Diagnostic Accuracy of a Deep Learning-Based Software for Automated Multiparametric Echocardiographic Measurements
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorCentro Cardiologico Monzino
About this trial
Transthoracic echocardiography is an essential imaging modality for the diagnosis and follow-up of cardiovascular diseases. Comprehensive echocardiographic assessment requires multiple quantitative measurements of cardiac structure and function, which are time-consuming and highly dependent on operator expertise. US2.AI (Us2.v1) is an artificial intelligence (deep learning)-based software designed to automatically analyze standard two-dimensional and Doppler echocardiographic DICOM video clips acquired from different ultrasound vendors. The software provides automated measurements of cardiac morphology and function, including chamber dimensions and volumes, left and right ventricular systolic and diastolic function, myocardial strain, and Doppler-derived parameters, generating a comprehensive echocardiographic report based on current international guideline recommendations. In addition, the software may assist in identifying echocardiographic features suggestive of several cardiovascular conditions, including heart failure, pulmonary hypertension, hypertrophic cardiomyopathy, cardiac amyloidosis, valvular heart disease, and ischemic cardiomyopathy.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Adults aged 18 years or older.
Undergoing clinically indicated standard transthoracic echocardiography.
Adequate echocardiographic image quality for automated and expert analysis.
Written informed consent provided prior to study participation.
Disqualifiers
Age <18 years.
Frequent and/or complex cardiac arrhythmias during echocardiographic examination.
Suboptimal echocardiographic images.
Trial population
Consecutive adult patients undergoing clinically indicated standard transthoracic echocardiography at seven high-volume echocardiography laboratories with experienced operators.
Trial design
Design model
Cohort
Time perspective
Prospective
Treatments tested in this trial
Not listed
Trial groups
1,157 Participants
are grouped into 1 trial groupGroup A: Prospective Cohort
Trial outcomes
Primary outcomes
1
Agreement between AI-derived and expert-derived echocardiographic measurements across predefined patient subgroups
Comparison of the agreement between automated and expert-derived measurements in predefined subgroups, including participants with normal echocardiographic findings and those with specific cardiovascular diseases.
Time frame
January 20272
Agreement between AI-derived and expert-derived echocardiographic measurements
Agreement between automated echocardiographic measurements generated by the US2.AI software and manual measurements performed by experienced echocardiographers (reference standard) across standard two-dimensional, Doppler, and strain parameters.
Time frame
Jan 20273
Time required for echocardiographic analysis
Comparison of the time required to obtain a complete set of echocardiographic measurements using manual analysis by experienced echocardiographers versus automated analysis by the US2.AI software.
Time frame
January 2027Secondary outcomes
1
Agreement between AI-assisted and expert final echocardiographic diagnoses
Agreement between the final echocardiographic diagnosis suggested by the US2.AI software and the final diagnosis reported by the expert echocardiographer.
Time frame
January 2027Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Centro Cardiologico Monzino
Lead sponsor
Azienda Ospedaliero Universitaria Policlinico Modena
Collaborator
Universita di Verona
Collaborator
Monaldi Hospital, Napoli, Italy
Collaborator
ASST Grande Ospedale Metropolitano Niguarda
Collaborator
Policlinico G . Martino, Messina Italy
Collaborator
Ospedale San Giovanni Evangelista Tivoli
Collaborator
Source ClinicalTrials.gov