The goal of this study is to develop a wearable sensor system that can estimate left ventricular ejection fraction (LVEF), which is a measurement of the heart's function.
Study Type
OBSERVATIONAL
Enrollment
500
Colorado Heart and Vascular
Golden, Colorado, United States
Clearwater Cardiovascular Consultants
Clearwater, Florida, United States
Midwest Cardiovascular Institute
Naperville, Illinois, United States
Cardiovascular Institute of the South
Houma, Louisiana, United States
Correlation between wearable-derived and transthoracic echocardiography-derived left ventricular ejection fraction estimates
The primary analysis will compute the correlation coefficient (r) between wearable-derived model estimates of LVEF and transthoracic echocardiography-derived LVEF in the Hold-Out Test Set. The prespecified performance target is r \> 0.70.
Time frame: From baseline through study completion (up to 6 months) at each paired assessment
Clinical accuracy of wearable-derived LVEF compared with echocardiography
Proportion of predictions within ±5 percentage points of TTE-derived LVEF in the Hold-Out Test Set. Error metrics will be calculated as Mean Absolute Error (MAE) between wearable-derived and TTE-derived LVEF. Differences across subgroups will be tested with ANOVA or Kruskal-Wallis as appropriate. Prespecified performance target: MAE ≤ 5 percentage points.
Time frame: From baseline through study completion (up to 6 months) at each paired assessment
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.
Strong Memorial Hospital
Rochester, New York, United States
Cardiology Consultants of Philadelphia
Yardley, Pennsylvania, United States
Stern Cardiovascular Center
Germantown, Tennessee, United States