Health System Scale Semantic Search Across Unstructured Clinical Notes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911628948144128 |
|---|---|
| author | Mutinda, Faith Wavinya Makeneni, Spandana Lin, Anna Dutta, Shivaji Rasooly, Irit R. Dibussolo, Patrick Belman, Shivani Kamath Shahriari, Hessam Murphy, Kevin Ruan, Alex B. Chaiyachati, Barbara H. Chainani, Sanjay Grundmeier, Robert W. Haag, Scott M. Miller, Jeffrey M. Griffis, Heather M. Campbell, Ian M. |
| author_facet | Mutinda, Faith Wavinya Makeneni, Spandana Lin, Anna Dutta, Shivaji Rasooly, Irit R. Dibussolo, Patrick Belman, Shivani Kamath Shahriari, Hessam Murphy, Kevin Ruan, Alex B. Chaiyachati, Barbara H. Chainani, Sanjay Grundmeier, Robert W. Haag, Scott M. Miller, Jeffrey M. Griffis, Heather M. Campbell, Ian M. |
| contents | Introduction: Semantic search, which retrieves documents based on conceptual similarity rather than keyword matching, offers substantial advantages for retrieval of clinical information. However, deploying semantic search across entire health systems, comprising hundreds of millions of clinical notes, presents formidable engineering, cost, and governance challenges that have prevented adoption. Methods: We deployed a semantic search system at a large children's hospital indexing 166 million clinical notes (484 million vectors) from 1.68 million patients. The system uses instruction-tuned qwen3-embedding-0.6B embeddings, stores vectors in a managed database with storage-optimized indexing, maintains full-text metadata in a low-latency key-value store, and operates within a HIPAA-compliant governance framework. We evaluated the system through three experiments: optimization of embedding model and chunking strategy using a physician-authored benchmark dataset, characterization of full-scale performance (cost, latency, retrieval quality), and clinical utility assessment via comparison of chart abstraction efficiency across three tasks. Results: The system delivers sub-second query latency (median 237 ms single-user, 451 ms 20-user concurrency) with monthly costs of approximately USD 4,000. Qwen3 embeddings with 300-token chunk size achieved 94.6% accuracy on a clinical question-answering benchmark. In clinical utility evaluation across three abstraction tasks, semantic search reduced time-to-completion by 24 to 89% compared to clinician-performed chart review while maintaining comparable inter-rater agreement. Conclusion: Health-system-scale semantic search is both technically and operationally feasible. The system provides infrastructure supporting interactive search, cohort generation, and downstream LLM-powered clinical applications without requiring specialized informatics expertise. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25605 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Health System Scale Semantic Search Across Unstructured Clinical Notes Mutinda, Faith Wavinya Makeneni, Spandana Lin, Anna Dutta, Shivaji Rasooly, Irit R. Dibussolo, Patrick Belman, Shivani Kamath Shahriari, Hessam Murphy, Kevin Ruan, Alex B. Chaiyachati, Barbara H. Chainani, Sanjay Grundmeier, Robert W. Haag, Scott M. Miller, Jeffrey M. Griffis, Heather M. Campbell, Ian M. Information Retrieval Artificial Intelligence Databases Introduction: Semantic search, which retrieves documents based on conceptual similarity rather than keyword matching, offers substantial advantages for retrieval of clinical information. However, deploying semantic search across entire health systems, comprising hundreds of millions of clinical notes, presents formidable engineering, cost, and governance challenges that have prevented adoption. Methods: We deployed a semantic search system at a large children's hospital indexing 166 million clinical notes (484 million vectors) from 1.68 million patients. The system uses instruction-tuned qwen3-embedding-0.6B embeddings, stores vectors in a managed database with storage-optimized indexing, maintains full-text metadata in a low-latency key-value store, and operates within a HIPAA-compliant governance framework. We evaluated the system through three experiments: optimization of embedding model and chunking strategy using a physician-authored benchmark dataset, characterization of full-scale performance (cost, latency, retrieval quality), and clinical utility assessment via comparison of chart abstraction efficiency across three tasks. Results: The system delivers sub-second query latency (median 237 ms single-user, 451 ms 20-user concurrency) with monthly costs of approximately USD 4,000. Qwen3 embeddings with 300-token chunk size achieved 94.6% accuracy on a clinical question-answering benchmark. In clinical utility evaluation across three abstraction tasks, semantic search reduced time-to-completion by 24 to 89% compared to clinician-performed chart review while maintaining comparable inter-rater agreement. Conclusion: Health-system-scale semantic search is both technically and operationally feasible. The system provides infrastructure supporting interactive search, cohort generation, and downstream LLM-powered clinical applications without requiring specialized informatics expertise. |
| title | Health System Scale Semantic Search Across Unstructured Clinical Notes |
| topic | Information Retrieval Artificial Intelligence Databases |
| url | https://arxiv.org/abs/2604.25605 |