AI service — AI Medical · Respiratory and acoustics
Health acoustics analysis
Screen cough, breath and lung sounds with audio foundation models, and interpret spirometry alongside them.
Send us your data volume, throughput and latency targets and any constraint we should design around. You get a proposed configuration, a benchmark on your own data, and a known cost per unit of work before you commit.
Cough and breath recordings are cheap to collect and hard to interpret. These models turn short audio clips into embeddings that a classifier of your own trains on with a small labelled set, which is what makes tuberculosis and respiratory screening projects feasible at all.
Audio arrives from a phone app, a digital stethoscope or a recorded archive and comes back as embeddings or scored classes. Spirometry interpretation is a separate, non-audio step we run in the same pipeline where it is wanted.
Every output is clinical decision support, not a diagnosis: a qualified professional reviews and signs it. Where clinical use requires regulatory approval in your jurisdiction, that approval remains yours to hold — we provide the infrastructure, the model operations and the audit trail behind it.
What we size for
We build the health acoustics analysis pipeline around the workload you actually have: data format, accuracy target, latency, throughput, concurrency, retention and scheduling. Start with a pilot, then scale production capacity without changing a line of your integration.
Common use cases
- Respiratory screening — Score cough or breath recordings to prioritise follow-up testing.
- Auscultation support — Classify crackles and wheeze from digital stethoscope recordings.
- Pulmonary function review — Classify spirometry patterns alongside the acoustic signal.