Clinically Interpretable Survival Risk Stratification in Head and Neck Cancer Using Bayesian Networks and Markov Blankets.

PURPOSE: To identify a clinically interpretable subset of survival-relevant features in head and neck cancer using Bayesian network (BN) and evaluate its prognostic and causal utility.

METHODS AND MATERIALS: We used the RADCURE data set, consisting of 3346 patients with head and neck cancer treated with definitive (chemo)radiation therapy. A probabilistic BN was constructed to model dependencies among clinical, anatomic, and treatment variables. The Markov blanket (MB) of 2-year survival (SVy2) was extracted and used to train a logistic regression model. After excluding incomplete cases, a temporal split yielded a train/test (2174/820) data set using 2007 as the cutoff year. Model performance was assessed using the area under the receiver operating characteristic (ROC) curve (AUC), concordance index (C-index), and Kaplan-Meier survival stratification. Model fit was further evaluated using a log-likelihood ratio test. Causal inference was performed using do-calculus interventions on MB variables.

RESULTS

The MB of SVy2 included 6 clinically relevant features: Eastern Cooperative Oncology Group performance status, T stage, human papillomavirus (HPV) status, disease site, the primary gross tumor volume, and treatment modality. The model achieved an AUC of 0.65 and C-index of 0.78 on the test data set, significantly stratifying patients into high- and low-risk groups (log-rank P < .01). Model fit was further supported by a log-likelihood ratio of 70.32 (P < .01). Subgroup analyses revealed strong performance in HPV-negative (AUC = 0.69; C-index = 0.76), T4 (AUC = 0.69; C-index = 0.80), and large-gross tumor volume (AUC = 0.67; C-index = 0.75) cohorts, each showing significant Kaplan-Meier separation. Causal analysis further supported the positive survival impact of Eastern Cooperative Oncology Group 0, HPV-positive status, and chemoradiation.

CONCLUSIONS

A compact, MB-derived BN model can robustly stratify survival risk in head and neck cancer. The model's structure enables explainable prognostication and supports individualized decision-making across key clinical subgroups.