Ticino Artificial InTelligence integrAtioN for Occlusion Myocardial Infarction (TITAN-OMI)

The goal of this clinical trial is to evaluate whether an artificial intelligence (AI)-based ECG interpretation tool improves the early diagnosis and treatment of occlusion myocardial infarction (OMI) in adults presenting with suspected acute coronary syndrome (ACS) who do not meet traditional ST-elevation myocardial infarction (STEMI) criteria.

The main questions it aims to answer are:

1. Does AI-assisted ECG interpretation enable more timely identification and treatment of OMI, as defined by earlier initiation of coronary intervention?
2. Does AI-assisted diagnosis reduce infarct size, measured by peak high-sensitivity troponin T (hsTnT) levels?

Researchers will compare AI-assisted ECG interpretation to standard care to determine if the AI tool improves clinical outcomes and care timelines.

Participants will:

1. Present with symptoms suggestive of ACS but without clear STEMI criteria
2. Be randomized 1:1 to either AI-assisted or standard ECG interpretation
3. Undergo follow-up assessments for cardiovascular outcomes, including 30-day death, time to treatment of total coronary occlusion, and peak hsTnT levels

Study Overview

• Status: Recruiting
• Conditions: Acute Coronary Syndrome (ACS); Myocardial Infarction (MI)
• Intervention / Treatment: Diagnostic test: AI-assisted ECG interpretation (PMcardio)

• Study Type: Interventional
• Enrollment (Estimated): 500
• Phase: Not Applicable

Contacts and Locations

Study Locations

• Switzerland
  • Canton Ticino
    • Lugano, Canton Ticino, Switzerland, 6900
      • Recruiting
      • Cardiocentro Ticino Institute
      • Contact: Marco Valgimigli, MD, PhD; Phone Number: +41 91 8115363; Email: marco.valgimigli@eoc.ch
      • Contact: Andrea Milzi, MD; Phone Number: +41 91 8115385; Email: andrea.milzi@eoc.ch
      • Principal Investigator: Marco Valgimigli, MD PhD
      • Sub-Investigator: Andrea Milzi, MD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

1. Symptoms suspected of ongoing acute myocardial ischemia: Patients presenting with symptoms such as chest pain, dyspnoea, sweating, nausea or vomiting, pain radiating to the shoulder/arm/jaw/back, fatigue, or light-headedness
2. Age: Patients aged 18 years or older.
3. Informed Consent: Patients able to provide informed consent

Exclusion Criteria:

1. Clear diagnosis of ST-segment elevation MI (STEMI) according to managing physicians.
2. Pregnancy or Lactation.
3. Legally incompetent to provide informed consent.
4. Symptoms onset>24 hrs prior to clinical presentation.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Double

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: AI-assisted ECG interpretation; Participants will receive ECG interpretation supported by a CE-marked artificial intelligence (AI) tool (PMcardio, Powerful Medical). The AI output is made available to clinicians in real time, prior to diagnostic or therapeutic decisions, to facilitate earlier identification of occlusion myocardial infarction (OMI) and potentially expedite intervention.	Diagnostic test: AI-assisted ECG interpretation (PMcardio); Participants in the experimental arm will undergo 12-lead ECG interpretation supported by a CE-marked artificial intelligence (AI) tool (PMcardio, Powerful Medical, Slovakia). The AI algorithm analyzes ECG data in real time to detect patterns suggestive of occlusion myocardial infarction (OMI), including cases not meeting traditional ST-elevation myocardial infarction (STEMI) criteria. In the experimental arm, the AI output is provided immediately to the treating clinician and used as an adjunct to standard ECG interpretation to support timely diagnosis and management decisions.
No Intervention: Standard of Care; Participants will receive standard ECG interpretation without AI support. Clinical decisions regarding diagnosis and treatment will follow usual care pathways, without influence from the AI tool. This arm serves as the comparator to evaluate the added value of AI integration.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Hierarchical primary endpoint	The primary endpoint of the prospective phase, analysed hierarchically using the unmatched, unstratified win ratio, will be a composite of: Cardiovascular mortality at 30 days.; Timely treatment of angiographically confirmed TIMI 0-1 occlusions, defined as insertion of the arterial sheath within 120 minutes from randomization.; Time-to-treatment of angiographically confirmed TIMI 0-1 occlusions.; Peak high- hsTnT levels in ng/mL as a surrogate measure of infarct size. Time of coronary intervention will be defined as time from randomisation to insertion of the arterial sheath. Peak hsTnT is defined as the maximum level of hsTnT within 48h from randomization or within 48 hours from intervention if percutaneous coronary intervention took place later than 24 hours from randomization.	30 days

