Medical Codes Prediction from Clinical Notes: From Human Coders to Machines

TL;DR

This paper discusses the automation of medical code prediction from clinical notes using advanced NLP models, emphasizing the importance of accuracy and explainability for clinical trust and efficiency.

Contribution

It evaluates the performance of deep learning models, including transformers, in medical code prediction and explores explainability methods for these complex models.

Findings

Deep learning models achieve high accuracy in code prediction.

Explainability methods help interpret complex neural network decisions.

Transformers show promise but need better explainability.

Abstract

Prediction of medical codes from clinical notes is a practical and essential need for every healthcare delivery organization within current medical systems. Automating annotation will save significant time and excessive effort that human coders spend today. However, the biggest challenge is directly identifying appropriate medical codes from several thousands of high-dimensional codes from unstructured free-text clinical notes. This complex medical codes prediction problem from clinical notes has received substantial interest in the NLP community, and several recent studies have shown the state-of-the-art code prediction results of full-fledged deep learning-based methods. This progress raises the fundamental question of how far automated machine learning systems are from human coders' working performance, as well as the important question of how well current explainability methods apply to advanced neural network models such as transformers. This is to predict correct codes and present references in clinical notes that support code prediction, as this level of explainability and accuracy of the prediction outcomes is critical to gaining trust from professional medical coders.