TNM cancer staging is a critical process for characterizing tumor burden and guiding clinical decisions. Nevertheless, its automated extraction remains challenging due to the unstructured and heterogeneous nature of free-text pathology reports. This paper describes the participation of the URJC-Team in Task 6 of the Social Media Mining for Health/Health Real-World Data (#SMM4H-HeaRD) 2026 Shared Tasks. It focuses on predicting TNM staging from pathology reports. The proposed workflow combines hand-crafted regular expressions with a Large Language Model (LLM). First, explicit TNM mentions are extracted using rule-based patterns. Then, any stage not recovered by these rules is inferred by an LLM. Overall, the proposal provides competitive results across all official shared-task phases.

Standard clinical Natural Language Processing (NLP) benchmarks often yield inflated metrics by forcing deterministic classification on ambiguous instances, thereby obscuring the clinical risks of overconfident predictions. To bridge this gap, we propose a risk-aware hybrid selective classification framework, evaluated on early Human Immunodeficiency Virus suspicion identification in Spanish clinical notes. Our dual-verification approach explicitly decouples aleatoric uncertainty through Mondrian conformal prediction and epistemic uncertainty using a Multi-Centroid Mahalanobis Distance veto. Empirical evaluations reveal that standard uncertainty metrics and baseline classifiers are structurally insufficient for safe medical triage, suffering severe coverage collapse when forced to operate under strict reliability constraints. In contrast, by demanding that clinical narratives pass both probabilistic and geometric safeguards, the proposed framework successfully isolates a highly trustworthy operational domain.The obtained results show that explicit, decoupled uncertainty quantification is essential for translating biomedical NLP into responsible clinical practice.