients

Abstract

Background Optimal management of oral cancer relies upon accurate and individualized risk prediction of relevant clinical outcomes. Individualized prognostic calculators have been developed to guide patient–physician communication and treatment-related decision-making. However it is critical to scrutinize their accuracy prior to integrating into clinical care. Aim To compare and evaluate oral cavity cancer prognostic calculators using an independent dataset. Methods: Five prognostic calculators incorporating patient and tumor characteristics were identified that evaluated five-year overall survival. A total of 505 patients with previously untreated oral cancer diagnosed between 2003 and 2014 were analyzed. Calculators were applied to each patient to generate individual predicted survival probabilities. Predictions were compared among prognostic tools and with observed outcomes using Kaplan-Meier plots, ROC curves and calibration plots. Results Correlation between the five calculators varied from 0.59 to 0.86. There were considerable differences between individual predictions from pairs of calculators, with as many as 64% of patients having predictions that differed by more than 10%. Four of five calculators were well calibrated. For all calculators the predictions were associated with survival outcomes. The area under the ROC curve ranged from 0.65 to 0.71, with C-indices ranging from 0.63 to 0.67. An average of the 5 predictions had slightly better performance than any individual calculator. Conclusion Five prognostic calculators designed to predict individual outcomes of oral cancer differed significantly in their assessments of risk. Most were well calibrated and had modest discriminatory ability. Given the increasing importance of individualized risk prediction, more robust models are needed.

Individualized survival prediction for patients with oropharyngeal cancer in the human papillomavirus era

“…27, 46 In the current study, we found OPSCC calculators to yield higher AUCs and C-indices than did oral cavity and larynx models. This is likely due to the availability and incorporation of HPV, a robust biomarker in the OPSCC calculators.…”

Early squamous cell carcinoma of the oral tongue with histologically benign lymph nodes: A model predicting local control and vetting of the eighth edition of the American Joint Committee on Cancer pathologic T stage

“…These findings are in agreement with previously published data. 24 The discriminatory ability of the model proposed herein is higher than that of the 5 known risk calculators for oral cavity SCC, for which the AUC ranged from 0.652 to 0.706. The AJCC decided on a checklist of 16 items necessary for their endorsement of any risk model.…”

“…For example, tumor bed sampling and the need for margin revision correlated with higher rates of LR. 24 To the best of our knowledge, none of the other oral cavity SCC models accounts for oral cavity subsite, margin status, or PNI. 11,13,21,22 A prognostic risk model for early oral tongue SCC may facilitate the prediction of LR and LRR and guide therapeutic choices after glossectomy for patients with pN0 disease.…”

“…11,13,21,22 A prognostic risk model for early oral tongue SCC may facilitate the prediction of LR and LRR and guide therapeutic choices after glossectomy for patients with pN0 disease. 24 More detailed comparison with other models is difficult because they predict 5-year overall survival for patients with oral cavity SCC across all TNM stages. 23 The discussion of the model proposed herein will center on the AJCC checklist.…”

Individualized outcome prognostication for patients with laryngeal cancer

“…To assess clinical prognostic tools, analyses that compare the calculators' predictions with each other and with modern observed outcomes are imperative . These validation studies are best performed on independent patient cohorts that encompass diverse geographic regions and patient demographics . The objective of the current study was to use an independent patient cohort to externally evaluate and validate published prognostic calculators designed for patients with laryngeal cancer.…”