Artificial Intelligence System for Early Warning of Adverse Events in Acute Myocardial Infarction

NCT07139860 | Recruiting

• 1 other identifier: BFH2023063001
• Study Type: observational
• Target: 1,400
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this observational study is to learn about the effectiveness of an artificial intelligence-based early warning system for predicting adverse events in patients with acute myocardial infarction (AMI). The main question it aims to answer is: Does an AI-based early warning system improve the assessment and prediction of adverse events across the full course of AMI care (from prevention to diagnosis, treatment, and rehabilitation)? Participants who are receiving routine medical care for AMI in tertiary hospitals will have their multimodal medical data (clinical records, diagnostic tests, imaging, treatment pathways) collected and analyzed. Data will be integrated using innovative cross-modal representation methods and predictive models. The study will follow patients during their hospital stay and subsequent clinical follow-up to evaluate the feasibility, accuracy, and clinical value of the AI-based early warning system.

Conditions

Acute Myocardial Infarction With ST Elevation; Intelligent Management Platform; Early Warning

Outcome Measures

Primary Outcomes (1)

• MACCE

  Cardiac death All-cause mortality Malignant arrhythmia Non-fatal recurrent myocardial infarction Non-fatal stroke Unplanned repeat revascularization Rehospitalization for heart failure

  1-3 years

Study Arms (2)

BFH

group1

AZH

group2

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

1. Retrospective Study Population: Data were obtained from the Cardiovascular Center Database (CBDBank) of Beijing Friendship Hospital. CBDBank is a continuously collected sample dataset of patients with acute coronary syndrome since January 2013. A total of 1,000 patients with acute myocardial infarction admitted to Beijing Friendship Hospital, Capital Medical University, from January 2017 to December 2019 were included in the retrospective cohort. After discharge, all patients received scheduled telephone follow-ups at 1 month, 3 months, 6 months, and annually thereafter, with continuous follow-up for 3 years. 2. Prospective Study Population: A total of 800 patients with acute myocardial infarction admitted to the Cardiovascular Center of Beijing Friendship Hospital from July 2023 to July 2026 will be enrolled in the prospective cohort. Randomization will be performed using random codes, and prognosis prediction will be conducted using either the predictive system or traditional met

You may qualify if:

• \. Hospitalized patients who meet the diagnostic criteria for acute myocardial infarction. 2. Patients who agree to participate and sign the informed consent form.

You may not qualify if:

• \. Patients with terminal malignant tumors and an expected survival time of less than 3 months. 2. Patients with complete disability and inability to communicate. 3. Patients unable to comply with follow-up.

Sponsors & Collaborators

• Hui Chen: lead

Study Sites (1)

Beijing Friendship Hospital

Beijing, 100050, China

RECRUITING

MeSH Terms

Conditions

ST Elevation Myocardial Infarction

Condition Hierarchy (Ancestors)

Myocardial Infarction; Myocardial Ischemia; Heart Diseases; Cardiovascular Diseases; Vascular Diseases; Infarction; Ischemia; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Necrosis

Central Study Contacts

Hui Chen

CONTACT

+86 13910710028; 13910710028@163.com

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: OTHER
• Target Duration: 1 Year
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: PHD

Study Record Dates

• First Submitted: August 22, 2025
• First Posted: August 24, 2025
• Study Start: November 26, 2022
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): December 31, 2026
• Last Updated: August 24, 2025

Record last verified: 2025-08

Locations

CN (1)