Streamlining evidence based clinical recommendations with large language models

TL;DR

This paper introduces Quicker, an LLM-powered system that automates evidence synthesis and generates clinical recommendations, significantly reducing time and improving accuracy in clinical decision-making processes.

Contribution

The paper presents Quicker, a novel LLM-based system that streamlines guideline development workflows and demonstrates its effectiveness through a new benchmark and empirical evaluations.

Findings

Quicker accurately decomposes questions and retrieves relevant evidence.

It improves the completeness and coherence of clinical recommendations.

System-level testing shows a reduction of recommendation development time to 20-40 minutes.

Abstract

Clinical evidence underpins informed healthcare decisions, yet integrating it into real-time practice remains challenging due to intensive workloads, complex procedures, and time constraints. This study presents Quicker, an LLM-powered system that automates evidence synthesis and generates clinical recommendations following standard guideline development workflows. Quicker delivers an end-to-end pipeline from clinical questions to recommendations and supports customized decision-making through integrated tools and interactive interfaces. To evaluate how closely Quicker can reproduce guideline development processes, we constructed Q2CRBench-3, a benchmark derived from guideline development records for three diseases. Experiments show that Quicker produces precise question decomposition, expert-aligned retrieval, and near-comprehensive screening. Quicker assistance improved the accuracy of extracted study data, and its recommendations were more comprehensive and coherent than clinician-written ones. In system-level testing, Quicker working with one participant reduced recommendation development to 20-40 min. Overall, the findings demonstrate Quicker's potential to enhance the speed and reliability of evidence-based clinical decision-making.