Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.25816 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909877904867328 |
|---|---|
| author | Chawdhury, Tarun Kumar Duke, Jon D. |
| author_facet | Chawdhury, Tarun Kumar Duke, Jon D. |
| contents | Electronic Health Records (EHR) store clinical documentation as base64 encoded attachments in FHIR DocumentReference resources, which makes semantic question answering difficult. Traditional vector database methods often miss nuanced clinical relationships. The Clinical Entity Augmented Retrieval (CLEAR) method, introduced by Lopez et al. 2025, uses entity aware retrieval and achieved improved performance with an F1 score of 0.90 versus 0.86 for embedding based retrieval, while using over 70 percent fewer tokens. We developed a Clinical Notes QA Evaluation Platform to validate CLEAR against zero shot large context inference and traditional chunk based retrieval augmented generation. The platform was tested on 12 clinical notes ranging from 10,000 to 65,000 tokens representing realistic EHR content. CLEAR achieved a 58.3 percent win rate, an average semantic similarity of 0.878, and used 78 percent fewer tokens than wide context processing. The largest performance gains occurred on long notes, with a 75 percent win rate for documents exceeding 65,000 tokens. These findings confirm that entity aware retrieval improves both efficiency and accuracy in clinical natural language processing. The evaluation framework provides a reusable and transparent benchmark for assessing clinical question answering systems where semantic precision and computational efficiency are critical. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_25816 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Long Context: When Semantics Matter More than Tokens Chawdhury, Tarun Kumar Duke, Jon D. Computation and Language Machine Learning 68T50, 68T07 I.2.7; H.3.3 Electronic Health Records (EHR) store clinical documentation as base64 encoded attachments in FHIR DocumentReference resources, which makes semantic question answering difficult. Traditional vector database methods often miss nuanced clinical relationships. The Clinical Entity Augmented Retrieval (CLEAR) method, introduced by Lopez et al. 2025, uses entity aware retrieval and achieved improved performance with an F1 score of 0.90 versus 0.86 for embedding based retrieval, while using over 70 percent fewer tokens. We developed a Clinical Notes QA Evaluation Platform to validate CLEAR against zero shot large context inference and traditional chunk based retrieval augmented generation. The platform was tested on 12 clinical notes ranging from 10,000 to 65,000 tokens representing realistic EHR content. CLEAR achieved a 58.3 percent win rate, an average semantic similarity of 0.878, and used 78 percent fewer tokens than wide context processing. The largest performance gains occurred on long notes, with a 75 percent win rate for documents exceeding 65,000 tokens. These findings confirm that entity aware retrieval improves both efficiency and accuracy in clinical natural language processing. The evaluation framework provides a reusable and transparent benchmark for assessing clinical question answering systems where semantic precision and computational efficiency are critical. |
| title | Beyond Long Context: When Semantics Matter More than Tokens |
| topic | Computation and Language Machine Learning 68T50, 68T07 I.2.7; H.3.3 |
| url | https://arxiv.org/abs/2510.25816 |