Respiratory Health - The Science

Clinically validated screening for a range of respiratory diseases.

Cough AI Tuberculosis AI COVID AI

The science behind Helfie's Cough AI.

Helfie's Cough AI turns your smartphone into a screening tool that analyses cough sounds to help you make informed decisions about the health of your lungs.

Developed in partnership with Swaasa® and powered by advanced machine-learning models trained on real-world clinical datasets, Cough AI provides fast, accessible screening for tuberculosis, COVID-19, COPD, and asthma. Anytime, anywhere.

Using just a 10-second cough recording, the system extracts acoustic features linked to airflow obstruction, airway inflammation, and respiratory infection. These signals are processed through clinically validated algorithms to deliver reliable, data-driven screening results within seconds.

Why is respiratory screening important?

Respiratory diseases are among the world's leading causes of illness and death. Chronic respiratory diseases, including COPD and asthma, accounted for around 4 million deaths globally in 2019.¹ Infectious diseases such as tuberculosis and COVID-19 have added significantly to this burden, particularly in low- and middle-income countries.² ³

Cough is often an early symptom of respiratory disease, but timely screening remains limited by cost, availability of diagnostic tests, and access to specialised care. Many people delay seeking help until symptoms worsen, leading to late-stage diagnosis and poorer outcomes.

Helfie's Cough AI addresses this gap by enabling immediate, low-cost respiratory screening using a smartphone. By identifying cough patterns associated with respiratory disease, it supports timely follow-up, helps reduce delays in diagnosis, and expands access for people who would otherwise struggle to reach a clinic.

Sources
1 - Global Burden of Disease Study 2019: Chronic respiratory diseases

2 - WHO: Global tuberculosis report 2022

3 - WHO: The top 10 causes of death

How does a smartphone microphone screen for respiratory diseases?

Cough AI uses advanced acoustic analysis to transform cough recordings into meaningful health insights via a two-stage process.

1. Cough event detection

The smartphone records approximately 10 seconds of coughing. Machine-learning models identify individual coughs and separate them from background noise. The system analyses acoustic features, including frequency distribution, amplitude, airflow signatures, and sound envelope, to isolate clinically relevant cough components.

2. Disease classification

Once isolated, individual coughs are analysed using advanced deep learning models:

Tuberculosis and COVID-19:
Convolutional neural networks (CNNs) analyse cough spectrograms, while a feedforward neural network processes user information. Together, these models classify coughs as TB-positive, TB-negative, or inconclusive, and identify patterns associated with COVID-19.

COPD and Asthma:
An Audio Spectrogram Transformer (AST) analyses acoustic patterns associated with airway obstruction, inflammation, and chronic respiratory diseases such as COPD and asthma. Together, these models identify cough patterns associated with tuberculosis, COVID-19, COPD, and asthma, helping distinguish potentially concerning coughs from those less likely to indicate respiratory disease.

Is Helfie's respiratory screening clinically validated?

The underlying Swaasa® models have undergone clinical validation using data from nearly 4,700 participants across multiple hospital sites in India. Studies were conducted in partnership with Apollo Hospitals, the Government TB and Chest Hospital, and Christian Medical College (CMC) Vellore.

Reported screening perfomance:

  • 86.82%

    Tuberculosis

  • 75.54%

    COVID-19

  • 86.3%

    COPD

  • 83%

    Asthma

Sensitivity and specificity values demonstrate strong agreement with gold-standard diagnostic tests, confirming the models’ suitability as an early screening tool. Performance has been tested across diverse populations and environments, supporting broad, equitable use.

Sources

Tuberculosis: Development and clinical validation of Swaasa AI platform for screening and prioritization of pulmonary TB Scientific Reports, 2023.

COVID-19: Screening COVID-19 by Swaasa AI platform using cough sounds: a cross-sectional study Scientific Reports, 2023.

COPD, asthma: Clinical validation of Swaasa's respiratory disease screening technology medRxiv, 2025.

Cough AI Respiratory Health

Ready to get Helfie?

Take control of your health and join the waitlist.

Helfie Licensing Pty Ltd will use your email for the purpose of providing you with further information about Helfie and to give you notice when early access is available. You can find out more about how we manage your data in our Privacy policy.