# When Does Multimodal Learning Help in Healthcare? A Benchmark on EHR and Chest X-Ray Fusion

arXiv: https://arxiv.org/abs/2602.23614 · HTML: https://mlsanity.com/paper/2602.23614/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 23 of 23)

- [Multitask learning and benchmarking with clinical time series data](https://mlsanity.com/paper/1703.07771/) (2017)
- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling](https://mlsanity.com/paper/2307.14126/) (2023)
- [MMTM: Multimodal Transfer Module for CNN Fusion](https://mlsanity.com/paper/1911.08670/) (2019)
- [MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III](https://mlsanity.com/paper/1907.08322/) (2019)
- [EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models](https://mlsanity.com/paper/2307.02028/) (2023)
- [Time Series Prediction using Deep Learning Methods in Healthcare](https://mlsanity.com/paper/2108.13461/) (2021)
- [M3Care: Learning with Missing Modalities in Multimodal Healthcare Data](https://mlsanity.com/paper/2210.17292/) (2022)
- [Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts](https://mlsanity.com/paper/2410.08245/) (2024)
- [DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency](https://mlsanity.com/paper/2403.06197/) (2024)
- [Combining 3D Image and Tabular Data via the Dynamic Affine Feature Map Transform](https://mlsanity.com/paper/2107.05990/) (2021)
- [Benchmarking machine learning models on multi-centre eICU critical care dataset](https://mlsanity.com/paper/1910.00964/) (2019)
- [Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling](https://mlsanity.com/paper/2210.12156/) (2022)
- [RadFusion: Benchmarking Performance and Fairness for Multimodal Pulmonary Embolism Detection from CT and EHR](https://mlsanity.com/paper/2111.11665/) (2021)
- [Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML](https://mlsanity.com/paper/2306.05109/) (2023)
- [Learning Missing Modal Electronic Health Records with Unified Multi-modal Data Embedding and Modality-Aware Attention](https://mlsanity.com/paper/2305.02504/) (2023)
- [HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data](https://mlsanity.com/paper/2311.09115/) (2023)
- [Multimodal Clinical Benchmark for Emergency Care (MC-BEC): A Comprehensive Benchmark for Evaluating Foundation Models in Emergency Medicine](https://mlsanity.com/paper/2311.04937/) (2023)
- [Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition](https://mlsanity.com/paper/2503.18595/) (2025)
- [Benchmarking Deep Learning Architectures for Predicting Readmission to the ICU and Describing Patients-at-Risk](https://mlsanity.com/paper/1905.08547/) (2019)
- [Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion](https://mlsanity.com/paper/2502.20120/) (2025)
- [Clairvoyance: A Pipeline Toolkit for Medical Time Series](https://mlsanity.com/paper/2310.18688/) (2023)
- [Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment](https://mlsanity.com/paper/2510.11112/) (2025)

## Abstract (arXiv)

Machine learning holds promise for advancing clinical decision support, yet it remains unclear when multimodal learning truly helps in practice, particularly under modality missingness and fairness constraints. In this work, we conduct a systematic benchmark of multimodal fusion between Electronic Health Records (EHR) and chest X-rays (CXR) on standardized cohorts from MIMIC-IV and MIMIC-CXR, aiming to answer four fundamental questions: when multimodal fusion improves clinical prediction, how different fusion strategies compare, how robust existing methods are to missing modalities, and whether multimodal models achieve algorithmic fairness. Our study reveals several key insights. Multimodal fusion improves performance when modalities are complete, with gains concentrating in diseases that require complementary information from both EHR and CXR. While cross-modal learning mechanisms capture clinically meaningful dependencies beyond simple concatenation, the rich temporal structure of EHR introduces strong modality imbalance that architectural complexity alone cannot overcome. Under realistic missingness, multimodal benefits rapidly degrade unless models are explicitly designed to handle incomplete inputs. Moreover, multimodal fusion does not inherently improve fairness, with subgroup disparities mainly arising from unequal sensitivity across demographic groups. To support reproducible and extensible evaluation, we further release a flexible benchmarking toolkit that enables plug-and-play integration of new models and datasets. Together, this work provides actionable guidance on when multimodal learning helps, when it fails, and why, laying the foundation for developing clinically deployable multimodal systems that are both effective and reliable. The open-source toolkit can be found at https://github.com/jakeykj/CareBench.