Deep Learning-Based Automated Pressure-Strain Loop Analysis
ConditionHeart Failure
Trial statusNot yet recruiting
Trial phaseNot applicable
Trial typeInterventional
Biological sexAll
Age18+
SponsorNorwegian University of Science and Technology
About this trial
Noninvasive left ventricular pressure-strain loop analysis estimates myocardial work from longitudinal strain, brachial systolic blood pressure, and cardiac valve-event timing. It provides global work index, constructive work, wasted work, and work efficiency.
This study evaluates a deep-learning method that automates myocardial work and loop-shape analysis. The method may reduce analysis time, improve reproducibility, and identify patterns associated with heart failure.
Eligibility criteria
This trial accepts healthy volunteersQualifiers
Age ≥18 years
Able to provide informed consent
Previous myocardial infarction
Left ventricular ejection fraction ≤40% after myocardial infarction
Disqualifiers
Unstable disease
Contraindication to exercise testing or echocardiography, as judged by an experienced cardiologist
Hypertension
Diabetes mellitus
Trial design
Design model
Parallel
Treatments tested in this trial
Sustained Isometric Handgrip Exercise
BehavioralParticipants perform sustained isometric handgrip at around 30 % of maximal voluntary contraction for 5 minutes during echocardiography.
Semi-Supine Bicycle Exercise
BehavioralParticipants perform graded semi-supine bicycle exercise during echocardiography.
Treatment groups
25 Participants
are divided into 2 treatment groupsGroup A: Participants With Heart FailureExperimental treatment 2 interventions
Group B: Healthy VolunteersExperimental treatment 2 interventions
Trial outcomes
Primary outcomes
1
Echocardiographic Acquisition Success
Percentage of acquired examinations successfully processed by the deep-learning pipeline to generate myocardial work indices, assessed separately at rest, during handgrip, and during bicycle exercise.
Time frame
During one study visit: at rest, during the handgrip and bicycle test.Secondary outcomes
1
Agreement Between Deep Learning- and Expert-Derived Myocardial Work Indices
Agreement for myocardial work indices will be assessed using mean bias with 95% limits of agreement, and mean absolute error.
Time frame
Echocardiograms acquired at rest and during handgrip and bicycle exercise at a single study visit.Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Norwegian University of Science and Technology
Lead sponsor
St. Olavs Hospital
Collaborator
Source ClinicalTrials.gov
This trial is not recruiting at the moment. You can still explore other options: