Article

Prompt-engineering improves clinical safety of large language models for opioid equipotency conversion

2026-05-08

Abstract excerpt

<h4>Background: </h4> Large language models (LLMs) are increasingly used in medical education and clinical decision-making, but their reliability in high-risk medication dosing remains unclear. Opioid rotation is a common task requiring precise calculations where errors may result in overdose or inadequate pain relief. <h4>Methods:</h4> Thirteen LLMs were tested using an API-based framework to ensure independent q...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 27783332-08a2-5260-b3b3-8a32902f1b73
DOI: 10.64898/2026.05.06.26352590

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Prompt-engineering improves clinical safety of large language models for opioid equipotency conversionDOI 10.64898/2026.05.06.26352590Read

Development and Testing of a Novel Large Language Model-Based Clinical Decision Support Systems for Medication Safety in 12 Clinical SpecialtiesSemantic proximity Read

Rx-LLM: a benchmarking suite to evaluate safe large language model performance for medication-related tasksSemantic proximity Read

Recovering Clinical Detail in AI-Generated Responses for Low Back Pain Through Prompt DesignSemantic proximity Read

Large Language Models Are Highly Vulnerable to Adversarial Hallucination Attacks in Clinical Decision Support: A Multi-Model Assurance AnalysisSemantic proximity Read

Retrieval Augmented Generation for 10 Large Language Models and its Generalizability in Assessing Medical FitnessSemantic proximity Read

Evaluating Large Language Models’ Performance in FDA Regulatory ScienceSemantic proximity Read

A Three-Tier Operational Benchmark for Evaluating Large Language Models on Hospital Medication SafetySemantic proximity Read

Development and validation of a generative AI-assisted medication-indication knowledge baseSemantic proximity Read

Evaluating a Customised Large Language Model (DELSTAR) and its Ability to Address Medication-Related Questions Associated with Delirium: A Quantitative Exploratory StudySemantic proximity Read

Large language models management of complex medication regimens: a case-based evaluationSemantic proximity Read

General-Purpose vs. Domain-Specific Large Language Models in Antibiotic Clinical Decision-Making: A Double-Blind Evaluation with a 2×2 Factorial DesignSemantic proximity Read

Prompt Engineering in Large Language Models for Patient Education: A Systematic ReviewSemantic proximity Read