Researchers have developed LTR-ICD, a novel framework for automatically assigning and ranking diagnostic codes from clinical notes. Unlike previous classification-based methods, LTR-ICD treats the problem as a retrieval task, considering the essential order of ICD codes. This approach significantly improves the accuracy of identifying primary diagnosis codes, achieving 47% ranking accuracy compared to 20% for state-of-the-art classifiers. The framework also demonstrates superior classification performance with micro- and macro-F1 scores of 0.6065 and 0.2904, respectively. AI
IMPACT This framework could enhance the accuracy and efficiency of medical coding, potentially improving healthcare administration and reimbursement processes.
RANK_REASON The cluster contains an academic paper detailing a new framework for automatic ICD coding. [lever_c_demoted from research: ic=1 ai=1.0]
- arXiv
- DagsHub
- Hugging Face
- IArxiv
- International Statistical Classification of Diseases and Related Health Problems
- LTR-ICD
- Mohammad Mansoori
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
