Google, in collaboration with the Indian startup Calcite Technologies, has developed an AI model called Health Acoustic Representations (HeAR). The model was trained on 300 million audio recordings, all of which were freely available, containing sounds of breathing, sneezing, and coughing from around the world. This neural network can detect early signs of respiratory illnesses such as tuberculosis and chronic obstructive pulmonary disease. This development is particularly useful in regions with limited access to modern medical equipment. With the help of the AI application, a smartphone can alert the owner or user if they need to see a doctor. Google plans to make the model available to other developers, allowing them to train it for the detection of other diseases.