Salcit partners with Google on AI technology to detect disease based on coughs

Salcit Technologies, an India-based respiratory healthcare company, has joined forces with the Google Research team to explore how Google’s Health Acoustic Representations (HeAR), can help expand the capabilities of Salcit’s bioacoustic AI technology Swaasa.

Swaasa uses HeAR to help research and enhance early detection of tuberculosis based on cough sounds.

“Every missed case of tuberculosis is a tragedy; every late diagnosis, a heartbreak,” Sujay Kakarmath, a product manager at Google Research working on HeAR, said in a statement “Acoustic biomarkers offer the potential to rewrite this narrative. I am deeply grateful for the role HeAR can play in this transformative journey.”

Google's team trained HeAR on 300 million pieces of audio data curated from a diverse and de-identified dataset, and trained the cough model in particular using roughly 100 million cough sounds.

The company said that HeAR learns to discern patterns within health-related sounds, creating a powerful foundation for medical audio analysis.

Salcit said that Swaasa has a history of using machine learning to help detect diseases early, while at the same time bridging the gap with accessibility, affordability and scalability by offering location-independent, equipment-free respiratory health assessment.

With HeAR, Salcit aims to extend screening for TB more widely across India.

Additionally, Google Research said it has received support for the AI-enabled approach to fighting tuberculosis from the United Nations organization titled the Stop TB Partnership, which brings together TB experts and affected communities with the goal of ending TB by 2030.

“Solutions like HeAR will enable AI-powered acoustic analysis to break new ground in tuberculosis screening and detection, offering a potentially low-impact, accessible tool to those who need it most," Zhi Zhen Qin, digital health specialist with the Stop TB Partnership, said in a statement.

THE LARGER TREND

The use of sound and machine learning technologies to diagnose and monitor a variety of health conditions have been gaining traction in the past few years.

In 2022, smart stethoscope company EKO received FDA clearance for an algorithm that detects and characterizes heart murmurs in adult and pediatric patients. Eko Murmur Analysis Software is a machine learning algorithm that uses heart sounds, phonocardiograms and ECG signals to detect innocent and structural heart murmurs.

The Israeli health tech company TytoCare received $49 million in growth funding for its AI-enabled TytoCare Home Smart Clinic, which allows clinicians to conduct exams remotely, including connected device that gathers readings from its otoscope, tongue depressor, thermometer and an FDA-approved stethoscope that analyzes lung sounds for wheeze detection.

Canary Speech, a company that makes speech analysis software, entered into a partnership with Microsoft to apply AI technology to expand its machine learning speech models for healthcare. Canary offers vocal biomarker technology that captures and analyzes data to determine whether irregularities exist within an individual's speech. 

Under terms of the partnership, Canary will employ Microsoft's AI to accelerate speech analysis technology in order to reduce healthcare costs, address mental health challenges and scale remote patient monitoring solutions.

The HIMSS AI in Healthcare Forum is scheduled to take place September 5-6 in Boston. Learn more and register.