Dr. Google is real! AI tool listens to you cough and determines if you have a certain disease

Have you ever received a diagnosis from Dr. Google? With an "office" open 24/7 365 days a year, all you need to do is type in your symptoms in the Google search bar and you can get some diagnosis that might or might not apply to your actual condition. That's why, when you speak to a real doctor and explain to him why you think you have a terminal condition, he will probably ask you, "Who did you get this diagnosis from, Dr. Google?"

While Dr. Google is considered a quack, Google itself is working on an AI model called "HeAR" that uses acoustic data and AI to help spot the early signs of certain diseases. One of the diseases that can be spotted early using this process is tuberculous. With most "killer" diseases, the key to survival is the speed of the diagnosis. And this is more than just some hope for the future. A respiratory healthcare company in India uses HeAR now to improve its own bioacoustic AI models.

HeAR is short for Health Acoustic Representations which is a tool that researchers can use to build AI models that, as Google says, "listen to human sounds and flag early signs of disease." Google trained HeAR using 300 million pieces of audio data and 100 million, or a third of them, were coughing sounds. In a new high-tech version of "turn to the right and cough," a Doctor (perhaps even Dr. Google) could ask you to cough and, using AI, diagnose you based on AI analysis of the cough.

According to Google, HeAR, with less training data than other AI models, outperforms its rivals. And what makes this all very exciting is that this technology can fit inside a mobile phone. The potential here is enormous. Imagine taking a smartphone into a remote area that is far away from a hospital and health care and being able to perform screening tests using a smartphone microphone instead of an expensive imaging machine like an X-ray, CT scan, or MRI.

Google has teamed with India's Salcit Technologies, a respiratory healthcare company that has its own AI bioacoustic model called Swaasa. The latter uses coughing sounds to help determine the condition of patient's lungs. Salcit is also using the sounds of patients coughing to improve Swaasa's early detection of tuberculous.

Getting Doctors to believe that they can diagnose patients by using technology like HeAR is going to be a problem. But it surely helps when a recognized organization with a great reputation such as the United Nations's StopTB Partnership supports HeAR. Eventually, you might find yourself really getting diagnosed and cured by Dr. Google.