Clinical Note Bloat Reduction for Efficient LLM Use
This addresses cost and efficiency issues for health systems deploying LLMs, though it is incremental as it focuses on preprocessing rather than core LLM advancements.
The paper tackled the problem of clinical note bloat, which dilutes signal and increases computational costs for LLMs in healthcare, by introducing TRACE, a preprocessing pipeline that removed 47.3% of chart text while maintaining performance for information extraction and outcome prediction.
Health systems are rapidly deploying large language models (LLMs) that use clinical notes for clinical decision support applications. However, modern documentation practices rely heavily on templates, copy--paste shortcuts, and auto-populated fields, producing extensive duplicated text (``note bloat'') that dilutes clinically meaningful signal and substantially increases the computational cost of LLM use. We introduce TRACE, a scalable preprocessing pipeline that removes note bloat by leveraging EHR attribution metadata to identify templated and copied content and applying frequency-based deduplication when metadata are unavailable. We evaluated TRACE across four real--world clinical cohorts spanning liver transplantation, obstetrics, and inpatient care (5.3 million notes) using blinded physician review and downstream modeling tasks. TRACE removed 47.3% of chart text while preserving performance for information extraction and clinical outcome prediction. At a large academic medical center, this reduction corresponds to an estimated $9.5 million annual decrease in LLM inference costs assuming one query per encounter. These findings show how underutilized EHR metadata can enable more scalable and cost-efficient deployment of LLM-based clinical systems.