Cardiac Output
Conditions
Brief summary
Based on the monitoring data of wearable devices, with cardiac output (CO) as the gold standard, this study intends to develop a non-invasive evaluation model of CO based on wearable data, and optimize the parameters to realize the cardiac capacity detection function in resting and exercise states on the wearable device.
Interventions
OTHERExercise
Cardiac output (CO) was measured after exercise intervention in patients with normal cardiac function
Sponsors
Navy General Hospital, Beijing
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
Yes
Inclusion criteria
* Over 18 years old * Left ventricular ejection fraction (Left ventricular ejection fraction, LVEF) \< 50%(200 subjects) * Left ventricular ejection fraction (Left ventricular ejection fraction, LVEF) ≥50% (100 subjects) * Able to use smart phones and operate wearable devices such as wristbands/watches
Exclusion criteria
* Patients with pacemaker implantation * No smartphone * Currently participating in other clinical trials * Lactating women * Pregnant Women * Unable to run and ride due to personal physical and external reasons (subjects participating in the exercise state cardiac output model study) * Physical examination results in the past year have clear cardiovascular, metabolic, bone and joint related diseases that have exercise risk, or have diseases and related potential health risks confirmed by the self-examination form of physical status before exercise (participants in the exercise state cardiac output model study) * No informed consent was obtained
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| cardiac output | From enrollment to the end of follow-up at 1 month | Taking cardiac function indicators such as cardiac output by echocardiography as the gold standard, using wearable device monitoring data（Photoplethysmographic pulse wave）, the resting state cardiac output artificial intelligence machine learning model was established, and the sensitivity, specificity, positive predictive value, negative predictive value, F1 score, diagnostic efficiency Area Under Curve (AUC), and the sensitivity, specificity, positive predictive value, negative predictive value, F1 score, diagnostic efficiency of the model were calculated. AUC), precision and precision-recall curves were used to evaluate the performance of the model. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Heart failure | From enrollment to the end of follow-up at 1 month | Heart failure symptoms, acute heart failure episodes, rehospitalization rates, and cardiovascular mortality |
Contacts
Primary ContactYutao Guo
Outcome results
None listed