An LLM chatbot to facilitate primary-to-specialist care transitions: a randomized controlled trial

TL;DR

An LLM chatbot helped patients prepare for specialist visits, reducing consultation time and improving communication and satisfaction.

Contribution

A co-designed LLM chatbot improved care transitions by reducing consultation time and enhancing communication in a randomized trial.

Findings

PreA-only group had 28.7% shorter consultation times compared to the No-PreA group.

Physician-perceived care coordination improved by 113.1% in the PreA-only group.

Patient-reported communication ease increased by 16.0% in the PreA-only group.

Abstract

Patient-facing large language models (LLMs) hold potential to streamline inefficient transitions from primary to specialist care. We developed the preassessment (PreA), an LLM chatbot co-designed with local stakeholders, to perform the general medical consultations for history-taking, preliminary diagnoses, and test ordering that would normally be performed by primary care providers and to generate referral reports for specialists. PreA was tested in a randomized controlled trial involving 111 specialists from 24 medical disciplines across two health centers, where 2,069 patients (1,141 women; 928 men) were randomly assigned to use PreA independently (PreA-only), use it with staff support (PreA-human), or not use it (No-PreA) before specialist consultation. The trial met its primary end points with the PreA-only group showing significantly reduced physician consultation duration (28.7% reduction; 3.14 ± 2.25 min) compared to the No-PreA group (4.41 ± 2.77 min; P < 0.001), alongside significant improvements in physician-perceived care coordination (mean scores 113.1% increase; 3.69 ± 0.90 versus 1.73 ± 0.95; P < 0.001) and patient-reported communication ease (mean scores 16.0% increase; 3.99 ± 0.62 versus 3.44 ± 0.97; P < 0.001). Equivalent outcomes between the PreA-only and PreA-human groups confirmed the autonomous operation capability. Co-designed PreA outperformed the same model with additional fine-tuning on local dialogues across clinical decision-making domains. Co-design with local stakeholders, compared to passive local data collecting, represents a more effective strategy for deploying LLMs to strengthen health systems and enhance patient-centered care in resource-limited settings. Chinese Clinical Trial Registry identifier: ChiCTR2400094159.

In a trial involving 2,069 patients and 111 clinicians across 24 disciplines, patients performing a preconsultation session with an LLM-powered chatbot had a significantly lower consultation time and both patients and clinicians reported improved communication and satisfaction.

Figures