A single fine-tuned 8B-parameter LLM extracts medical terms plus six clinical attributes from EHR notes in one pass, outperforming cTAKES and MetaMap on a small human-annotated test set.
NILE: Fast Natural Language Processing for Electronic Health Records
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Objective: Narrative text in Electronic health records (EHR) contain rich information for medical and data science studies. This paper introduces the design and performance of Narrative Information Linear Extraction (NILE), a natural language processing (NLP) package for EHR analysis that we share with the medical informatics community. Methods: NILE uses a modified prefix-tree search algorithm for named entity recognition, which can detect prefix and suffix sharing. The semantic analyses are implemented as rule-based finite state machines. Analyses include negation, location, modification, family history, and ignoring. Result: The processing speed of NILE is hundreds to thousands times faster than existing NLP software for medical text. The accuracy of presence analysis of NILE is on par with the best performing models on the 2010 i2b2/VA NLP challenge data. Conclusion: The speed, accuracy, and being able to operate via API make NILE a valuable addition to the NLP software for medical informatics and data science.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GENIE: Generative Note Information Extraction model for structuring EHR data
A single fine-tuned 8B-parameter LLM extracts medical terms plus six clinical attributes from EHR notes in one pass, outperforming cTAKES and MetaMap on a small human-annotated test set.