# Snomed2Vec: Random Walk and Poincar'e Embeddings of a Clinical Knowledge Base for Healthcare Analytics

arXiv: https://arxiv.org/abs/1907.08650 · HTML: https://mlsanity.com/paper/1907.08650/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2019.

## Built on by (most cited first, 6 of 6)

- [Ontology Embedding: A Survey of Methods, Applications and Resources](https://mlsanity.com/paper/2406.10964/) (2024)
- [HypKG: Hypergraph-based Knowledge Graph Contextualization for Precision Healthcare](https://mlsanity.com/paper/2507.19726/) (2025)
- [Analyzing historical diagnosis code data from NIH N3C and RECOVER Programs using deep learning to determine risk factors for Long Covid](https://mlsanity.com/paper/2210.02490/) (2022)
- [KEEP: Integrating Medical Ontologies with Clinical Data for Robust Code Embeddings](https://mlsanity.com/paper/2510.05049/) (2025)
- [Development of a Knowledge Graph Embeddings Model for Pain](https://mlsanity.com/paper/2308.08904/) (2023)
- [OntoBook: Ontology-Grounded Synthetic Textbooks for Medical Encoder Pretraining](https://mlsanity.com/paper/2607.18927/) (2026)

## Abstract (arXiv)

Representation learning methods that transform encoded data (e.g., diagnosis and drug codes) into continuous vector spaces (i.e., vector embeddings) are critical for the application of deep learning in healthcare. Initial work in this area explored the use of variants of the word2vec algorithm to learn embeddings for medical concepts from electronic health records or medical claims datasets. We propose learning embeddings for medical concepts by using graph-based representation learning methods on SNOMED-CT, a widely popular knowledge graph in the healthcare domain with numerous operational and research applications. Current work presents an empirical analysis of various embedding methods, including the evaluation of their performance on multiple tasks of biomedical relevance (node classification, link prediction, and patient state prediction). Our results show that concept embeddings derived from the SNOMED-CT knowledge graph significantly outperform state-of-the-art embeddings, showing 5-6x improvement in ``concept similarity" and 6-20% improvement in patient diagnosis.