Machine Learning for Handheld Vascular Studies
For patients and families
In plain language
An automatic summary of structured registry data. It is an orientation aid, not a substitute for the official protocol or a physician assessment.
- What is being studied
- The protocol lists: Non-invasive vascular testing, machine-learning algorithm.
- Who it may be relevant to
- Registry conditions: Atherosclerosis, Wounds and Injuries. Basic parameters: No limits · All.
- What needs checking
- Age, condition and sex are only basic indicators. Prior treatment, laboratory values and other mandatory requirements appear in the eligibility criteria below.
- Where it takes place
- United States
- Next step
- Save the trial, show it to the treating physician, and confirm current recruitment with the study center. Costs, documents and travel →
Unsure about the terms? Read our patient guide →
Official title
Development and Validation of a Novel Machine-learning Algorithm to Assist in Handheld Vascular Diagnostics
Overview
The use of handheld arterial 'stethoscopes' (continuous wave Doppler devices) are ubiquitous in clinical practice. However, most users have received no formal training in their use or the interpretation of the returned data. This leads to delays in diagnosis and errors in diagnosis. The investigators intend to create a novel machine-learning algorithm to assist clinicians in the use of this data. This study will allow the investigators to collect sound files from the use of the devices and compare the algorithms output to established, existing vascular testing. There will be no invasive procedures, and use of these stethoscopes is part of routine clinical care. If successful, this data and algorithm will be later deployed via smartphone app for point of case testing in a separate study
Detailed description
There are three main research tasks for this project: 1) the identification of discriminant features of Doppler audio for patient classification, 2) the selection and training of classification algorithms, and 3) CWD audio data enrichment using physics-based models. The investigators will determine which discriminant features are optimal for patient classification from ultrasound Doppler audio.
To this end, the investigators will employ signal features in the frequency domain such as bandwidth, peak frequency, mean power, mean frequency, and time harmonic distortion, among others.
Furthermore, the investigators will investigate whether time domain features are necessary for accurate sound classification. Other studies have shown that specific features of audio waveforms can classify the data. The investigators will employ some of the most effective machine-learning algorithms for classification such as SVM, logistic regression, and Naïve Bayes, among others. The investigators will start with a binary classification problem in which individuals will be classified as healthy or unhealthy. Then, the investigators will move in complexity to multi-class classification problems in which individuals will be categorized into different groups according to defined abnormal arterial conditions. Data enrichment using physics-based models employing physiologically accurate finite element models of fluid flow in arteries to generate synthetic sound signals corresponding to various arterial conditions. Physics-based simulations would allow the investigators to produce a wealth of training data that can span many known arterial conditions. This capability can augment the classification accuracy and generalization of our algorithms, as clinical data may not be exhaustive enough to incorporate all the known arterial conditions. The investigators will study the performance of the trained algorithms on patient data. To this end, the investigators will partition the data into training and testing samples. The training samples will be used for training of the algorithms, while the testing set will be used to assess generalization capability. The investigators will compute misclassification rates for each algorithm as a metric for performance.
Interventions
- Device Non-invasive vascular testing
Results of clinically indicated non-invasive vascular testing will be used to develop a machine learning algorithm - Device machine-learning algorithm
Primary outcome measures
- Algorithm generated Doppler classification [Time frame: 1 year]
Secondary outcome measures (4)
- Presence or absence of pulse [Time frame: 1 year]
- Quality of pulse [Time frame: 1 year]
- Presence or absence of Doppler signal [Time frame: 1 year]
- Quality of Doppler signal [Time frame: 1 year]
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)
Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.
Healthy volunteers: Yes
Study design
- Observational model
- Cohort
Study locations
United States · 1 center
- Duke University Medical Center — Durham
Identifiers
NCT: NCT02932176 · Pro00070090