“Useful theory should have an application in real life” – Jiawei Yang’s device uses AI to detect worsening heart failure

Jiawei Yang, Senior Researcher at the University's MSCA-co-funded SYS-LIFE programme is working to create a meaningful application for his earlier work in computer science. During his PhD, Yang worked on developing algorithms and AI that detect anomalies in data. Now he is using his knowledge to develop a wearable device that uses AI anomaly detection to detect changes in the user's heart signals.

The practical application of AI is important to Yang:

"My past research is about algorithm design and AI model development, which is purely about computer science theory. Useful theory should have an application in real life, and heart failure is a very important application that affects a lot of people globally."

Early detection of worsening heart failure saves lives and money

Yang's research aims to help heart failure patients by tracking their heart health in case of worsening heart failure. When heart failure worsens, it immediately damages the life of the person affected by it, and causes significant burden to public healthcare. To Yang, this makes heart failure detection an important topic to study.

The appliance Yang is working on is a patch that will be attached to the wearer's chest, where it will gather data about the heart. The device will capture both electrocardiography and seismocardiography signals during periods of rest and exercise. This will allow continuous and precise tracking of the heart.

"It's health monitoring. If something weird happens in the heart, the user gets told that they should visit the hospital at an early stage, instead of the heart failure becoming serious. It's kind of an early warning."

Currently there is no non-invasive way to continuously track the heart health of heart failure patients, which is why a non-invasive, low-maintenance, and low-risk heart tracking device is needed. According to Yang, creating such a device would have been practically impossible just a few years ago.

Advanced software and hardware, which Yang's project relies on, have both progressed a lot in the recent years. Deep-learning AI has taken leaps in the past years and already has very powerful learning ability. In addition, there are very accurate sensors available for the project hardware. Yang thinks the project is well-timed, as well as well-supported:

"SYS-LIFE is a very big programme, so we have good support from the programme, as well as the Turku University Hospital. We have just the right timing and resources to try to develop something like this."

Integrating AI into healthcare

Artificial intelligence is an important part of Yang's project, and the AI model for the appliance is under development. A recent breakthrough in Yang's research has to do with data scaling. Yang's research group has developed a novel scaling method that can shorten very long signals for efficient processing by AI models. This is essential for the device, as the AI models need large amounts of data to be fully trained.

Yang's experience in computer science and AI model development has left him with a deep understanding of AI - what it can and cannot do. He emphasises the importance of human contribution, stating that AI can never, for instance, be responsible for clinical decision making.

"AI has great potential to significantly improve healthcare services, but it is important to understand that there is still a long way to go before it can be fully integrated into clinical practice."

Yang's research is ongoing, and the project progresses steadily:

"The hardware is ready, and on the software side we have developed a processing pipeline that includes several algorithms. Some of them are already working well, while others are still being improved. The next step is to develop a lightweight model that can run directly on wearable devices."

SYS-LIFE, Systemic Approaches to Improve Cardiometabolic and Brain Health during Lifespan is Marie Skłodowska-Curie postdoctoral programme cofunded by University of Turku and European union (project 101126611) in 2023-2028. SYS-LIFE supports excellent international early and mid-career stage researchers by providing 22 three-year bottom-up project grants in cardiometabolic and brain research, complemented with training and possibility for secondments outside academia. SYS-LIFE partners include Turku University Hospital, Business Turku, Siemens Healthineers and Ghent University.

Text and photo: Iida Taskila