Guardado en:
Detalles Bibliográficos
Autores principales: Lee, Simon A., Jain, Sujay, Chen, Alex, Ono, Kyoka, Fang, Jennifer, Rudas, Akos, Chiang, Jeffrey N.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2402.00160
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909676186107904
author Lee, Simon A.
Jain, Sujay
Chen, Alex
Ono, Kyoka
Fang, Jennifer
Rudas, Akos
Chiang, Jeffrey N.
author_facet Lee, Simon A.
Jain, Sujay
Chen, Alex
Ono, Kyoka
Fang, Jennifer
Rudas, Akos
Chiang, Jeffrey N.
contents In this work, we introduce the Multiple Embedding Model for EHR (MEME), an approach that serializes multimodal EHR tabular data into text using pseudo-notes, mimicking clinical text generation. This conversion not only preserves better representations of categorical data and learns contexts but also enables the effective employment of pretrained foundation models for rich feature representation. To address potential issues with context length, our framework encodes embeddings for each EHR modality separately. We demonstrate the effectiveness of MEME by applying it to several decision support tasks within the Emergency Department across multiple hospital systems. Our findings indicate that MEME outperforms traditional machine learning, EHR-specific foundation models, and general LLMs, highlighting its potential as a general and extendible EHR representation strategy.
format Preprint
id arxiv_https___arxiv_org_abs_2402_00160
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Emergency Department Decision Support using Clinical Pseudo-notes
Lee, Simon A.
Jain, Sujay
Chen, Alex
Ono, Kyoka
Fang, Jennifer
Rudas, Akos
Chiang, Jeffrey N.
Computation and Language
In this work, we introduce the Multiple Embedding Model for EHR (MEME), an approach that serializes multimodal EHR tabular data into text using pseudo-notes, mimicking clinical text generation. This conversion not only preserves better representations of categorical data and learns contexts but also enables the effective employment of pretrained foundation models for rich feature representation. To address potential issues with context length, our framework encodes embeddings for each EHR modality separately. We demonstrate the effectiveness of MEME by applying it to several decision support tasks within the Emergency Department across multiple hospital systems. Our findings indicate that MEME outperforms traditional machine learning, EHR-specific foundation models, and general LLMs, highlighting its potential as a general and extendible EHR representation strategy.
title Emergency Department Decision Support using Clinical Pseudo-notes
topic Computation and Language
url https://arxiv.org/abs/2402.00160