# A large language model for complex cardiology care

## TL;DR

A large language model helped general cardiologists manage complex heart cases better than usual care, as judged by specialists.

## Contribution

A tailored large language model improved complex cardiology care in a randomized trial with real-world patient data.

## Key findings

- Subspecialists preferred AMIE-assisted assessments in 46.7% of cases, versus 32.7% for cardiologists alone.
- AMIE-assisted cardiologists had fewer errors and missing content compared to those working alone.
- Physicians using AMIE reported it helped their assessments over half the time and saved time in 50.5% of cases.

## Abstract

The scarcity of subspecialist medical expertise poses a considerable challenge for healthcare delivery. This issue is particularly acute in cardiology, where timely, accurate management determines outcomes. We explored the potential of Articulate Medical Intelligence Explorer (AMIE), a large language model-based experimental medical artificial intelligence system, to augment clinical decision-making in this challenging context. We conducted a randomized controlled trial comparing large language model-assisted care with the usual care of complex patients suspected of having a genetic cardiomyopathy, and we curated a real-world dataset of complex cases from a subspecialist cardiology practice. Nine participating general cardiologists were provided with access to both clinical text reports and raw diagnostic data—including electrocardiograms, echocardiograms, cardiac magnetic resonance imaging scans and cardiopulmonary exercise testing—and were randomized to manage these cases, either with or without assistance from AMIE. We developed a ten-domain evaluation rubric used by three blinded subspecialists to evaluate the quality of triage, diagnosis and management. In our randomized controlled trial with retrospective patient data, subspecialists favored large language model-assisted responses overall, and for the management plan and diagnostic testing domains, with the remaining domains considered a tie. Overall, subspecialists preferred AMIE-assisted cardiology assessments 46.7% of the time, compared with 32.7% for cardiologists alone (P = 0.02), with 20.6% rated as a tie. Subspecialists also quantified errors, extra and missing content, reasoning and potential bias. Cardiologists alone had more clinically significant errors (24.3% versus 13.1%, P = 0.033) and more missing content (37.4% versus 17.8%, P = 0.0021) than cardiologists assisted by AMIE. Lastly, cardiologists who used AMIE reported that AMIE helped their assessment more than half the time (57.0%) and saved time in 50.5% of cases.

In a randomized study involving 9 general cardiologists and 107 real-world patient cases, assistance from a specifically tailored large language model resulted in preferable responses on complex case management compared to physicians alone, as rated by specialist cardiologists using a multidimensional scoring rubric.