Papers for

medical billing teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Large language model automates clinical note clarifications with mixed success

Closing Ambient Clinical Documentation Gaps with Automated Provider Queries

Abstract: Provider queries are clarifying requests sent by clinical documentation specialists to physicians to close gaps in the clinical note and ensure accurate billing. Prior work automates note drafting, ICD-10 coding, and order extraction assuming a complete transcript, leaving these gaps unaddressed. We study whether an LLM can automate the query loop, termed DAU (Draft, Ask, Update), across those three tasks. An audit of 3,000 real visits identifies the sources of missing documentation, from which we build five transcript-degradation benchmarks on public data. Analyzing 21k clarification turns on real conversations, we find useful-question predictors are task-specific: oracle confidence dominates, but note completeness needs only simple recall questions while ICD-10 coding needs harder, multi-option ones. About 9% of turns hurt performance, driven by redundant questions and non-answers that still trigger a rewrite. Deployment depends on learning "when not" as much as "what to" ask.

Mon 5 OctComputation and Language

The gist

Medical notes sometimes miss important information that affects billing and patient care. The authors looked at using a large language model (LLM) to automatically ask doctors clarifying questions and update notes in three key tasks: writing notes, assigning billing codes, and identifying medical orders. They found that different tasks need different types of questions and that the system can both help and sometimes harm accuracy, especially if it asks unnecessary or unclear questions. The study highlights that knowing when not to ask questions is just as important as what to ask.

Open → 2610.07502v1