# M3Care: Learning with Missing Modalities in Multimodal Healthcare Data

arXiv: https://arxiv.org/abs/2210.17292 · HTML: https://mlsanity.com/paper/2210.17292/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 62 references that are in the map.
- First posted on arXiv 28 Oct 2022.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [Memory Fusion Network for Multi-view Sequential Learning](https://mlsanity.com/paper/1802.00927/) (2018)
- [A Survey on Multi-view Learning](https://mlsanity.com/paper/1304.5634/) (2013)
- [Learning Deep Kernels for Non-Parametric Two-Sample Tests](https://mlsanity.com/paper/2002.09116/) (2020)
- [Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis](https://mlsanity.com/paper/2002.05000/) (2020)
- [MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare](https://mlsanity.com/paper/1810.09593/) (2018)
- [ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context](https://mlsanity.com/paper/1911.12216/) (2019)
- [AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration](https://mlsanity.com/paper/1911.12205/) (2019)
- [RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data](https://mlsanity.com/paper/1807.08820/) (2018)
- [COMPOSE: Cross-Modal Pseudo-Siamese Network for Patient Trial Matching](https://mlsanity.com/paper/2006.08765/) (2020)
- [A Benchmark of Ocular Disease Intelligent Recognition: One Shot for Multi-disease Detection](https://mlsanity.com/paper/2102.07978/) (2021)
- [Deep Fusion Network for Image Completion](https://mlsanity.com/paper/1904.08060/) (2019)
- [Integrative Analysis of Patient Health Records and Neuroimages via Memory-based Graph Convolutional Network](https://mlsanity.com/paper/1809.06018/) (2018)
- [Top-N Recommendation on Graphs](https://mlsanity.com/paper/1609.08264/) (2016)

## Built on by (most cited first, 30 of 72)

- [Deep Multimodal Learning with Missing Modality: A Survey](https://mlsanity.com/paper/2409.07825/) (2024)
- [Multimodal Representation Learning by Alternating Unimodal Adaptation](https://mlsanity.com/paper/2311.10707/) (2023)
- [DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency](https://mlsanity.com/paper/2403.06197/) (2024)
- [A Closer Look at Multimodal Representation Collapse](https://mlsanity.com/paper/2505.22483/) (2025)
- [REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models](https://mlsanity.com/paper/2402.07016/) (2024)
- [ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration](https://mlsanity.com/paper/2410.02551/) (2024)
- [Prompting Large Language Models for Zero-Shot Clinical Prediction with Structured Longitudinal Electronic Health Record Data](https://mlsanity.com/paper/2402.01713/) (2024)
- [EMERGE: Enhancing Multimodal Electronic Health Records Predictive Modeling with Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.00036/) (2024)
- [Distilled Prompt Learning for Incomplete Multimodal Survival Prediction](https://mlsanity.com/paper/2503.01653/) (2025)
- [HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research](https://mlsanity.com/paper/2508.02621/) (2025)
- [Multimodal Data Integration for Precision Oncology: Challenges and Future Directions](https://mlsanity.com/paper/2406.19611/) (2024)
- [Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring](https://mlsanity.com/paper/2508.09085/) (2025)
- [PRISM: Mitigating EHR Data Sparsity via Learning from Missing Feature Calibrated Prototype Patient Representations](https://mlsanity.com/paper/2309.04160/) (2023)
- [Knowledge Bridger: Towards Training-free Missing Modality Completion](https://mlsanity.com/paper/2502.19834/) (2025)
- [Missing-modality Enabled Multi-modal Fusion Architecture for Medical Data](https://mlsanity.com/paper/2309.15529/) (2023)
- [SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction](https://mlsanity.com/paper/2405.09039/) (2024)
- [MoE-Health: A Mixture of Experts Framework for Robust Multimodal Healthcare Prediction](https://mlsanity.com/paper/2508.21793/) (2025)
- [FlexCare: Leveraging Cross-Task Synergy for Flexible Multimodal Healthcare Prediction](https://mlsanity.com/paper/2406.11928/) (2024)
- [Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation](https://mlsanity.com/paper/2410.17918/) (2024)
- [Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity](https://mlsanity.com/paper/2403.09428/) (2024)
- [Towards the Causal Complete Cause of Multi-Modal Representation Learning](https://mlsanity.com/paper/2407.14058/) (2024)
- [MARIA: a Multimodal Transformer Model for Incomplete Healthcare Data](https://mlsanity.com/paper/2412.14810/) (2024)
- [Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingness](https://mlsanity.com/paper/2509.17228/) (2025)
- [Learnable Prompt as Pseudo-Imputation: Rethinking the Necessity of Traditional EHR Data Imputation in Downstream Clinical Prediction](https://mlsanity.com/paper/2401.16796/) (2024)
- [Can Text-to-image Model Assist Multi-modal Learning for Visual Recognition with Visual Modality Missing?](https://mlsanity.com/paper/2402.09036/) (2024)
- [From Orthogonality to Dependency: Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals](https://mlsanity.com/paper/2405.16083/) (2024)
- [Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach](https://mlsanity.com/paper/2408.07445/) (2024)
- [Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach](https://mlsanity.com/paper/2505.17637/) (2025)
- [No Modality Left Behind: Adapting to Missing Modalities via Knowledge Distillation for Brain Tumor Segmentation](https://mlsanity.com/paper/2509.15017/) (2025)
- [Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification](https://mlsanity.com/paper/2601.22853/) (2026)

## Abstract (arXiv)

Multimodal electronic health record (EHR) data are widely used in clinical applications. Conventional methods usually assume that each sample (patient) is associated with the unified observed modalities, and all modalities are available for each sample. However, missing modality caused by various clinical and social reasons is a common issue in real-world clinical scenarios. Existing methods mostly rely on solving a generative model that learns a mapping from the latent space to the original input space, which is an unstable ill-posed inverse problem. To relieve the underdetermined system, we propose a model solving a direct problem, dubbed learning with Missing Modalities in Multimodal healthcare data (M3Care). M3Care is an end-to-end model compensating the missing information of the patients with missing modalities to perform clinical analysis. Instead of generating raw missing data, M3Care imputes the task-related information of the missing modalities in the latent space by the auxiliary information from each patient's similar neighbors, measured by a task-guided modality-adaptive similarity metric, and thence conducts the clinical tasks. The task-guided modality-adaptive similarity metric utilizes the uncensored modalities of the patient and the other patients who also have the same uncensored modalities to find similar patients. Experiments on real-world datasets show that M3Care outperforms the state-of-the-art baselines. Moreover, the findings discovered by M3Care are consistent with experts and medical knowledge, demonstrating the capability and the potential of providing useful insights and explanations.