Medical-AI trial: detecting congenital heart disease from heart sounds recorded on a smartphone mic — assessing an algorithm (ausculto) (NCT07376785)
An observational study assessing ausculto, a set of computer algorithms that analyze heart sounds recorded from a smartphone built-in microphone for abnormal sounds, to tell murmurs of congenital heart disease from normal sounds and innocent murmurs. Recorded sounds are manually annotated to build a database for future AI training and testing. 220 participants; by invitation.
Trial overview (primary data)
- StatusEnrolling by invitation
- ConditionsCongenital Heart Disease (CHD)
- InterventionsDIAGNOSTIC_TEST: Computer algorithms
- SponsorThe University of Hong Kong
- Target enrollment220 participants
- Period2026-05-26 〜 2026-11-01
Key points
- An observational study assessing ausculto, software analyzing smartphone-recorded heart sounds for abnormalities.
- The primary outcome is telling murmurs of congenital heart disease (CHD) from normal sounds and innocent murmurs.
- Recorded sounds are manually annotated to build a database for future medical-AI training and testing.
- Childhood murmurs are often innocent; telling them from congenital heart disease takes expertise.
- 220 participants, by invitation. At the performance-and-data stage, not a replacement for diagnosis or an establishment of effectiveness.
- Many murmurs in children are innocent, and telling them from signs of congenital heart disease takes experience.
1Auscultation, a classic bedside skill
Abnormalities of the heart valves or blood flow can appear as a murmur in the heart sounds heard through a stethoscope. Many childhood murmurs are innocent and need no treatment, but some signal congenital heart disease (a heart defect present from birth), and telling them apart takes expertise.
If AI could distinguish abnormalities from heart sounds recorded on a smartphone microphone, it might help screen the heart even where stethoscopes and specialists are scarce.
2Evaluating a smartphone heart-sound app
This study assesses the performance of that smartphone heart-sound software, ausculto, as an observational study. Per the registry summary, ausculto is a set of computer algorithms intended to analyze heart sounds recorded from a smartphone built-in microphone and find abnormal sounds. The primary outcome is telling murmurs associated with congenital heart disease from normal sounds and innocent murmurs.
Participants have their heart sounds recorded during normal hospital attendance, and researchers manually annotate the recordings to build a database for future training and testing of medical AI. The size is 220, conducted by invitation.
3Murmurs needing no treatment, and those that do
Many murmurs in children are innocent and need no treatment. That is exactly why telling them apart is the problem.
The primary endpoint is distinguishing murmurs associated with congenital heart disease from normal sounds and innocent murmurs in the recordings. Participants have their heart sounds recorded at ordinary visits, and researchers annotate them by hand to build a database for training and validating future medical AI. Building an annotated database alongside evaluating performance is what marks the study.
Why it matters
The foundation of AI is good training data. Having experts label heart sounds gathered on a familiar smartphone supports the next stage of AI development and shows the potential to widen congenital-heart-disease screening with accessible devices (this study is at the performance-and-data stage, not an establishment of effectiveness).
FAQ
What is an innocent murmur?
Can a smartphone diagnose heart disease?
Sources (primary)
Source: ClinicalTrials.gov (U.S. NIH/NLM, public domain). This site does not provide medical advice. Verify the latest and exact details with the official source. This site is not endorsed or certified by the NIH/NLM.
- ClinicalTrials.gov (study record, original)
- NCT ID: NCT07376785