Evaluation of Clinical Intelligence Support to Reduce Errors in Normal ECGs

NCT07179185 | Not Yet Recruiting

• 1 other identifier: 409604/2022-4
• Study Type: interventional
• Target: 710
• Locations: 0 countries
• Sites: N/A

Brief Summary

This study will evaluate the performance of specialist physicians in interpreting normal electrocardiograms (ECGs) with and without the assistance of an artificial intelligence (AI) neural network. The primary aim is to determine whether AI support affects the rate of false-positive interpretations of normal tracings. Secondary aims include evaluating the time required for interpretation, the sensitivity for detecting abnormalities, and the effect on false positives in ECGs with major abnormalities according to the Minnesota Code system. All ECGs in the sample will be reviewed by a panel of three specialists, to determine the reference classification.

Conditions

Electrocardiogram; Cardiovascular Abnormalities

Keywords

artificial intelligence; electrocardiography; diagnostic methods; telemedicine; normal electrocardiogram

Outcome Measures

Primary Outcomes (1)

• Precision (Positive Predictive Value) for detection of normal ECG tracings

  Precision (Positive Predictive Value) of detecting normal ECG by the physician or physician+model compared against the reference standard defined by a panel of three specialists. Precision (Positive Predictive Value) is defined by the number of true positive normal cases divided by all positive predictions.

  One week

Secondary Outcomes (3)

• Sensitivity, Specificity, Negative Predictive Value, and F1 score for detection of normal ECG tracings

  One week

• ECGs with major abnormalities incorrectly classified as normal

  One week

• Time of analysis for normal cases (seconds per case)

  One week

Study Arms (2)

Control - Specialist Interpretation Without AI

ACTIVE COMPARATOR

Specialist physicians interpret normal ECGs without the assistance of the AI-ECG tool. ECGs are routine tracings performed by the Rede de Telemedicina de Minas Gerais (RTMG). Final classification for study endpoints will be based on a panel review by three specialists.

Diagnostic Test: Specialist ECG Interpretation Without AI

Specialist interpretation with AI assistance

EXPERIMENTAL

Specialist physicians interpret ECGs using the AI-ECG tool, which provides automated classification support indicating whether the ECG is normal or not. ECGs are routine tracings performed by RTMG. Final classification for study endpoints will be based on a panel review by three specialists.

Diagnostic Test: AI-Assisted ECG Interpretation (AI-ECG)

Interventions

AI-Assisted ECG Interpretation (AI-ECG) DIAGNOSTIC_TEST

Neural network-based AI software that analyzes ECG tracings and provides a classification as normal suggestion to the interpreting specialist.

Specialist interpretation with AI assistance

Specialist ECG Interpretation Without AI DIAGNOSTIC_TEST

Manual interpretation of ECGs by specialists without AI support, following standard diagnostic procedures

Control - Specialist Interpretation Without AI

Eligibility Criteria

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

You may qualify if:

• ECGs performed routinely by the Rede de Telemedicina de Minas Gerais (RTMG)

You may not qualify if:

• ECGs from patients younger than 18 years

Sponsors & Collaborators

• Federal University of Minas Gerais: lead
• Uppsala University: collaborator

Related Publications (3)

• Oliveira CRA, Paixao GMM, Tostes VC, Gomes PR, Mendes MS, Paixao MC, Marcolino MS, Ribeiro ALP. Upscaling a regional telecardiology service to a nationwide coverage and beyond: the experience of the Telehealth Network of Minas Gerais. BMJ Glob Health. 2025 Jan 19;10(1):e016692. doi: 10.1136/bmjgh-2024-016692.

  PMID: 39828428 BACKGROUND

• Ribeiro ALP, Paixao GMM, Gomes PR, Ribeiro MH, Ribeiro AH, Canazart JA, Oliveira DM, Ferreira MP, Lima EM, Moraes JL, Castro N, Ribeiro LB, Macfarlane PW. Tele-electrocardiography and bigdata: The CODE (Clinical Outcomes in Digital Electrocardiography) study. J Electrocardiol. 2019 Nov-Dec;57S:S75-S78. doi: 10.1016/j.jelectrocard.2019.09.008. Epub 2019 Sep 7.

  PMID: 31526573 BACKGROUND

• Ribeiro AH, Ribeiro MH, Paixao GMM, Oliveira DM, Gomes PR, Canazart JA, Ferreira MPS, Andersson CR, Macfarlane PW, Meira W Jr, Schon TB, Ribeiro ALP. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat Commun. 2020 Apr 9;11(1):1760. doi: 10.1038/s41467-020-15432-4.

  PMID: 32273514 BACKGROUND

MeSH Terms

Conditions

Cardiovascular Abnormalities

Condition Hierarchy (Ancestors)

Cardiovascular Diseases; Congenital Abnormalities; Congenital, Hereditary, and Neonatal Diseases and Abnormalities

Central Study Contacts

Antonio Luiz P. Ribeiro, MD, PhD

CONTACT

55(31)3307-9201; alpr@ufmg.br

Gabriela Miana M. Paixão, MD, PhD

CONTACT

55(31) 3307-9201; gabimiana@gmail.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Full Professor, Internal Medicine Department, School of Medicine

Study Record Dates

• First Submitted: September 11, 2025
• First Posted: September 17, 2025
• Study Start: October 1, 2025
• Primary Completion: October 5, 2025
• Study Completion: November 1, 2025
• Last Updated: September 22, 2025

Record last verified: 2025-09

Data Sharing

• IPD Sharing: Will not share