PRIME: Pretraining for Patient Condition Representation with Irregular Multimodal Electronic Health Records
ACM Transactions on Knowledge Discovery from Data · 31.08.2025 · 19 (7) · 1-39
DOI: 10.1145/3744251 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 07.08.2025. Verfasst von Bohao Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities of China.
Abstract (Originalsprache)
With the increasing collection of electronic health records (EHRs), deep learning has become a crucial tool for real-time treatment analysis. However, due to patient privacy concerns, the scarcity of labeled data limits the end-to-end models that rely on large training data. Self-supervised pretraining offers a promising solution. Nevertheless, applying pretraining to EHRs faces two key issues: (1) EHRs exhibit multimodality, including monitoring data and recorded clinical note. For multimodal pretraining, designing a self-supervised task that can establish cross-modal associations while preserving all modal-unique information remains challenging. (2) Both modalities are sequential and irregular, with varying intervals between monitoring or records. Aligning monitoring times with recorded times poses a significant issue for fine-grained cross-modal pretraining. Existing pretraining models either focus on a single modality or only models regular data, failing to address them together. To fill this gap and fully utilize unlabel EHR data, we propose a p retraining model to learn patient r epresentation using unlabel i rregular m ultimodal E HRs, named PRIME. We first utilize a multi-element encoding module to extract patient condition snapshots from both modalities. Then, to construct multiple aligned cross-modal positive sample pairs that span the entire treatment process from irregular data, we employ patient condition alignment modules that integrate time-aware and feature-aware components to transfer snapshots to the aligned timestamps. Next, to preserve both shared and unique information of each modality, our decoupled representation learning strategy first uses a constraint matrix to separate shared information. We then employ contrastive-based cross-modal learning and reconstruction-based intra-modal learning to model shared and complete information, respectively. Extensive experiments on two real-world tasks demonstrate the superiority of PRIME over the state-of-the-art models, especially with limited labels.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities of China
Zitieren
APA
Li, B., Du, B., & Ye, J. (2025). PRIME: Pretraining for Patient Condition Representation with Irregular Multimodal Electronic Health Records. ACM Transactions on Knowledge Discovery from Data, 19(7), 1-39. https://doi.org/10.1145/3744251
Vancouver
Li B, Du B, Ye J. PRIME: Pretraining for Patient Condition Representation with Irregular Multimodal Electronic Health Records. ACM Transactions on Knowledge Discovery from Data. 2025;19(7):1-39. doi:10.1145/3744251
BibTeX
@article{Li2025,
author = {Li, Bohao and Du, Bowen and Ye, Junchen},
title = {PRIME: Pretraining for Patient Condition Representation with Irregular Multimodal Electronic Health Records},
journal = {ACM Transactions on Knowledge Discovery from Data},
year = {2025},
volume = {19},
number = {7},
pages = {1--39},
doi = {10.1145/3744251}
}
EUVIMED