Automated Fusion of Multimodal Electronic Health Records for Better Medical Predictions

The widespread adoption of Electronic Health Record (EHR) systems in healthcare institutes has generated vast amounts of medical data, offering significant opportunities for improving healthcare services through deep learning techniques. However, the complex and diverse modalities and feature struct...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the ... SIAM International Conference on Data Mining Jg. 2024; S. 361
Hauptverfasser: Cui, Suhan, Wang, Jiaqi, Zhong, Yuan, Liu, Han, Wang, Ting, Ma, Fenglong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States 2024
Schlagworte:
Electronic Health Records
Neural Architecture Search
Multimodal Fusion
ISSN:2167-0102
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The widespread adoption of Electronic Health Record (EHR) systems in healthcare institutes has generated vast amounts of medical data, offering significant opportunities for improving healthcare services through deep learning techniques. However, the complex and diverse modalities and feature structures in real-world EHR data pose great challenges for deep learning model design. To address the multi-modality challenge in EHR data, current approaches primarily rely on hand-crafted model architectures based on intuition and empirical experiences, leading to sub-optimal model architectures and limited performance. Therefore, to automate the process of model design for mining EHR data, we propose a novel neural architecture search (NAS) framework named AutoFM, which can automatically search for the optimal model architectures for encoding diverse input modalities and fusion strategies. We conduct thorough experiments on real-world multi-modal EHR data and prediction tasks, and the results demonstrate that our framework not only achieves significant performance improvement over existing state-of-the-art methods but also discovers meaningful network architectures effectively.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2167-0102
DOI:10.1137/1.9781611978032.41