Project · 2020–2025 · Trial complete
RAPIDx AI: AI for chest pain in the emergency department
The first AI-based randomised clinical trial for chest pain. Machine-learning decision support was embedded in emergency-department workflow across 12 South Australian hospitals, and about 14,000 patients were enrolled.
At a glance
- Status
- Trial complete
- Setting
- 12 SA Health hospitals, emergency departments
- Patients
- About 14,000
- Funding
- NHMRC partnership project, $1.23M, led by Flinders University
- Our role
- The AI was built by the group. Zhibin Liao was AI lead for the NHMRC partnership project (2021–2023); Johan Verjans is AI lead for RAPIDx AI.
Why it matters
Chest pain is one of the most common reasons people come to an emergency department, and deciding quickly who is having a heart attack is hard. RAPIDx AI tested whether machine-learning support for that decision could be built into real emergency-department workflow and evaluated as a randomised trial.
It also established the clinical-governance and integration pathway that the lab's later systems, AUScribe and AutoMedic, are built on. Results were presented at ESC Congress 2024 (ESC press release).