Main Article Content
Copyright (c) 2023 Proceedings on Automation in Medical Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
Interconnected medical devices enable new therapies and automate existing ones. Following this approach, we can identify two challenges: Interoperability and Verifiability. Due to various manufacturers and interfaces, interoperability is often not directly possible but needs to be enabled with the help of auxiliary hardware. Addressing the demand for safety of the interconnected medical application, verifiability is essential and depends, among other aspects, on the complexity of the created overall system, which is increasing with the dimension of interconnected devices. However, many of the state-of-the-art medical hardware platforms neglect this need for verifiability. They often rely on a centralized unit, running a Linux operating system containing e.g., closed source libraries. We propose the ASMO hardware platform, which provides various interfaces to enable interoperability. Additionally, in an architecture using the proposed hardware, the workload is distributed such that the complexity of each unit can be reduced, which is beneficial for the verification of the used algorithms, without reducing the overall processing capabilities. Each ASMO board is based on a STM32 F767ZIT6 microcontroller, which offers enough computational power to perform embedded machine learning. By running a low-level real-time operating system, the verifiability can be further preserved, and abstraction layers are available to easily upgrade the interconnected medical setup if a device needs to be introduced. Thanks to the modular design of the ASMO board and the publicly available layout, it can even be adapted to meet new requirements like custom protocols or interfaces. The presented hardware platform can be used as a ground pillar for the creation of a cyber medical system.