@inproceedings{madrueno-etal-2026-urjc,
    title = "{URJC}-Team at {\#}{SMM}4{H}-{H}ea{RD} 2026: {TNM} Stage Extraction with a Regex-{LLM} Workflow",
    author = "Madrue{\~n}o, Natalia  and
      P{\'e}rez, Jose Walter Hern{\'a}ndez  and
      Fern{\'a}ndez, Rub{\'e}n R.  and
      Montalvo, Soto",
    editor = "Lopez-Garcia, Guillermo  and
      Gonzalez-Hernandez, Graciela",
    booktitle = "Proceedings of the 11th Social Media Mining for Health Research and Applications ({SMM}4{H}-{H}ea{RD} 2026) Workshop and Shared Tasks",
    month = jul,
    year = "2026",
    address = "San Diego, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.smm4h-1.22/",
    pages = "133--138",
    ISBN = "979-8-89176-432-3",
    abstract = "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."
}