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.
Professor Martin Jaggi, a world-leading hub of AI specialists, said, “We’ve named the new deep learning algorithms DeepChest – using lung ultrasound images – and DeepBreath – using breath sounds from a digital stethoscope. This AI is helping us better to understand complex patterns in these fundamental clinical exams. So far, results are auspicious.”
CHUV, Lausanne’s University Hospital, is leading the clinical part of the DeepChest project, collecting thousands of lung ultrasound images from patients with Covid-19 compatible symptoms admitted to the Emergency Department. As principal investigator, Dr. Noémie Boillat-Blanco explains that the project started in 2019, 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.
Dr. Noémie Boillat-Blanco said, “Many of the patients who agreed to take part in our study were scared and very ill, 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 integrate new scientific knowledge into everyday medical practice rapidly.”
Professor Alain Gervaix, M.D., Chairman, Department of Woman, Child and Adolescent, has been collecting breath sounds since 2017 to build an intelligent digital stethoscope, the “Pneumoscope.” The recordings have now been used to develop the DeepBreath algorithm at EPFL.
Professor Gervaix said, “Pneumoscope with the DeepBreath algorithm can be compared to applications which can identify music based on a short sample played. The idea came from my daughter when I explained to her that auscultation allows me to hear sounds which help me identify asthma, bronchitis, or pneumonia.”
Dr. Hartley said, “There is still much work to do. We are continuing to refine and validate the algorithms and make the complex black box logic more interpretable to clinicians. We want to make robust, trustworthy tools that extend beyond this pandemic.”
“Work is also underway to develop an application that allows these complex deep learning algorithms to work on mobile phones, even in the most remote regions.”
“None of this work would have been possible without the incredible students and researchers from all over the world who have donated their time and expertise during a tumultuous period.”
Scientists are moving forward to gather more data. COVID or not, pneumonia, which kills more than one million children every year, remains one of the leading causes of under-fives’ death. It’s also one of the significant drivers of antibiotic resistance, affecting mostly low-income countries and communities.
Hartley said, “we want to collect data from under-represented communities so that our tools can be accurate even in low settings. Our algorithm is, for instance, specifically designed to tolerate errors in image or sound collection and inconsistent quality, which are more likely in those types of settings.”
They are already working on extending these models to distinguish between viral and bacterial pneumonia with the hope of drastically reducing antibiotic use.
Hartley concluded, “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.”