# THCM-CAL: Temporal-Hierarchical Causal Modelling with Conformal Calibration for Clinical Risk Prediction

arXiv: https://arxiv.org/abs/2506.17844 · HTML: https://mlsanity.com/paper/2506.17844/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 21 Jun 2025.

## Builds on (most cited first, 15 of 15)

- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission](https://mlsanity.com/paper/1904.05342/) (2019)
- [RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism](https://mlsanity.com/paper/1608.05745/) (2016)
- [Explainable Prediction of Medical Codes from Clinical Text](https://mlsanity.com/paper/1802.05695/) (2018)
- [GRAM: Graph-based Attention Model for Healthcare Representation Learning](https://mlsanity.com/paper/1611.07012/) (2016)
- [BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text](https://mlsanity.com/paper/2403.18421/) (2024)
- [Collaborative Graph Learning with Auxiliary Text for Temporal Event Prediction in Healthcare](https://mlsanity.com/paper/2105.07542/) (2021)
- [Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphs](https://mlsanity.com/paper/2112.05195/) (2021)
- [DKEC: Domain Knowledge Enhanced Multi-Label Classification for Diagnosis Prediction](https://mlsanity.com/paper/2310.07059/) (2023)
- [A novel method for Causal Structure Discovery from EHR data, a demonstration on type-2 diabetes mellitus](https://mlsanity.com/paper/2011.05489/) (2020)
- [Semantically Enhanced Dynamic Bayesian Network for Detecting Sepsis Mortality Risk in ICU Patients with Infection](https://mlsanity.com/paper/1806.10174/) (2018)
- [Sepsyn-OLCP: An Online Learning-based Framework for Early Sepsis Prediction with Uncertainty Quantification using Conformal Prediction](https://mlsanity.com/paper/2503.14663/) (2025)
- [NeuroSep-CP-LCB: A Deep Learning-based Contextual Multi-armed Bandit Algorithm with Uncertainty Quantification for Early Sepsis Prediction](https://mlsanity.com/paper/2503.16708/) (2025)

## Abstract (arXiv)

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.