Ultra-low power AI for implantable medical devices
TTP in Cambridge has developed a low power AI system for implantable medical devices.
The AI framework developed by TTP is capable of classifying real-time ECG data and screening it for potential arrhythmias at a power budget that makes the system suitable for running with an implantable pacemaker.
Pattern recognition is a fundamental capability of AI. When used in closed-loop therapies such as implanted cardioverter defibrillators and neurostimulators, it can be more accurate classification of electrical or nerve activity in the body.
Conventional AI systems would quickly drain the limited battery power available in a medical implant. In addition, they typically rely on continuous internet connectivity, making them unacceptable as part of a system that is key to sustaining life.
The developers used an off-the-shelf microcontroller from Analog Devices with a dedicated low-power neural network accelerator to build a system that is able to classify real-time ECG data at the power budget available in an implantable pacemaker.
They developed new techniques for the way AI models for signal classification are trained in concert with changes in the design of the system hardware.
First, the AI model have to be trained to successfully classify ECG data at the reduced resolution of a low-power AI accelerator. The Quantisation Aware Training technique allows the AI model to understand as it is being trained how its performance will change with a reduction in resolution of the data. This helped maintain performance at the 8bit resolution of the low-power embedded AI accelerator.
In the body, the amplitude of ECG data is influenced by electrical contact, person-to-person variation and heart activity. To eliminate biases due to the amplitude of features, it is common to rescale the data before processing. But at the limited resolution of low-power edge devices, it isn’t always possible to scale the data digitally and still get the same classification performance.
For the arrythmia classification hardware, the analogue front-end was re-designed to use the full dynamic range, potentially even being able to dynamically change gain before the signal is digitised.
The final challenge in implementing low-power AI was one of timing. To reduce power consumption, edge devices are off most of the time, meaning that sampling and signal classification cannot run continuously. In addition, pre-labelled training datasets are often time-aligned, so that the trained AI model only expects to see data in the middle of the sampling window.
If sampling and data processing are started at the wrong time, this can either lead to data being discarded (and battery power being wasted) or result in worse classification performance. In a low-power system, it is therefore desirable to pre-process the data still in the analogue domain to enable efficient timing of sampling and inference.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