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Cardiovascular mortality at 30 days	Cardiovascular mortality at 30 days	30 days
Timely treatment of TIMI 0-1 occlusions	Timely treatment is defined as arterial sheath insertion within 120 minutes of randomization	Periprocedural
Time-to-treatment of TIMI 0-1 occlusions	Expressed in minutes from time of randomization	Periprocedural
Peak hsTnT levels	Peak hsTnT is defined as the maximum level of hsTnT within 48h from randomization or within 48 hours from intervention if percutaneous coronary intervention took place later than 24 hours from randomization.	48 hours from randomization or intervention
Major adverse cardiovascular events (MACE) at follow-up	Major adverse cardiovascular events (MACE), defined as a composite of cardiovascular death, myocardial infarction, or stroke at follow up (30-days, 1 year, 3/5/10 years)	up to 10 years
Cardiovascular death at follow-up	Cardiovascular death at follow up (30-days, 1 year, 3/5/10 years)	up to 10 years
Myocardial infarction at follow-up	Myocardial infarction at follow up (30-days, 1 year, 3/5/10 years)	up to 10 years
Stroke at follow-up	Stroke at follow up (30-days, 1 year, 3/5/10 years)	up to 10 years
Infarct Size	• hsTnT area under the curve	48 hours from randomization or intervention
Infarct Size	• Creatine kinase-MB (CK-MB) peak concentration	48 hours from randomization or intervention
Infarct Size	• CK-MB area under the curve	48 hours from randomization or intervention
Time from randomization to antithrombotic therapy	Time from randomization to antithrombotic therapy (expressed in minutes)	periprocedural
Time from randomization to coronary angiography	Time from randomization to coronary angiography (expressed in minutes) This outcome will be assessed both in all patients and in patients with OMI according to the different definitions.	periprocedural
Angiographic outcomes (restricted to patients undergoing PCI)	Worst TIMI flow grade post-PCI (0-3); Worst TIMI thrombus grade post-PCI (0-5)	Periprocedural
Total time spent in the emergency department post-randomization	Total time spent in the emergency department post-randomization	periprocedural
Length of hospital stay post-randomization	Length of hospital stay post-randomization (days)	up to 30 days
Resource utilization	Number of diagnostic tests and procedures performed post-randomization before coronary angiography, including troponin measurements, transthoracic echocardiography and stress testing	periprocedural
Health economic outcomes	These include both direct and indirect costs. Direct costs are defined as medical costs incurred post-randomization during the index hospitalization or emergency department visit, including diagnostics and procedures (e.g., ECG, troponin testing, coronary angiography, PCI), medications and consumables, staff time, and length of stay. Indirect costs, defined as non-medical or societal costs up to 30 days post-randomization, including lost productivity (e.g., time off work for patients or caregivers), transportation to follow-up visits, informal caregiving support, and early rehabilitation services	30 days
Safety (Serious adverse events)		up to 10 years
Diagnostic accuracy of AI algorithm	Restricted to patients in the control group: Sensitivity; Specificity; Positive predictive value (PPV); Negative predictive value (NPV)	periprocedural
Quality of life (EuroQol 5-Dimension 5-Level [EQ-5D-5L] Index Score)	Health-related quality of life will be assessed using the EuroQol 5-Dimension 5-Level (EQ-5D-5L) instrument at discharge and 30 days post-randomization. The EQ-5D-5L descriptive system comprises five dimensions (mobility, self-care, usual activities, pain/discomfort, and anxiety/depression), each with five levels of severity. Responses are converted into a single index score using a country-specific value set. The index score typically ranges from values below 0 (worse than death) to 1 (full health), with higher scores indicating better health-related quality of life.	up to 30 days

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Pre-procedural ECG analysis	Sensitivity analysis of diagnostic accuracy of the AI-algorithm based on the 12-lead ECG recorded immediately prior to the start of coronary angiography, instead of the ECG at presentation.	periprocedural
Alternative OMI definitions	Sensitivity analysis of the primary outcome using an alternative definition of OMI: TIMI flow 0-1, or TIMI flow 2-3 in the presence of large thrombus burden (TIMI thrombus grade ≥3).	30 days

Collaborators and Investigators

• Sponsor: Cardiocentro Ticino

Study record dates

Study Major Dates

• Study Start (Actual): August 23, 2025
• Primary Completion (Estimated): August 1, 2027
• Study Completion (Estimated): September 1, 2027

Study Registration Dates

• First Submitted: July 1, 2025
• First Submitted That Met QC Criteria: July 11, 2025
• First Posted (Actual): July 22, 2025

Study Record Updates

• Last Update Posted (Actual): May 5, 2026
• Last Update Submitted That Met QC Criteria: April 29, 2026
• Last Verified: July 1, 2025

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Electrocardiogram; Occlusion Myocardial Infarction
• Additional Relevant MeSH Terms: Vascular Diseases; Cardiovascular Diseases; Pathologic Processes; Heart Diseases; Infarction; Necrosis; Myocardial Ischemia; Ischemia; Pathological Conditions, Signs and Symptoms; Myocardial Infarction; Acute Coronary Syndrome
• Other Study ID Numbers: 2024-01655

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Sharing Access Criteria: Reasonable request
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No