RCT aiTriage Chest Pain Risk Stratification

Chest Pain, Emergencies

Triage, emergency medicine, risk stratification, AI

Chest pain is one of the most common reasons people visit the Emergency Department (ED). While most cases are not serious, a small number may lead to life-threatening heart problems, known as Major Adverse Cardiac Events (MACE). Emergency staff need to quickly identify these high-risk patients, but current methods often take time, involve lab tests, and strain already busy EDs. In Singapore, for example, SGH sees over 120,000 ED patients a year. In the U.S., chest pain accounts for around 8-10 million ED visits annually, yet fewer than 10% are ultimately diagnosed with MACE. Still, over half of chest pain patients undergo extensive and costly testing, adding up to $10-13 billion each year. This over-testing is done to avoid missing a critical case, but it's inefficient and stressful for both staff and patients. Traditional risk scoring tools like TIMI, GRACE, HEART, and EDACS require time and blood test results, delaying early intervention. Waiting times in EDs can be 1-2 hours, during which patient conditions may worsen unnoticed. To address this, we've developed aiTriage, a portable device that uses AI to analyze heart rate variability, ECG readings, blood pressure, and oxygen levels. It provides a real-time risk score within 5 minutes, helping doctors decide which patients need urgent care. Unlike current methods, aiTriage works without waiting for lab tests and can ease the load on EDs. No existing devices offer real-time MACE risk scoring like aiTriage. Our previous studies show that this system outperforms standard tools and could transform how chest pain is managed in emergency care, saving time, money, and lives.

Primary Aim * To compare the admission rate defined as number of patients admitted/ all patients presenting to ED with chest pain (Inpatient admission or Emergency Observation Ward admission) of HRV guided accelerated diagnostic protocol (HRV-ADP) to the current standard protocol. * To evaluate the implementation of HRV-ADP and understand the potential factors affecting implementation success in routine practice using the REAIM/PRISM framework Secondary Aim * To determine 30-day MACE between groups for discharged patients. * To determine ED length of stay from registration to admission decision between groups. * To calculate predicted aiTriage HRV-ADP admission rate vs actual (control group). Primary Hypothesis - There will be a 10-20% reduction in admission rate with HRV-ADP comparing to the Standard protocol currently in practice. Secondary Hypothesis \- There is no increase in Major Adverse Cardiac Events (MACE) between groups for discharged patients.

No related papers found yet.

Singapore