Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 16, 2026npj Digital MedicineOpen Access

Evaluating real-world deployment of an HL7-CDA-aligned LLM for ICD-10-CM coding

View Full Paper
Ask AI
Bookmark
Share

Authors

HDHY DaiZLZhenghao LiALAn-Tai Lu

Discussion

Loading...

Member takes

Overview

A randomized controlled trial assesses AI-assisted workflows for ICD-10-CM coding, indicating potential for improved efficiency.

Key Points

  • This research aims to evaluate the effectiveness of an AI system in assisting ICD-10-CM coding in clinical settings.
  • Developed a modular pipeline for ICD-10-CM coding integrating specific model selection and training.
  • Conducted a human-in-the-loop randomized controlled trial with ten certified coding specialists.
  • Evaluated performance using pairwise LLM-as-judge evaluation and Plackett–Luce ranking.
  • AI-assisted workflows significantly reduced coding time while maintaining accuracy.
  • Performance and satisfaction varied based on coder experience, certification, and generational cohort.
  • Successful AI integration requires consideration of documentation infrastructure and user acceptance.

Cite This Study

Dai et al. (2026) studied this question.

synapsesocial.com/papers/69e07d732f7e8953b7cbe584https://doi.org/10.1038/s41746-026-02541-5
View Full Paper
Ask AI
Bookmark
Share