@inproceedings{zhang-etal-2025-thcm,
    title = "{THCM}-{CAL}: Temporal-Hierarchical Causal Modelling with Conformal Calibration for Clinical Risk Prediction",
    author = "Zhang, Xin  and
      Wei, Qiyu  and
      Zhu, Yingjie  and
      Wu, Fanyi  and
      Ananiadou, Sophia",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.48/",
    doi = "10.18653/v1/2025.findings-emnlp.48",
    pages = "916--928",
    ISBN = "979-8-89176-335-7",
    abstract = "Automated clinical risk prediction from electronic health records (EHRs) demands modeling both structured diagnostic codes and unstructured narrative notes. However, most prior approaches either handle these modalities separately or rely on simplistic fusion strategies that ignore the directional, hierarchical causal interactions by which narrative observations precipitate diagnoses and propagate risk across admissions. In this paper, we propose **THCM-CAL**, a Temporal-Hierarchical Causal Model with Conformal Calibration. Our framework constructs a multimodal causal graph where nodes represent clinical entities from two modalities: textual propositions extracted from notes and ICD codes mapped to textual descriptions. Through hierarchical causal discovery, **THCM-CAL** infers three clinically grounded interactions: intra-slice same-modality sequencing, intra-slice cross-modality triggers, and inter-slice risk propagation. To enhance prediction reliability, we extend conformal prediction to multi-label ICD coding, calibrating per-code confidence intervals under complex co-occurrences. Experimental results on MIMIC-III and MIMIC-IV demonstrate the superiority of **THCM-CAL**."
}