Machine Learning for Handheld Vascular Studies

Launched by DUKE UNIVERSITY · Oct 12, 2016

Keywords

ClinConnect Summary

This clinical trial is studying a way to improve the use of handheld devices called continuous wave Dopplers, which are similar to stethoscopes but are used specifically to check blood flow in the arteries. These devices are commonly used by healthcare providers, but many don't have formal training on how to use them or interpret the results correctly, which can lead to mistakes or delays in diagnosing conditions like atherosclerosis, which is a disease where arteries become narrowed. The researchers aim to develop a smart computer program, called a machine-learning algorithm, that can help doctors better understand the data from these devices. They will collect sound recordings from the devices during routine tests and compare the results to current methods used in vascular testing.

Anyone who is dealing with a medical issue that requires non-invasive vascular testing may be eligible to participate in this study. There are no specific exclusions, except for those who choose not to take part. Participants can expect to help improve the understanding of these devices without undergoing any invasive procedures, as this research will take place during routine care. If the study is successful, the smart program could later be used through a smartphone app, making it easier for doctors to assess patients on the spot.

Gender

ALL

Eligibility criteria

• Inclusion Criteria:
• • A clinically driven request for non-invasive vascular testing must be present
• Exclusion Criteria:
• • None (other than patient declines to participate)