Improving ICD coding using Chapter based Named Entities and Attentional Models

TL;DR

This paper presents an improved ICD coding method using chapter-based named entities and attentional models, achieving higher F1 scores and interpretability without relying on external data.

Contribution

It introduces a novel approach combining chapter-based entity recognition and attentional models for ICD coding, enhancing accuracy and interpretability.

Findings

F1 scores improved to 0.79 and 0.81 with new models

Chapter-based entity recognition reduces false positives

Models outperform previous benchmarks on ICD coding

Abstract

Recent advancements in natural language processing (NLP) have led to automation in various domains. However, clinical NLP often relies on benchmark datasets that may not reflect real-world scenarios accurately. Automatic ICD coding, a vital NLP task, typically uses outdated and imbalanced datasets like MIMIC-III, with existing methods yielding micro-averaged F1 scores between 0.4 and 0.7 due to many false positives. Our research introduces an enhanced approach to ICD coding that improves F1 scores by using chapter-based named entities and attentional models. This method categorizes discharge summaries into ICD-9 Chapters and develops attentional models with chapter-specific data, eliminating the need to consider external data for code identification. For categorization, we use Chapter-IV to de-bias and influence key entities and weights without neural networks, creating accurate thresholds and providing interpretability for human validation. Post-validation, we develop attentional models for three frequent and three non-frequent codes from Chapter-IV using Bidirectional-Gated Recurrent Units (GRUs) with Attention and Transformer with Multi-head Attention architectures. The average Micro-F1 scores of 0.79 and 0.81 from these models demonstrate significant performance improvements in ICD coding.