Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Open Access

Data Quality in Clinical Coding: A Critical Analysis and Preliminary Study

View Full Paper
Ask AI
Bookmark
Share

Authors

SKSupriya KhadkaXJXiaorui JiangVPVasile Palade

Discussion

Loading...

Member takes

Overview

Critical analysis reveals undercoding in datasets for clinical coding, suggesting enhancements for automation.

Key Points

  • Undercoding affects approximately 80% of clinical notes in the MDACE dataset and 86% in CodiEsp, indicating significant quality issues.
  • Errors in coding datasets degrade the performance of automated systems, leading to a 4% drop in precision and 7% drop in recall.
  • The study employs a three-stage pipeline using a large language model to enhance coding accuracy and rectify undercoding issues.
  • Ensuring data integrity is crucial for effective clinical coding, impacting overall healthcare practices and outcomes.

Cite This Study

Khadka et al. (2025) studied this question.

synapsesocial.com/papers/68c1d5fe54b1d3bfb60f93bbhttps://doi.org/10.1101/2025.08.24.25334321
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Recent Advances in AI for Automated ICD Coding: A Systematic Literature Review2026
  2. 2Artificial intelligence for automated ICD-10 coding: a systematic review of multi-label text classification in clinical narratives2026
  3. 3Exploring the consistency, quality and challenges in manual and automated coding of free-text diagnoses from hospital outpatient letters2025
  4. 4Why is the data quality of hospital morbidity so heterogeneous? A nationwide survey of Portuguese clinical coders2026
  5. 5Targeted education for clinicians and clinical coding staff improves the accuracy of clinical coding: A quality improvement project2024 · 9 citations