SurfCon combines surface form similarity and global context from co-occurrence counts to discover synonyms in privacy-aware clinical data and handle OOV queries.
Clinical concept embeddings learned from massive sources of medical data.arXiv preprint arXiv:1804.01486, 2018
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2019 3verdicts
UNVERDICTED 3representative citing papers
SNOMED-CT graph embeddings via random walks and Poincaré methods yield 5-6x better concept similarity and 6-20% better patient diagnosis prediction than prior embeddings.
Embedding models trained on medical codes outperform a commercial linear regression risk adjustment model for prospective risk score prediction.
citing papers explorer
-
SurfCon: Synonym Discovery on Privacy-Aware Clinical Data
SurfCon combines surface form similarity and global context from co-occurrence counts to discover synonyms in privacy-aware clinical data and handle OOV queries.
-
Snomed2Vec: Random Walk and Poincar\'e Embeddings of a Clinical Knowledge Base for Healthcare Analytics
SNOMED-CT graph embeddings via random walks and Poincaré methods yield 5-6x better concept similarity and 6-20% better patient diagnosis prediction than prior embeddings.
-
Medical Concept Representation Learning from Claims Data and Application to Health Plan Payment Risk Adjustment
Embedding models trained on medical codes outperform a commercial linear regression risk adjustment model for prospective risk score prediction.