Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Large Language Model in Medical Informatics: Direct Classification and Enhanced Text Representations for Automatic ICD Coding

Zeyd Boukhers, AmeerAli Khan, Qusai Ramadan, Cong Yang

TL;DR

This paper explores the use of Large Language Models (LLM), specifically the LLAMA architecture, to enhance ICD code classification through two methodologies: direct application as a classifier and as a generator of enriched text representations within a Multi-Filter Residual Convolutional Neural Network (MultiResCNN) framework.

Abstract

Addressing the complexity of accurately classifying International Classification of Diseases (ICD) codes from medical discharge summaries is challenging due to the intricate nature of medical documentation. This paper explores the use of Large Language Models (LLM), specifically the LLAMA architecture, to enhance ICD code classification through two methodologies: direct application as a classifier and as a generator of enriched text representations within a Multi-Filter Residual Convolutional Neural Network (MultiResCNN) framework. We evaluate these methods by comparing them against state-of-the-art approaches, revealing LLAMA's potential to significantly improve classification outcomes by providing deep contextual insights into medical texts.

Large Language Model in Medical Informatics: Direct Classification and Enhanced Text Representations for Automatic ICD Coding

TL;DR

This paper explores the use of Large Language Models (LLM), specifically the LLAMA architecture, to enhance ICD code classification through two methodologies: direct application as a classifier and as a generator of enriched text representations within a Multi-Filter Residual Convolutional Neural Network (MultiResCNN) framework.

Abstract

Addressing the complexity of accurately classifying International Classification of Diseases (ICD) codes from medical discharge summaries is challenging due to the intricate nature of medical documentation. This paper explores the use of Large Language Models (LLM), specifically the LLAMA architecture, to enhance ICD code classification through two methodologies: direct application as a classifier and as a generator of enriched text representations within a Multi-Filter Residual Convolutional Neural Network (MultiResCNN) framework. We evaluate these methods by comparing them against state-of-the-art approaches, revealing LLAMA's potential to significantly improve classification outcomes by providing deep contextual insights into medical texts.

Paper Structure

This paper contains 16 sections, 5 equations, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Traditional Machine Learning Techniques
  4. Neural Network and Knowledge-Enhanced Techniques for ICD Coding
  5. LLM-based Approaches
  6. LLAMA for ICD Coding
  7. LLM as Classifier
  8. LLAMA as text representation
  9. Generating Text Representations:
  10. MultiResCNN Classifier
  11. Experimental Results
  12. Dataset:
  13. Evaluation Metrics:
  14. Baselines:
  15. Results:
  16. ...and 1 more sections

Figures (1)

  • Figure 1: Architecture of the LLAMA-2 Model for Text Representation using RoPE and YaRN techniques. The process culminates in a label attention mechanism that outputs predictions across ICD classes.