SDG 3: Good Health and Well-being
2. Project Details
Company or Institution
Ghent University – imec
General description of the AI solution
Sleep apnea is one of the most common sleep disorders. It is characterized by pauses in the breathing, or shallow breathing during sleep. This can cause several adverse health effects, such as depression, high blood pressure, heart failure, fatigue, etc. Quite often, people are unaware of their condition. In Europe, it is estimated that 175 million people suffer from sleep apnea, whereas 80% of them are undiagnosed. Diagnosis is typically done in a sleep clinic using a polysomnography (PSG). A wide range of sensors are attached to the body of the patient, and multiple physiological signals are measured over time. These signals are analyzed by a trained sleep technician, and a diagnosis is made. An important drawback is that this approach is expensive and uncomfortable for the patient, because of the obtrusive setup and the fact that he/she has to sleep in an unfamiliar environment. To resolve this problem, the team of Prof. Deschrijver contributed to the development a home monitoring solution that makes use of a wearable device (imec Robin) that was developed in the Autonomous Therapeutics group of imec. It is worn around the neck, and can be attached to the chest via adhesive stickers. A key advantage of the home monitoring solution, is that it is more cost-efficient and less obtrusive for the patient than the standard PSG-based approach.
Ghent University – imec
Excellence and Scientific Quality: Please detail the improvements made by the nominee or the nominees’ team or yourself if your applying for the award, and why they have been a success.
The new AI solution combines imec hardware innovations and state-of-the-art deep learning algorithms. The device measures bio-impedance of the chest, which provides a more accurate estimation of respiratory flow and effort, as compared to existing solutions that work with indirect measurements. This bio-impedance data is filtered and analyzed using advanced deep-learning algorithms (such as LSTM’s), that are able to learn features and capture temporal dependencies in the raw data. This makes it possible to achieve a more reliable detection of sleep apnea events. The newly developed solution was filed for patenting, and the results were published in the IEEE Journal of Biomedical and Health Informatics (SCI 5.223), which is one of the leading journals in the field. The deep-learning algorithm for apnea detection has become one of major reference works in the domain. The results of this work have also been covered by an article in IEEE Spectrum, which is a flagship IEEE magazine that reports on new and emerging high-impact technologies. It was also covered by a Belgian popular science Magazine EOS, in the October 2020 edition. Furthermore, the research was also featured in the top 3 research pitches at the Innovation for Health conference.
Scaling of impact to SDGs: Please detail how many citizens/communities and/or researchers/businesses this has had or can have a positive impact on, including particular groups where applicable and to what extent.
The solutions that were developed are patented and valorized through the imec spin-off Onera Medical. They raised $9.3 million USD in Series A funding, and are now using the algorithms for further development of home-based sleep analysis. Onera has received a CE Certificate of Conformity for its patch-based Sleep Test System (STS) that brings the gold-standard quality of a hospital diagnostic system directly to a user’s home. The CE mark allows the groundbreaking device to be sold in the European market. As well as securing a CE mark in the EU, Onera is currently awaiting 510(k) clearance from the US Food and Drug Administration for its PSG system. During the upcoming months, they will focus on strategic partnerships with exclusive European and American partners to evaluate the potential of the product and patched-based technology. The company was recognized by CB Insights for its achievements in developing clinical-grade home monitoring for sleep management. More recently, in July 2021, the company closed €10.5 million in Series B funding. The round was led by Innovation Industries in close collaboration with Invest-NL and with existing investors imec.xpand, Jazz Pharmaceuticals, BOM and 15th Rock.
Scaling of AI solution: Please detail what proof of concept or implementations can you show now in terms of its efficacy and how the solution can be scaled to provide a global impact ad how realistic that scaling is.
Since the uprise of the COVID-19 pandemic, technology for real-time monitoring of respiratory-related illnesses has gained a lot of attention worldwide. The research team of Prof. Deschrijver is currently investigating the potential to generalize and scale up the artificial intelligence solutions towards the analysis of other respiratory-related illnesses (such as chronic obstructive pulmonary disease, asthma, sleep-related disorders,…). Since millions of people worldwide are suffering from these conditions, there is a strong need for innovative solutions. The aim of the ongoing research activities is to analyze unique data sets and to develop next-generation wearables that can serve as an early warning system for changes in the patient’s condition. Such new monitoring technology and better treatments are of paramount importance, and can have a very sustainable economic and positive societal impact. Currently, intense collaborations are already in place between different research units and hospitals, and future exchanges of researchers with leading international universities are planned.
Ethical aspect: Please detail the way the solution addresses any of the main ethical aspects, including trustworthiness, bias, gender issues, etc.
All necessary clearances in terms of ethical issues and data protection are obtained. Adequate procedures are in place for the data collection and privacy issues are properly handled. The technology is applicable at the global international scale, and it is fully compliant with all applicable laws and regulations. Furthermore, it is non-discriminative and inclusive to ensure good health and well-being of all people, independent of their nationality, race, gender, religious background, sexual orientation,…