Acoustic Respiratory AI — Research Programme

Building India's first WhatsApp-native acoustic AI screening model for respiratory disease.

Peer-reviewed literature confirms that cough acoustics carry clinically significant information about respiratory disease. Every attempt to deploy this at scale has failed — not because the science is wrong, but because models trained on clean, controlled audio degrade in real-world conditions. We train where we deploy — on WhatsApp, from real OPDs, under real acoustic conditions.

0.764
AUC — POC Validation
1,828
Recordings — POC Dataset
25,000+
Target — Full Study

Every published acoustic respiratory AI study was built on controlled-environment recordings with limited geographic and demographic diversity. None have been validated under real Indian OPD conditions — ambient noise, diverse patient populations, varying disease severity — that define actual clinical deployment environments.

None cover the full spectrum of respiratory disease with molecularly and objectively confirmed diagnosis labels. None have been trained on WhatsApp-compressed audio — the codec that 500 million Indians already use daily. This dataset does not exist. We are building it.

Domain-Matched Training

We train on WhatsApp-compressed audio from real OPDs — the same acoustic domain as deployment. Previous models trained on clean audio collapsed in production. Ours will not.

Confirmed Diagnosis Labels

Two-phase protocol separates recording from labelling. Ground truth uses GeneXpert for TB, spirometry for COPD and asthma, radiology for ILD. No provisional impressions.

Multi-Disease Classification

TB, COPD, Asthma, Bronchitis, ILD, Pleural Disease — classified simultaneously. Real OPD clinical reality, not binary TB-vs-healthy models.

Longitudinal Trajectory Data

Repeat recordings from the same patients across their treatment journey. No published acoustic respiratory AI dataset has this. Enables treatment monitoring — a new research frontier.

Geographic Diversity at Scale

Multi-site recruitment across urban, semi-urban, and rural India. Systematic demographic characterisation including occupation, city of residence, and environmental exposure.

Zero Infrastructure Deployment

Once validated, this model reaches every Indian with a respiratory concern through a single WhatsApp message — no app download, no clinic visit, no new infrastructure.

A prospective multi-centre observational study collecting cough recordings linked to confirmed clinical diagnoses across participating chest and pulmonary medicine outpatient departments in India. No intervention. No drugs. No disruption to clinical workflow.

Prospective · Multi-Centre · Observational 25,000 – 30,000 Target Recordings 18 Months Two-Phase Confirmed Diagnosis Protocol ICMR / CDSCO Compliant Three-Tier Hybrid Consent Framework
  1. 1
    A Deployable Screening Model

    A validated, WhatsApp-native acoustic respiratory AI screening model — deployable immediately to 500 million Indians without app download, without infrastructure, without clinical staff. No such model exists today.

  2. 2
    India's First Confirmed-Diagnosis Acoustic Dataset

    A large-scale, multi-disease, multi-geography acoustic respiratory dataset collected under real OPD conditions — available for future research by the academic community including all co-authoring institutions.

  3. 3
    A Published Collection Methodology

    A peer-reviewed methodology for WhatsApp-domain acoustic data collection establishing the standard for future studies globally — including the dual-track longitudinal protocol.

  4. 4
    A Treatment Monitoring Signal

    Longitudinal acoustic trajectory data across treatment journeys — enabling a treatment monitoring model for TB and COPD that could supplement expensive spirometry and GeneXpert follow-up in resource-limited settings.

  • Named co-authorship for the Respiratory Medicine team on publications targeting leading international peer-reviewed journals in respiratory medicine and AI
  • Institutional recognition as a contributing research site in all publications, presentations, and policy submissions — among a select group of leading hospitals across India
  • Priority deployment of the validated acoustic screening model before public commercialisation — built partly on your own patient data
  • Access to the validated model for non-commercial research use by your Respiratory Medicine team
  • All coordinator salary, PPE, IEC fees, and infrastructure costs funded entirely by Respiro Health — nothing falls on the participating institution
  • POC validated — 0.764 AUC on 1,828 recordings across multiple respiratory disease categories
  • ICMR TB Research Accelerator — application submitted
  • Coordinating centre established — ICMR-affiliated institution, Andhra Pradesh
  • First real-world deployment completed — village health camp, Punjab, July 2026
  • Multi-site activation in progress — Maharashtra, Punjab, Chandigarh, Lucknow, Andhra Pradesh
  • Active collaboration conversations with leading chest and pulmonary medicine departments in Pune and across India

Research Collaboration Enquiries We are actively onboarding clinical research sites across India. If your institution is interested in participating as a co-investigator site, we would welcome a conversation.

ajay.sharma@respirohealth.ai