Medication Error Detection Using Contextual Language Models

TL;DR

This paper presents a method using BERT-based contextual language models to detect medication errors in prescription texts and speech, achieving high accuracy and helping prevent medical complications.

Contribution

It introduces a novel application of BERT models for medication error detection using both textual and spoken data from real-world medical records.

Findings

Achieved up to 96.63% accuracy on text input

Achieved up to 79.55% accuracy on speech input

Demonstrated effectiveness in real-world medical data scenarios

Abstract

Medication errors most commonly occur at the ordering or prescribing stage, potentially leading to medical complications and poor health outcomes. While it is possible to catch these errors using different techniques; the focus of this work is on textual and contextual analysis of prescription information to detect and prevent potential medication errors. In this paper, we demonstrate how to use BERT-based contextual language models to detect anomalies in written or spoken text based on a data set extracted from real-world medical data of thousands of patient records. The proposed models are able to learn patterns of text dependency and predict erroneous output based on contextual information such as patient data. The experimental results yield accuracy up to 96.63% for text input and up to 79.55% for speech input, which is satisfactory for most real-world applications.