Using machine learning to improve handheld vascular testing
Development and Validation of a Novel Machine-learning Algorithm to Assist in Handheld Vascular Diagnostics
This study is testing a new smartphone app that uses machine learning to help doctors better understand sound data from handheld devices used in vascular testing.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 180 (estimated) |
| Sex | All |
| Sponsor | Duke University Academic / other |
| Locations | 1 site (Durham, North Carolina) |
| Trial ID | NCT02932176 on ClinicalTrials.gov |
What this trial studies
This observational study aims to enhance the use of handheld Doppler devices in clinical practice by developing a machine-learning algorithm that assists clinicians in interpreting the audio data collected during non-invasive vascular testing. The study will gather sound files from these devices and compare the algorithm's output with established vascular testing methods. The research will focus on identifying key features in the Doppler audio for patient classification and training various classification algorithms. Ultimately, the goal is to create a smartphone app for point-of-care testing based on the findings.
Who should consider this trial
Good fit: Ideal candidates for this study are individuals who have a clinically driven request for non-invasive vascular testing.
Not a fit: Patients who decline to participate in the study will not receive any benefit from this research.
Why it matters
Potential benefit: If successful, this approach could lead to faster and more accurate diagnoses of vascular conditions for patients.
How similar studies have performed: Other studies have shown promise in using machine learning for audio classification in medical diagnostics, indicating potential success for this approach.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * A clinically driven request for non-invasive vascular testing must be present Exclusion Criteria: * None (other than patient declines to participate)
Where this trial is running
Durham, North Carolina
- Duke University Medical Center — Durham, North Carolina, United States (Recruiting)
Study contacts
- Study coordinator: Leila Mureebe, MD
- Email: leila.mureebe@duke.edu
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.