MedM2T: A MultiModal Framework for Time-Aware Modeling with Electronic Health Record and Electrocardiogram Data

TL;DR

MedM2T is a novel multimodal, time-aware framework that effectively models heterogeneous medical data, including electronic health records and ECGs, to improve clinical prediction tasks with state-of-the-art performance.

Contribution

We introduce MedM2T, a comprehensive framework combining flexible time series encoding, hierarchical fusion, and cross-modal attention for multimodal medical data analysis.

Findings

Achieved high AUROC and AUPRC in cardiovascular disease prediction.

Outperformed existing models in mortality prediction.

Demonstrated robustness across multiple clinical tasks.

Abstract

The inherent multimodality and heterogeneous temporal structures of medical data pose significant challenges for modeling. We propose MedM2T, a time-aware multimodal framework designed to address these complexities. MedM2T integrates: (i) Sparse Time Series Encoder to flexibly handle irregular and sparse time series, (ii) Hierarchical Time-Aware Fusion to capture both micro- and macro-temporal patterns from multiple dense time series, such as ECGs, and (iii) Bi-Modal Attention to extract cross-modal interactions, which can be extended to any number of modalities. To mitigate granularity gaps between modalities, MedM2T uses modality-specific pre-trained encoders and aligns resulting features within a shared encoder. We evaluated MedM2T on MIMIC-IV and MIMIC-IV-ECG datasets for three tasks that encompass chronic and acute disease dynamics: 90-day cardiovascular disease (CVD) prediction, in-hospital mortality prediction, and ICU length-of-stay (LOS) regression. MedM2T achieved superior or comparable performance relative to state-of-the-art multimodal learning frameworks and existing time series models, achieving an AUROC of 0.932 and an AUPRC of 0.670 for CVD prediction; an AUROC of 0.868 and an AUPRC of 0.470 for mortality prediction; and Mean Absolute Error (MAE) of 2.33 for LOS regression. These results highlight the robustness and broad applicability of MedM2T, positioning it as a promising tool in clinical prediction. We provide the implementation of MedM2T at https://github.com/DHLab-TSENG/MedM2T.