# Clinical Note Bloat Reduction for Efficient LLM Use

arXiv: https://arxiv.org/abs/2604.16364 · HTML: https://mlsanity.com/paper/2604.16364/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 21 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Deduplicating Training Data Makes Language Models Better](https://mlsanity.com/paper/2107.06499/) (2021)
- [ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission](https://mlsanity.com/paper/1904.05342/) (2019)
- [Data-centric Artificial Intelligence: A Survey](https://mlsanity.com/paper/2303.10158/) (2023)
- [Data-Centric Foundation Models in Computational Healthcare: A Survey](https://mlsanity.com/paper/2401.02458/) (2024)
- [Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications](https://mlsanity.com/paper/2509.08604/) (2025)
- [Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models](https://mlsanity.com/paper/2506.00134/) (2025)

## Built on by (most cited first, 2 of 2)

- [Clinically Grounded Privacy Evaluation of Medical LMs](https://mlsanity.com/paper/2606.09590/) (2026)
- [A Living Benchmark for Information Retrieval from Electronic Health Records](https://mlsanity.com/paper/2609.30205/) (2026)

## Abstract (arXiv)

Background: Clinical notes contain extensive duplicated text from templates, copy-paste, and auto-populated fields ("note bloat"), diluting clinical signal, limiting longitudinal context, and increasing large language model (LLM) costs. Methods: TRACE removes note bloat using note-level EHR metadata to identify templated and copied content, with frequency-based de-duplication when metadata are unavailable. We evaluated TRACE using blinded physician span review and gold-standard templated-text annotations across four cohorts spanning liver transplant, obstetrics, and inpatient populations at multiple health systems (5.3M notes). We compared zero-shot LLMs and embedding-based classifiers using original and TRACE-processed notes for 20 information extraction tasks and prediction of 5-year survival, postpartum hemorrhage, and 30-day readmission. Results: Only 0.3-6.6% of removed text was flagged as author-generated; TRACE captured 86% of annotated templated characters. Information extraction F1 differences averaged by cohort ranged from -0.009 to +0.004; task-specific prediction F1 differences ranged from -0.011 to +0.018. Among 1,000 randomly sampled Stanford Health Care patients, TRACE reduced chart text by 47.3% (742.7M characters), averaging 220,167 fewer tokens per patient. Using 2024 encounter volumes at a large tertiary academic center and one query per encounter, projected three-year net savings ranged from 1.00M to 13.58M across evaluated model pricing schemes, including initial and annual TRACE processing costs. Conclusion: TRACE substantially reduces clinical note redundancy while preserving information extraction and prediction performance. Underused EHR metadata can reduce LLM inference costs, expand usable longitudinal context, and support scalable clinical AI.