Google HeAR AI Model Will Diagnose Tuberculosis Through Cough Analysis 

Google HeAR is an AI model designed to detect diseases, such as tuberculosis (TB) and chronic obstructive pulmonary disease (COPD) by analyzing cough sound. 

The Health Acoustic Representations (HeAR) model, introduced this year for bio-acoustic analysis, is capable of recognizing sound patterns and generating important health information.  

Trained on a vast dataset of 300 million audio samples, including coughs, breaths, and other body sounds, the Google HeAR can identify subtle acoustic biomarkers that may indicate diseases like TB and COPD. 

Remote Areas’ AI Disease Detection 

What makes the Google HeAT model apart is its ability to detect diseases early in areas lacking healthcare facilities.  

Tuberculosis, for instance, is a curable disease that often goes undiagnosed due to the absence of reliable and affordable diagnostic tools. With its low cost and user-friendly method of detecting TB and other respiratory conditions, Google’s HeAR could lead to more timely and effective treatment. 

In another development, Google is also partnering with Indian-based healthcare company, Swaasa, to integrate HeAR into their AI tool which assesses lung health through cough sounds analysis.  

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

Eliminating Tuberculosis by 2030 

The search engine parent is also collaborating with organizations like Stop TB Partnership to bring together experts and affected communities to put an end to tuberculosis by 2030. 

“Solutions like HeAR will enable AI-powered acoustic analysis to advance tuberculosis screening and detection, offering a potentially low-impact, accessible tool for those who need it most,” digital health specialist with the Stop TB Partnership, Zhi Zhen Qin highlighted the partnership’s important role. 

However, despite its promising potential, the Google HeAR model will be accessed through smartphones, triggering a line of questions around the collection of sensitive data from these devices.  

The AI model will need extensive testing and validation to guarantee its accuracy and reliability across different populations and environments. 

Inside Telecom provides you with an extensive list of content covering all aspects of the Tech industry. Keep an eye on our Medtech section to stay informed and updated with our daily articles.