The Clinical Utility of Artificial Intelligence-enabled Electrocardiograms in the Outpatient Practice - Diagnosing Aortic Stenosis and Diastolic Dysfunction

Summary

Two recently developed artificial intelligence-enabled electrocardiogram (AI-ECG) models have been developed to detect aortic stenosis (AS) and diastolic dysfunction (DD). AI-ECG for AS has a sensitivity of 78% and specificity of 74%, and AI-ECG for DD has a sensitivity of 83% and specificity of 80%. However, these models have never been prospectively applied to diagnose AS or DD, which may be useful for patients and providers from a diagnostic and prognostic perspective and especially in settings where access to higher- level medical care is limited. In this study, we aim to determine the clinical utility of these AI-ECG models by prospectively applying them to an outpatient cohort and then completing a focused point-of-care ultrasound to evaluate those who are AI-ECG positive for AS and DD.

Eligibility

Age range

60+ years

Sex

All

Healthy volunteers

No

Interventions

• Device
  AI-ECG Dashboard

  Patients standard of care ECG's will be processed through the AI-ECG Dashboard

• Diagnostic Test
  Point of care ultrasound (POCUS)

  Patients will undergo a ultrasound to confirm diagnosis of atrial stenosis or diastolic dysfunction.

Location