RCT aiTriage Chest Pain Risk Stratification

NCT07074808 | Completed Phase 4

• 1 other identifier: CIRB 2022-2323
• Study Type: interventional
• Target: 1,120
• Locations: 1 country
• Sites: 2

Brief Summary

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.

Conditions

Chest Pain; Emergencies

Keywords

Triage; emergency medicine; risk stratification; AI

Outcome Measures

Primary Outcomes (1)

• Admission rate

  \[number of patients admitted\] divided by \[all patients presenting to ED with chest pain\]

  Throughout in ED, an average of 3 days

Secondary Outcomes (3)

• 30-day MACE

  30 days starting from admission to ED

• Hospital Length of Stay

  Within hospital stay, an average of 7 days

• HRV-ADP Admission Rate

  within hospital stay, an average of 7 days

Study Arms (2)

HRV-ADP

EXPERIMENTAL

Using aiTriage risk score for stratification

Device: aiTriage risk score

Standard Control

NO INTERVENTION

Standard control (no AI risk score)

Interventions

aiTriage risk score DEVICE

Risk score generated by AI App aiTriage for chest pain patients

HRV-ADP

Eligibility Criteria

• Age: 21 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• All ED patients (≥21 years old) with chest pain suspected of having ACS will be eligible for being included in this study.

You may not qualify if:

• Patients who are not in sinus rhythm
• Patients who do not have mental capacity.
• Patients with unstable vital signs, STEMI, obvious ACS, and non cardiac cases like rib fractures, pneumothorax.
• Patients lost to follow- up or transferred to other hospitals within the 30 day time frame.
• Patients with a high percentage of artefacts and ectopics exceeding 30% of ECG recordings will be excluded.

Sponsors & Collaborators

• Singapore General Hospital: lead

Study Sites (2)

National University Hospital

Singapore, 119074, Singapore

Location

Singapore General Hospital

Singapore, 169608, Singapore

Location

Related Publications (2)

• Mahler SA, Burke GL, Duncan PW, Case LD, Herrington DM, Riley RF, Wells BJ, Hiestand BC, Miller CD. HEART Pathway Accelerated Diagnostic Protocol Implementation: Prospective Pre-Post Interrupted Time Series Design and Methods. JMIR Res Protoc. 2016 Jan 22;5(1):e10. doi: 10.2196/resprot.4802.

  PMID: 26800789 BACKGROUND

• Ong ME, Goh K, Fook-Chong S, Haaland B, Wai KL, Koh ZX, Shahidah N, Lin Z. Heart rate variability risk score for prediction of acute cardiac complications in ED patients with chest pain. Am J Emerg Med. 2013 Aug;31(8):1201-7. doi: 10.1016/j.ajem.2013.05.005. Epub 2013 Jun 10.

  PMID: 23763936 BACKGROUND

Related Links

• aiTriage clinical trial in Singapore

MeSH Terms

Conditions

Chest Pain; Emergencies

Condition Hierarchy (Ancestors)

Pain; Neurologic Manifestations; Signs and Symptoms; Pathological Conditions, Signs and Symptoms; Disease Attributes; Pathologic Processes

Study Design

• Study Type: interventional
• Phase: phase 4
• Allocation: RANDOMIZED
• Masking: DOUBLE
• Who Masked: PARTICIPANT, INVESTIGATOR
• Purpose: SCREENING
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: ADP vs Standard

Study Record Dates

• First Submitted: June 29, 2025
• First Posted: July 20, 2025
• Study Start: November 11, 2022
• Primary Completion: November 30, 2025
• Study Completion: December 29, 2025
• Last Updated: January 8, 2026

Record last verified: 2026-01

Locations

SG (2)