AI analysis of children's lung sounds to help diagnose tuberculosis

Automated lung sound analysis to improve the clinical diagnosis of pulmonary tuberculosis in children

NIH-funded research University of California, San Francisco · NIH-11192324

This project uses AI to listen to children's lung sounds with a digital stethoscope to help doctors decide if a child may have pulmonary tuberculosis.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionUniversity of California, San Francisco NIH-funded
Lab location1 site (San Francisco, United States)
Project IDNIH-11192324 on NIH RePORTER

What this research studies

The team will record lung sounds from children using digital stethoscopes and run them through an AI system called Lung AI to detect patterns linked to pulmonary TB. They will add the AI output to WHO TB treatment decision algorithms to try to reduce false positives while keeping cases from being missed. The work uses well-characterized pediatric TB cohorts and UCSF expertise to train and test the algorithms on real clinical data. The focus is on clinics where chest X-rays are scarce or hard to read, and researchers will compare AI results to standard clinical and laboratory findings.

Who could benefit from this research

Good fit: Children (infants through about 10–11 years old) who are being evaluated for possible pulmonary TB, especially at clinics without easy access to chest X-rays, are the best fit for this work.

Not a fit: Children whose TB is already confirmed by reliable laboratory tests or who have extrapulmonary TB not detectable by lung sounds may not benefit from this approach.

Why it matters

Potential benefit: If successful, this could help doctors more accurately identify children who need TB treatment and avoid unnecessary treatment for those who do not.

How similar studies have performed: Similar AI methods for lung-sound analysis have shown promise for spotting lower respiratory infections, but using them specifically to improve pediatric TB decision algorithms is a relatively new application.

Where this research is happening

San Francisco, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.