Cancer, Cardiotoxicity
Conditions
Brief summary
This study aims to compare conventionally acquired Left Ventricle Ejection Fraction (LVEF) and Global Longitudinal Strain (GLS) data to Artificial Intelligence (AI) driven automated processing of 2 dimensional contrast and 2 dimensional non-contrast resting transthoracic echocardiograms for application in the assessment of patients undergoing chemotherapy with cardiotoxic drugs. This is a single-centre retrospective study which utilizes echocardiographic DICOM image and meta-data datasets received from a Canadian site. Data processed using the AI driven automated processing will be compared to conventionally acquired LVEF and GLS measurements and results will be analysed to determine accuracy and precision.
Interventions
DEVICEEchoGo
EchoGo Core is a stand-alone software application. Echocardiograms should be acquired under the supervision of a physician and standard clinical protocols which includes focused apical 2, 3 and 4 chamber views. The results contain calculated measurements that will be returned to the interpreting physician. These results are intended as an additional input to standard diagnostic pathways and should only be used by a board-certified cardiologist/physician. EchoGo Core is intended to be used for the quantification and reporting of results of cardiovascular function to support physician diagnosis. EchoGo Core is indicated for use in adult populations.
Sponsors
Mazankowski Alberta Heart Institute
Ultromics Ltd
Study design
Observational model
COHORT
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Normal EF and no regional wall motion abnormalities prior to starting chemotherapy treatment. * Follow-up EF measurements available for at least 1 year during the treatment period. * Follow-up EF measurements for at least 1 year during the treatment period.
Exclusion criteria
* Age \< 18 years * Inadequate image quality (as determined by the Ultromics Operators Quality Control process)
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Compare the performance of automated EF and GLS measurements in resting transthoracic echocardiograms against conventional measurement acquisition. | Baseline | Measurements shall be compared using bias and 95% confidence intervals on bias. Regression coefficients and comparative statistics will be employed for this objective. |
| Compare the performance of automated EF and GLS measurements in resting transthoracic echocardiograms with and without the application of contrast agents. | Baseline | Measurements will be assessed using bias and 95% confidence internals on bias. Regression coefficients, comparative statistics and equivalence testing might also be employed as a comparison measure for this objective. |
Countries
Canada
Outcome results
None listed