Artificial intelligence accuracy in detecting pathological breath sounds in children using digital stethoscopes.
Ajay Kevat, Anaath Kalirajah, Robert Roseby
https://pubmed.ncbi.nlm.nih.gov/32993620/Actively Recruiting
Led by University of California, San Francisco · Updated on 2026-10-15
2100
Participants Needed
3
Research Sites
N/A
Total Duration
Researchers are evaluating new, faster, and simpler tests to diagnose tuberculosis TB in children under 15 years old. These studies, named Rapid Research in Diagnostics Development for TB Network R2D2 Kids and Assessing Diagnostics at Point-of-care for Tuberculosis in Children ADAPT for Kids, aim to reduce childhood TB deaths by improving diagnosis. The challenge lies in collecting sputum samples from children and the low bacteria levels in these samples, which causes delays in diagnosis and treatment. The studies will assess several novel point-of-care TB diagnostic tests including oral swab molecular testing, automated cough sound analysis, automated lung sound analysis with a digital stethoscope, and chest X-ray computer-aided detection using artificial intelligence. These tests are being evaluated for their ability to quickly and accurately detect TB without invasive sputum collection. The studies will enroll children suspected of TB and health workers to also assess the usability and acceptability of these new diagnostic tools. Participants will be children presenting with symptoms or risk factors for TB and will undergo these new diagnostic tests. Researchers will measure the proportion of positive and negative test results compared to standard TB definitions over two years. Usability will be assessed through observations and surveys of health workers. The study will monitor participants over time to evaluate the accuracy and practicality of the tests, with the goal of making TB diagnosis easier and faster in children worldwide.
CONDITIONS
Rapid Research in Diagnostics Development for TB Network (R2D2 Kids) and Assessing Diagnostics At POC for TB in Children (ADAPT for Kids)
D
Devan Jaganath, MD
B
Brittney Sweetser, MPH
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here
University of California, San Francisco
Lead Sponsor
Instituto Nacional de Saúde, Mozambique
Collaborating Sponsor
You may qualify if you...
You will not qualify if you...
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 visit (in-person)
Duration - Rolling enrollment over several years
Participants undergo novel point-of-care TB diagnostic tests including oral swab molecular testing, cough sound analysis, lung sound analysis, and chest X-ray computer-aided detection. Health workers also assess test usability.
Multiple visits depending on test evaluation schedule
Duration - 2 years
Participants are monitored over two years to assess the accuracy of the diagnostic tests by tracking positive and negative test results compared to TB diagnosis.
Periodic follow-up visits
Study Type
INTERVENTIONAL
Masking
NONE
Allocation
NA
Model
SINGLE_GROUP
Primary Purpose
DIAGNOSTIC
Number of Arms
1
Have more questions? Get in touch with our team for quick support
Ajay Kevat, Anaath Kalirajah, Robert Roseby
https://pubmed.ncbi.nlm.nih.gov/32993620/Carlos M Perez-Velez, Ben J Marais
https://pubmed.ncbi.nlm.nih.gov/22830465/Stephen M Graham, Luis E Cuevas, Patrick Jean-Philippe...
https://pubmed.ncbi.nlm.nih.gov/26409281/Stephen R C Howie
https://pubmed.ncbi.nlm.nih.gov/21346890/Peter J Dodd, Courtney M Yuen, Charalambos Sismanidis...
https://pubmed.ncbi.nlm.nih.gov/28807188/A Andama, G R Whitman, R Crowder...
https://pubmed.ncbi.nlm.nih.gov/35758702/Gayatri Devi Yellapu, Gowrisree Rudraraju, Narayana Rao Sripada...
https://pubmed.ncbi.nlm.nih.gov/36959347/Miriam Harris, Amy Qi, Luke Jeagal...
https://pubmed.ncbi.nlm.nih.gov/31479448/David M Lewinsohn, Michael K Leonard, Philip A LoBue...
https://pubmed.ncbi.nlm.nih.gov/28052967/Devan Jaganath, Jeanette Beaudry, Nicole Salazar-Austin
https://pubmed.ncbi.nlm.nih.gov/35168714/University of California, San Francisco
Lead Sponsor
Instituto Nacional de Saúde, Mozambique
Collaborating Sponsor