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

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.

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.

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.

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.