# Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingness

arXiv: https://arxiv.org/abs/2509.17228 · HTML: https://mlsanity.com/paper/2509.17228/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 57 references that are in the map.
- First posted on arXiv 21 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission](https://mlsanity.com/paper/1904.05342/) (2019)
- [Attention Bottlenecks for Multimodal Fusion](https://mlsanity.com/paper/2107.00135/) (2021)
- [Multimodal Deep Learning](https://mlsanity.com/paper/2301.04856/) (2023)
- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [Large Language Models are Few-Shot Clinical Information Extractors](https://mlsanity.com/paper/2205.12689/) (2022)
- [Are Multimodal Transformers Robust to Missing Modality?](https://mlsanity.com/paper/2204.05454/) (2022)
- [Handling Missing Data with Graph Representation Learning](https://mlsanity.com/paper/2010.16418/) (2020)
- [Understanding and Improving Information Transfer in Multi-Task Learning](https://mlsanity.com/paper/2005.00944/) (2020)
- [M3Care: Learning with Missing Modalities in Multimodal Healthcare Data](https://mlsanity.com/paper/2210.17292/) (2022)
- [Stable Prediction with Model Misspecification and Agnostic Distribution Shift](https://mlsanity.com/paper/2001.11713/) (2020)
- [Stable Prediction across Unknown Environments](https://mlsanity.com/paper/1806.06270/) (2018)
- [DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency](https://mlsanity.com/paper/2403.06197/) (2024)
- [Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers](https://mlsanity.com/paper/2010.11750/) (2020)
- [Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity](https://mlsanity.com/paper/2409.06091/) (2024)
- [Explanation of Machine Learning Models Using Shapley Additive Explanation and Application for Real Data in Hospital](https://mlsanity.com/paper/2112.11071/) (2021)
- [Boosting Multitask Learning on Graphs through Higher-Order Task Affinities](https://mlsanity.com/paper/2306.14009/) (2023)
- [Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach](https://mlsanity.com/paper/2409.19458/) (2024)
- [Towards Semi-supervised Learning with Non-random Missing Labels](https://mlsanity.com/paper/2308.08872/) (2023)
- [Efficient Ensemble for Fine-tuning Language Models on Multiple Datasets](https://mlsanity.com/paper/2505.21930/) (2025)
- [FRAMM: Fair Ranking with Missing Modalities for Clinical Trial Site Selection](https://mlsanity.com/paper/2305.19407/) (2023)
- [Target PCA: Transfer Learning Large Dimensional Panel Data](https://mlsanity.com/paper/2308.15627/) (2023)
- [Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control](https://mlsanity.com/paper/2302.00839/) (2023)

## Built on by (most cited first, 5 of 5)

- [Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness](https://mlsanity.com/paper/2604.21235/) (2026)
- [Additive Causal Construction for Transferable and Reconfigurable Cross-System Learning in Multi-Source Image Fusion](https://mlsanity.com/paper/2607.02572/) (2026)
- [CRS-Triage: Confidence- and Reliability-Aware Selective Triage under Incomplete Clinical Evidence](https://mlsanity.com/paper/2608.03862/) (2026)
- [Multimodal Prompt Learning with Irregular EHRs for Robust Monitoring of Critical Care Patients](https://mlsanity.com/paper/2608.21941/) (2026)
- [GLR-MM: Graph-Based Global-Local Reconstruction for Robust Multimodal Chest X-ray and EHR Representation Learning under Missing Modalities](https://mlsanity.com/paper/2609.23876/) (2026)

## Abstract (arXiv)

Clinical notes contain rich patient information, such as diagnoses or medications, making them valuable for patient representation learning. Recent advances in large language models have further improved the ability to extract meaningful representations from clinical texts. However, clinical notes are often missing. For example, in our analysis of the MIMIC-IV dataset, 24.5% of patients have no available discharge summaries. In such cases, representations can be learned from other modalities such as structured data, chest X-rays, or radiology reports. Yet the availability of these modalities is influenced by clinical decision-making and varies across patients, resulting in modality missing-not-at-random (MMNAR) patterns. We propose a causal representation learning framework that leverages observed data and informative missingness in multimodal clinical records. It consists of: (1) an MMNAR-aware modality fusion component that integrates structured data, imaging, and text while conditioning on missingness patterns to capture patient health and clinician-driven assignment; (2) a modality reconstruction component with contrastive learning to ensure semantic sufficiency in representation learning; and (3) a multitask outcome prediction model with a rectifier that corrects for residual bias from specific modality observation patterns. Comprehensive evaluations across MIMIC-IV and eICU show consistent gains over the strongest baselines, achieving up to 13.8% AUC improvement for hospital readmission and 13.1% for ICU admission.