Researchers are developing a biocompatible implantable AI platform that classifies in real-time, the health and pathological patterns in biological signals.
Artificial Intelligence (AI) led technologies will change the field of medicine and healthcare. Machine learning models can identify diseases at a very early stage from patient data such as ECG, EEG or X-ray images. However, implanting AI-led technologies inside a human body is still a major challenge.
Researchers from TU Dresden are developing a biocompatible implantable AI platform that classifies in real time healthy and pathological patterns in biological signals such as heartbeats without medical supervision.
The research team was led by Prof. Karl Leo, Dr. Hans Kleemann and Matteo Cucchi. They developed a biocompatible AI chip for real-time classification of healthy and diseased bio-signals using polymer-based fiber networks that structurally resemble the human brain and enable the neuromorphic AI principle of reservoir computing. The nonlinearity of these networks amplify even the smallest signal changes such as heartbeats.
In trials, the AI was able to differentiate between healthy heartbeats from three common arrhythmias with an 88% accuracy rate. The polymer network consumed less energy than a pacemaker.
“The vision of combining modern electronics with biology has come a long way in recent years with the development of so-called organic mixed conductors,” explains Matteo Cucchi, PhD student and first author of the paper. “So far, however, successes have been limited to simple electronic components such as individual synapses or sensors. Solving complex tasks has not been possible so far. In our research, we have now taken a crucial step toward realizing this vision. By harnessing the power of neuromorphic computing, such as reservoir computing used here, we have succeeded in not only solving complex classification tasks in real time but we will also potentially be able to do this within the human body. This approach will make it possible to develop further intelligent systems in the future that can help save human lives.”
The research appeared in the journal Science Advances.