Using AI to detect COVID-19 in lung images and breath sounds

EPFL researchers have developed DeepChest and DeepBreath, new deep learning algorithms that identify patterns of COVID-19 in lung images and breath sounds.

Using artificial intelligence (AI), Dr. Mary-Anne Hartley, a medical doctor and researcher in EPFL’s Intelligent Global Health group (iGH) and team, have developed new algorithms to identify patterns of COVID-19 in lung images and breath sounds. The algorithms called DeepChest and DeepBreath can accurately diagnose the novel coronavirus in patients and predict how ill they are likely to become.

“We have named the new deep learning algorithms DeepChest (use of lung ultrasound images) and DeepBreath (breath sounds heard using a digital stethoscope). AI helps us to better understand complex patterns in these basic clinical examinations. The results so far are very promising,” explains Martin Jaggi, machine learning specialist at EPFL.

Since the beginning of the COVID-19 pandemic, Dr Hartley’s research team has been working with nearby the two university hospitals in Lausanne and Geneva were also involved in the research, at whose departments necessary clinical data such as lung ultrasound images and breath sounds were collected in studies before the outbreak of the corona pandemic.

As principal investigator at Lausanne’s University Hospital, Dr Noémie Boillat-Blanco explains that the project started in 2019, at first trying to identify markers that would enable better identification of viral pneumonia versus bacterial ones. However, the project took a more specific COVID focus in 2020. “Many of the patients who agreed to take part in our study were scared and very ill,” she said, “but they wanted to contribute to broader medical research, just like we do. I think there is a collective motivation to learn something from this crisis and to rapidly integrate new scientific knowledge into everyday medical practice.”

The DeepBreath algorithm is expected to be available by the end of the year and should make it possible to diagnose Covid-19 based on breath sounds. Amazingly, initial results also suggest that DeepBreath is even able to detect asymptomatic Covid by detecting changes in lung tissue before the patient notices them, according to EPFL.

Artificial intelligence (AI) has transformed industries around the world, and its potential to radically alter the field of healthcare is one of the most discussed topics in healthcare environments. With this in mind, Dr. Mary-Anne Hartley concludes, “COVID has sensitized people to the vulnerability of public health, and its enormous complexity. The need to build large scale AI research efforts to understand and react to rapidly emerging data has never been more obvious. Let’s hope the momentum continues beyond the pandemic and can be used to enable equitable access to health care.”