AI-ECG for One-Year Mortality Risk Prediction

An Artificial Intelligence-Based Electrocardiogram Analysis System for One-Year Mortality Risk Prediction

Cardiovascular disease (CVD) remains one of the leading causes of death worldwide. While the electrocardiogram (ECG) is a standard, widely accessible tool for cardiovascular screening, traditional risk assessment models often rely heavily on blood test results, which may be unavailable in electronic health records (EHRs). To address this limitation, the Chang Gung ECG Mortality Risk Prediction Software, an artificial intelligence (AI)-based Software as a Medical Device (SaMD), was developed. The software analyzes standard 10-second, 12-lead resting ECG signals to predict the probability of cardiac-related mortality within one year.

This study is a multicenter retrospective cohort study designed to validate the clinical performance of the AI software. Researchers will analyze retrospectively collected ECG data from patients aged 20 years or older with suspected cardiovascular disease across three hospitals in Taiwan. The AI model's predictions will be compared with the actual one-year mortality outcomes documented in the patients' medical records. The primary objective is to determine whether the AI model can accurately and consistently stratify patients according to their risk of cardiac-related mortality (e.g., heart failure, arrhythmia, and myocardial infarction), with an area under the receiver operating characteristic curve (AUC) greater than 0.80. The software is intended to serve as a clinical decision-support tool for long-term risk stratification in non-acute clinical settings, thereby assisting physicians in clinical decision-making and long-term patient management.

Study Overview

• Status: Completed
• Conditions: Electrocardiogram; Mortality Risk Prediction
• Intervention / Treatment: Device: Chang Gung ECG Mortality Risk Prediction Software (Model: CGMH-DRP-001)

Detailed Description

Cardiovascular disease (CVD) is a major global health burden. Current cardiovascular risk assessment models (e.g., Framingham and QRISK) rely heavily on blood biochemical data, which limits their applicability when electronic health record (EHR) data are incomplete. The 12-lead resting electrocardiogram (ECG) is a rapid, non-invasive, and widely accessible screening tool. Recent advances in artificial intelligence (AI), particularly deep learning models such as ResNet, have demonstrated superior capabilities for automatically extracting clinically relevant features from ECG signals to predict cardiovascular risk.

This national multi-center retrospective study aims to evaluate the clinical performance of the Chang Gung ECG Mortality Risk Prediction Software, a standalone Software as a Medical Device (SaMD). The core algorithm utilizes a 1D-ResNet-18 convolutional neural network to analyze 10-second, 12-lead resting ECG signals sampled at 500 Hz with a 60-Hz Alternating Current (AC) filter. The software outputs the predicted probability of cardiac-related mortality within one year to assist physicians in non-acute clinical settings.

Study Methodology: The study will retrospectively collect de-identified electronic health records and ECG data obtained between August 2011 and September 2024 from three institutions in Taiwan: Tri-Service General Hospital, Kaohsiung Armed Forces General Hospital, and Taipei Municipal Wanfang Hospital. Only the first eligible ECG from each patient will be included to avoid intra-individual bias.

The AI model's predictions will be compared with the actual one-year mortality outcomes. To improve interpretability, cardiologists with more than five years of clinical experience will review high-risk predictions using Gradient-weighted Class Activation Mapping (Grad-CAM). A prediction will be considered clinically interpretable only if both the predicted risk and the corresponding Grad-CAM localization are deemed clinically reasonable.

Statistical Analysis: The study employs a one-tailed superiority design with a significance level of 0.05. The null hypothesis states that the area under the receiver operating characteristic curve (AUC) is ≤0.80, whereas the alternative hypothesis states that the AUC is >0.80. Subgroup analyses will be performed according to age groups (e.g., 20-40, 41-60, and >60 years) and disease categories (e.g., arrhythmia, myocardial infarction, and heart failure). DeLong's test will be used to evaluate the model's predictive performance across different demographic and clinical subgroups.

Data Privacy and Federated Learning: All patient data will be strictly de-identified in accordance with Health Insurance Accountability and Portability Act (HIPAA) guidelines and analyzed within secure, closed intra-hospital networks. If the initial validation does not achieve the predefined performance target (AUC >0.80), a horizontal federated learning architecture will be implemented. Up to 10% of the available dataset will be used for model fine-tuning, after which the updated model will be independently validated using a separate untouched dataset to ensure robustness and prevent data contamination.

• Study Type: Observational
• Enrollment (Actual): 461982

Contacts and Locations

Study Locations

• Taiwan
  • Kaohsiung City, Taiwan, 807
    • Kaohsiung Armed Forces General Hospital
  • Taipei, Taiwan, 114
    • Tri-Service General Hospital
  • Taipei, Taiwan, 114
    • Taipei Municipal Wanfang Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: N/A

• Sampling Method: Non-Probability Sample

Study Population

The study population consists of adult patients (aged 20 years and older) with suspected cardiovascular disease who underwent standard 12-lead resting electrocardiogram (ECG) examinations. Data will be retrospectively collected from three medical institutions in Taiwan-Tri-Service General Hospital, Kaohsiung Armed Forces General Hospital, and Taipei Municipal Wanfang Hospital-between August 2011 and September 2024. The study population represents a diverse real-world patient population across multiple clinical settings, including outpatient clinics, inpatient wards, and emergency departments, with comprehensive documentation of clinical diagnoses and one-year mortality outcomes.

Description

Inclusion Criteria:

• Adults aged 20 years and older.
• Patients who underwent a 12-lead resting electrocardiogram (ECG).
• ECG records must meet the software input specifications: 12 leads, a sampling rate of 500 Hz, a 60-Hz Alternating Current (AC) filter, a recording duration of 10 seconds, and Extensible Markup Language (XML) file format.
• Only the first eligible 12-lead ECG record from each patient will be included to avoid intra-individual bias.

Exclusion Criteria:

• ECG records with missing leads.
• Cases with missing demographic information (e.g., age, sex, or mortality status) or incomplete clinical diagnostic data.
• ECG records that do not meet the software input specifications (e.g., an incorrect sampling rate, AC filter setting, recording duration, or file format).
• Pregnant women and patients with implanted pacemakers..

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Area Under the Receiver Operating Characteristic Curve (AUC) for Predicting One-Year Cardiac-Related Mortality	The primary outcome measure is the area under the receiver operating characteristic curve (AUC) for predicting one-year cardiac-related mortality. The AI model's predictions will be retrospectively compared with the actual one-year mortality outcomes documented in electronic health records (EHRs) and the death registry. The study will be considered successful if the observed AUC is greater than 0.80.	Up to 1 year (365 days) from the index ECG examination.

Collaborators and Investigators

• Sponsor: National Defense Medical Center, Taiwan
• Collaborators: Taipei Medical University WanFang Hospital; Kaohsiung Armed Forces General Hospital
• Investigators: Principal Investigator: Chin Lin, PhD, National Defense Medical Center

Study record dates

Study Major Dates

• Study Start (Actual): April 1, 2025
• Primary Completion (Actual): July 21, 2025
• Study Completion (Actual): July 21, 2025

Study Registration Dates

• First Submitted: June 15, 2026
• First Submitted That Met QC Criteria: June 15, 2026
• First Posted (Actual): June 22, 2026

Study Record Updates

• Last Update Posted (Actual): June 24, 2026
• Last Update Submitted That Met QC Criteria: June 21, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Other Study ID Numbers: A202503002

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

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