# LeMoF: Level-guided Multimodal Fusion for Heterogeneous Clinical Data

arXiv: https://arxiv.org/abs/2601.10092 · HTML: https://mlsanity.com/paper/2601.10092/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Builds on (most cited first, 7 of 7)

- [MMTM: Multimodal Transfer Module for CNN Fusion](https://mlsanity.com/paper/1911.08670/) (2019)
- [MedFuse: Multi-modal fusion with clinical time-series data and chest X-ray images](https://mlsanity.com/paper/2207.07027/) (2022)
- [DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency](https://mlsanity.com/paper/2403.06197/) (2024)
- [A Transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics](https://mlsanity.com/paper/2306.00864/) (2023)
- [Heterogeneous Graph Learning for Multi-modal Medical Data Analysis](https://mlsanity.com/paper/2211.15158/) (2022)
- [HyperFusion: A Hypernetwork Approach to Multimodal Integration of Tabular and Medical Imaging Data for Predictive Modeling](https://mlsanity.com/paper/2403.13319/) (2024)
- [Predictive Modeling with Temporal Graphical Representation on Electronic Health Records](https://mlsanity.com/paper/2405.03943/) (2024)

## Built on by (most cited first, 1 of 1)

- [Large Language Models as Unified Multimodal Learners for Clinical Prediction](https://mlsanity.com/paper/2607.15380/) (2026)

## Abstract (arXiv)

Multimodal clinical prediction is widely used to integrate heterogeneous data such as Electronic Health Records (EHR) and biosignals. However, existing methods tend to rely on static modality integration schemes and simple fusion strategies. As a result, they fail to fully exploit modality-specific representations. In this paper, we propose Level-guided Modal Fusion (LeMoF), a novel framework that selectively integrates level-guided representations within each modality. Each level refers to a representation extracted from a different layer of the encoder. LeMoF explicitly separates and learns global modality-level predictions from level-specific discriminative representations. This design enables LeMoF to achieve a balanced performance between prediction stability and discriminative capability even in heterogeneous clinical environments. Experiments on length of stay prediction using Intensive Care Unit (ICU) data demonstrate that LeMoF consistently outperforms existing state-of-the-art multimodal fusion techniques across various encoder configurations. We also confirmed that level-wise integration is a key factor in achieving robust predictive performance across various clinical conditions.