The technology was already mentioned amid the COVID-19 pandemic, but it looks like American startup Hyfe is ready to take the next step. The concept is simple: Every disease causes symptoms, and when it comes to a condition that affects the airways, the sound of a cough varies slightly depending on what’s caught. For a human, it would be very complicated to differentiate between these different sounds.
But it is possible to specifically train Artificial Intelligence for this. An example of what hype manager Peter Small says “Epidemiological Acoustics”. One of the main businesses offered by Haife is tuberculosis screening. “with very low cost per patient”Professor Grant Theron at Stellenbosch University (South Africa). In the event of a positive result on application, patients can be referred “Towards a Laboratory Test” To confirm or refute the diagnosis.
This application published by Haife will soon make it possible to establish a diagnosis by listening to your cough
This dematerialization of screening may prove to be an essential asset in the fight against diseases that have almost ended in developed countries in the developing world. Of course there is also COVID-19 – but the app paves the way for more frequent diagnosis, detecting serious conditions and therefore leading to a healthier life expectancy. But for now Hyph continues to improve its app — the startup is feeding its AI with a massive amount of cough recordings to make up for it.
At this stage, an encouraging clinical trial has already been conducted on 800 people with nocturnal cough. Other steps are still required before launching this application – which is only a matter of time. Such an approach has already been explored by competitors. For example, ResApp already exists and makes it possible to quickly establish a diagnosis by recording a cough. It remains to be seen whether such screening will one day be rejected by variants using other sensors of the smartphone.
After all, they are equipped with a number of advanced sensors in addition to their microphones, such as cameras, pulse sensors and even ultra-precise LiDAR sensors on some models. It remains to be seen whether AI can eventually use this data to deliver such useful health advice.
Analyst. Amateur problem solver. Wannabe internet expert. Coffee geek. Tv guru. Award-winning communicator. Food nerd.