Prospective Evaluation of Cardiac Point-of-Care Ultrasound (POCUS) Performed by PEM Fellows and Artificial Intelligence on Children With Pre-existing Cardiac Conditions. (POCUS-AI PEM)

Prospective Evaluation of Cardiac Point-of-Care Ultrasound (POCUS) Performed by PEM Fellows and Artificial Intelligence Interpretation Compared With a Complete Echocardiography in Children With Preexisting Cardiac Disease

The goal of this study is to prospectively assess the diagnostic agreement of PEM fellow-performed cardiac POCUS and of AI-assisted interpretation using the Exo Iris probe, as compared to a complete echocardiography for detecting left ventricular (LV) systolic dysfunction and pericardial effusion in children with preexisting cardiac disease.

Study Overview

• Status: Not yet recruiting
• Conditions: Cardiac Anomalies
• Intervention / Treatment: Diagnostic test: AI Pocus_Cardiac

Detailed Description

Investigators hypothesize that PEM fellow-performed cardiac POCUS, when supported by AI analysis for LV dysfunction, will demonstrate diagnostic accuracy comparable to complete echocardiogram interpretation in identifying (1) pericardial effusion and (2) left ventricular systolic dysfunction in children with preexisting cardiac disease. Investigators anticipate that AI will improve accuracy and image interpretation confidence among trainees. Prospective evaluation of this method may influence future ED workflows, enhance resource utilization, support training pathways, and potentially reduce time to diagnosis in this high-risk pediatric population.

• Study Type: Observational
• Enrollment (Estimated): 200

Contacts and Locations

• Study Contact: Name: Paul Khalil, MD Medical Director Care Ultrasound Program, MD; Phone Number: 1-786-624-3742; Email: paul.khalil@nicklaushealth.org

Study Locations

• United States
  • Florida
    • Miami, Florida, United States, 33155
      • Nicklaus Children's Hospital
      • Contact: Jenny Esteves, MBA, MHSA, LPPB; Phone Number: 1-786-624-2854; Email: jenny.esteves@nicklaushealth.org
      • Principal Investigator: Paul Khalil, MD
      • Sub-Investigator: Tomas Leng, MD

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

Children aged 0-21 years with preexisting cardiac disease will be for inclusion if participants are either evaluated in the ED or in the cardiology setting. Eligible ED patients will undergo cardiac POCUS and AI assessment as part of participant's clinical assessment, while participants evaluated in the cardiology setting will undergo fellow-performed cardiac POCUS with concurrent AI-based image assessment as part of the study protocol.

Description

Inclusion Criteria:

• Children aged 0-21 years
• Preexisting cardiac disease
• Participants are either evaluated in the ED or in the cardiology setting.

Exclusion Criteria:

• Participant's clinical condition requires immediate life-saving interventions
• New diagnosis of cardiac condition
• Preexisting cardiac abnormality documented prior to the index encounter.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

cardiac disease illness; cardiac disease illness that can be examined at the ER

Diagnostic test: AI Pocus_Cardiac; assess the diagnostic agreement of PEM fellow-performed cardiac POCUS and of AI-assisted interpretation using the Exo Iris probe, as compared to a complete echocardiography for detecting left ventricular (LV) systolic dysfunction and pericardial effusion in children with preexisting cardiac disease who present to the Emergency Department (ED) and are evaluated in the cardiology setting.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
presence of pericardial effusion and LV systolic dysfunction	Diagnostic test characteristics (sensitivity, specificity, predictive values, and the Kappa statistic) for PEM fellow interpretation and AI interpretation will be calculated using complete echocardiography as the reference standard	2 years

Collaborators and Investigators

• Sponsor: Nicklaus Children's Hospital f/k/a Miami Children's Hospital

Study record dates

Study Major Dates

• Study Start (Estimated): March 30, 2026
• Primary Completion (Estimated): February 1, 2028
• Study Completion (Estimated): March 30, 2028

Study Registration Dates

• First Submitted: March 25, 2026
• First Submitted That Met QC Criteria: March 25, 2026
• First Posted (Actual): March 31, 2026

Study Record Updates

• Last Update Posted (Actual): April 8, 2026
• Last Update Submitted That Met QC Criteria: April 2, 2026
• Last Verified: March 1, 2026

More Information

Terms related to this study

• Keywords: Children; POCUS AI
• Additional Relevant MeSH Terms: Cardiovascular Diseases; Heart Diseases; Congenital Abnormalities; Cardiovascular Abnormalities; Congenital, Hereditary, and Neonatal Diseases and Abnormalities; Heart Defects, Congenital
• Other Study ID Numbers: RDC26011

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED
• IPD Plan Description: Decision to share information has not been determined yet.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: Yes
• product manufactured in and exported from the U.S.: No