MIPO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peng, Xueping, Long, Guodong, Shen, Tao, Wang, Sen, Zhang, Chengqi, Clarke, Allison, Schlegel, Clement
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908754136530944
author Peng, Xueping
Long, Guodong
Shen, Tao
Wang, Sen
Zhang, Chengqi
Clarke, Allison
Schlegel, Clement
author_facet Peng, Xueping
Long, Guodong
Shen, Tao
Wang, Sen
Zhang, Chengqi
Clarke, Allison
Schlegel, Clement
contents Representation learning on electronic health records (EHRs) plays a vital role in downstream medical prediction tasks. Although natural language processing techniques, such as recurrent neural networks, and self-attention, have been adapted for learning medical representations from hierarchical, time-stamped EHR data, they often struggle when either general or task-specific data are limited. Recent efforts have attempted to mitigate this challenge by incorporating medical ontologies (i.e., knowledge graphs) into self-supervised tasks like diagnosis prediction. However, two main issues remain: (1) small and uniform ontologies that lack diversity for robust learning, and (2) insufficient attention to the critical contexts or dependencies underlying patient journeys, which could further enhance ontology-based learning. To address these gaps, we propose MIPO (Mutual Integration of Patient Journey and Medical Ontology), a robust end-to-end framework that employs a Transformer-based architecture for representation learning. MIPO emphasizes task-specific representation learning through a sequential diagnosis prediction task, while also incorporating an ontology-based disease-typing task. A graph-embedding module is introduced to integrate information from patient visit records, thus alleviating data insufficiency. This setup creates a mutually reinforcing loop, where both patient-journey embedding and ontology embedding benefit from each other. We validate MIPO on two real-world benchmark datasets, showing that it consistently outperforms baseline methods under both sufficient and limited data conditions. Furthermore, the resulting diagnosis embeddings offer improved interpretability, underscoring the promise of MIPO for real-world healthcare applications.
format Preprint
id arxiv_https___arxiv_org_abs_2107_09288
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle MIPO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning
Peng, Xueping
Long, Guodong
Shen, Tao
Wang, Sen
Zhang, Chengqi
Clarke, Allison
Schlegel, Clement
Artificial Intelligence
Representation learning on electronic health records (EHRs) plays a vital role in downstream medical prediction tasks. Although natural language processing techniques, such as recurrent neural networks, and self-attention, have been adapted for learning medical representations from hierarchical, time-stamped EHR data, they often struggle when either general or task-specific data are limited. Recent efforts have attempted to mitigate this challenge by incorporating medical ontologies (i.e., knowledge graphs) into self-supervised tasks like diagnosis prediction. However, two main issues remain: (1) small and uniform ontologies that lack diversity for robust learning, and (2) insufficient attention to the critical contexts or dependencies underlying patient journeys, which could further enhance ontology-based learning. To address these gaps, we propose MIPO (Mutual Integration of Patient Journey and Medical Ontology), a robust end-to-end framework that employs a Transformer-based architecture for representation learning. MIPO emphasizes task-specific representation learning through a sequential diagnosis prediction task, while also incorporating an ontology-based disease-typing task. A graph-embedding module is introduced to integrate information from patient visit records, thus alleviating data insufficiency. This setup creates a mutually reinforcing loop, where both patient-journey embedding and ontology embedding benefit from each other. We validate MIPO on two real-world benchmark datasets, showing that it consistently outperforms baseline methods under both sufficient and limited data conditions. Furthermore, the resulting diagnosis embeddings offer improved interpretability, underscoring the promise of MIPO for real-world healthcare applications.
title MIPO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning
topic Artificial Intelligence
url https://arxiv.org/abs/2107.09288