Clinical Predictive Keyboard using Statistical and Neural Language Modeling

TL;DR

This paper explores the use of statistical and neural language models to predict clinical text, demonstrating significant accuracy and potential time savings for physicians in radiology report authoring.

Contribution

It introduces a novel application of neural language models in clinical text prediction, evaluating their effectiveness in medical report contexts.

Findings

Neural models achieve up to 51.3% accuracy in radiology reports.

Models can significantly reduce keystrokes for physicians.

Application of language models can expedite clinical documentation.

Abstract

A language model can be used to predict the next word during authoring, to correct spelling or to accelerate writing (e.g., in sms or emails). Language models, however, have only been applied in a very small scale to assist physicians during authoring (e.g., discharge summaries or radiology reports). But along with the assistance to the physician, computer-based systems which expedite the patient's exit also assist in decreasing the hospital infections. We employed statistical and neural language modeling to predict the next word of a clinical text and assess all the models in terms of accuracy and keystroke discount in two datasets with radiology reports. We show that a neural language model can achieve as high as 51.3% accuracy in radiology reports (one out of two words predicted correctly). We also show that even when the models are employed only for frequent words, the physician can save valuable time.