Self-supervised Hierarchical Representation for Medication Recommendation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917829118263296 |
|---|---|
| author | Liang, Yuliang Liu, Yuting Dang, Yizhou Yang, Enneng Guo, Guibing Cai, Wei Zhao, Jianzhe Wang, Xingwei |
| author_facet | Liang, Yuliang Liu, Yuting Dang, Yizhou Yang, Enneng Guo, Guibing Cai, Wei Zhao, Jianzhe Wang, Xingwei |
| contents | Medication recommender is to suggest appropriate medication combinations based on a patient's health history, e.g., diagnoses and procedures. Existing works represent different diagnoses/procedures well separated by one-hot encodings. However, they ignore the latent hierarchical structures of these medical terms, undermining the generalization performance of the model. For example, "Respiratory Diseases", "Chronic Respiratory Diseases" and "Chronic Bronchiti" have a hierarchical relationship, progressing from general to specific. To address this issue, we propose a novel hierarchical encoder named HIER to hierarchically represent diagnoses and procedures, which is based on standard medical codes and compatible with any existing methods. Specifically, the proposed method learns relation embedding with a self-supervised objective for incorporating the neighbor hierarchical structure. Additionally, we develop the position encoding to explicitly introduce global hierarchical position. Extensive experiments demonstrate significant and consistent improvements in recommendation accuracy across four baselines and two real-world clinical datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_03143 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-supervised Hierarchical Representation for Medication Recommendation Liang, Yuliang Liu, Yuting Dang, Yizhou Yang, Enneng Guo, Guibing Cai, Wei Zhao, Jianzhe Wang, Xingwei Information Retrieval Medication recommender is to suggest appropriate medication combinations based on a patient's health history, e.g., diagnoses and procedures. Existing works represent different diagnoses/procedures well separated by one-hot encodings. However, they ignore the latent hierarchical structures of these medical terms, undermining the generalization performance of the model. For example, "Respiratory Diseases", "Chronic Respiratory Diseases" and "Chronic Bronchiti" have a hierarchical relationship, progressing from general to specific. To address this issue, we propose a novel hierarchical encoder named HIER to hierarchically represent diagnoses and procedures, which is based on standard medical codes and compatible with any existing methods. Specifically, the proposed method learns relation embedding with a self-supervised objective for incorporating the neighbor hierarchical structure. Additionally, we develop the position encoding to explicitly introduce global hierarchical position. Extensive experiments demonstrate significant and consistent improvements in recommendation accuracy across four baselines and two real-world clinical datasets. |
| title | Self-supervised Hierarchical Representation for Medication Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2411.03143 |