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.

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.

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.

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.

Decision to share information has not been determined yet.