A Review of Published Machine Learning Natural Language Processing Applications for Protocolling Radiology Imaging

TL;DR

This paper reviews the current state of machine learning and natural language processing applications in automating radiology protocolling, highlighting the potential to improve efficiency and accuracy in clinical workflows.

Contribution

It provides a systematic review of ML models for radiology protocolling using clinical text and discusses progress towards clinical implementation.

Findings

Few ML models for automated protocolling have been published.

Existing models show potential but lack widespread clinical adoption.

The review identifies best practices and gaps in current research.

Abstract

Machine learning (ML) is a subfield of Artificial intelligence (AI), and its applications in radiology are growing at an ever-accelerating rate. The most studied ML application is the automated interpretation of images. However, natural language processing (NLP), which can be combined with ML for text interpretation tasks, also has many potential applications in radiology. One such application is automation of radiology protocolling, which involves interpreting a clinical radiology referral and selecting the appropriate imaging technique. It is an essential task which ensures that the correct imaging is performed. However, the time that a radiologist must dedicate to protocolling could otherwise be spent reporting, communicating with referrers, or teaching. To date, there have been few publications in which ML models were developed that use clinical text to automate protocol selection. This article reviews the existing literature in this field. A systematic assessment of the published models is performed with reference to best practices suggested by machine learning convention. Progress towards implementing automated protocolling in a clinical setting is discussed.