Is That the Right Dose? Investigating Generative Language Model Performance on Veterinary Prescription Text Analysis
Brian Hur, Lucy Lu Wang, Laura Y. Hardefeldt, Meliha Yetişgen · 2024
Optimizing antibiotic dosing recommendations is a vital aspect of antimicrobial stewardship (AMS) programs aimed at combating antimicrobial resistance (AMR), a significant public health concern, where inappropriate dosing contributes to the selection of AMR pathogens.A key challenge is the extraction of dosing information, which is embedded in free-text clinical records and necessitates numerical transformations.This paper assesses the utility of Large Language Models (LLMs) in extracting essential prescription attributes such as dose, duration, active ingredient, and indication.We evaluate methods to optimize LLMs on this task against a baseline BERT-based ensemble model.Our findings reveal that LLMs can achieve exceptional accuracy by combining probabilistic predictions with deterministic calculations, enforced through functional prompting, to ensure data types and execute necessary arithmetic.This research demonstrates new prospects for automating aspects of AMS when no training data is available.Output the dosage in mg/kg.Dose is determined by multiplying the total dose units given per administration multiplied by the size of the medication in mg, dividing by the weight of the patient in kg to determine the mg per kg ** Example: ** Item Label: Disp By: ***: Dog 21.00 x Clinacin Tabs 150Mg One \& half (1.5) tablets twice a day with food *** ** Item Name: Clinacin Tabs 150Mg (100) Clindamycin ** Weight: 30kgs ** Medication Unit Size: 150.0 **