PharmMT: A Neural Machine Translation Approach to Simplify Prescription Directions

TL;DR

PharmMT is a neural machine translation system designed to automatically simplify complex prescription directions into patient-friendly language, reducing errors and pharmacist workload, with high accuracy and usability demonstrated on a large dataset.

Contribution

This work introduces a novel neural machine translation approach for prescription direction simplification, achieving significant improvements over rule-based methods and demonstrating real-world feasibility.

Findings

Achieved BLEU score of 60.27, a 39.6% improvement over rule-based normalization.

94.3% of simplified directions were judged usable by pharmacists.

Successfully processed over 530,000 prescriptions from a large pharmacy dataset.

Abstract

The language used by physicians and health professionals in prescription directions includes medical jargon and implicit directives and causes much confusion among patients. Human intervention to simplify the language at the pharmacies may introduce additional errors that can lead to potentially severe health outcomes. We propose a novel machine translation-based approach, PharmMT, to automatically and reliably simplify prescription directions into patient-friendly language, thereby significantly reducing pharmacist workload. We evaluate the proposed approach over a dataset consisting of over 530K prescriptions obtained from a large mail-order pharmacy. The end-to-end system achieves a BLEU score of 60.27 against the reference directions generated by pharmacists, a 39.6% relative improvement over the rule-based normalization. Pharmacists judged 94.3% of the simplified directions as usable as-is or with minimal changes. This work demonstrates the feasibility of a machine translation-based tool for simplifying prescription directions in real-life.