The first ACM/IEEE TinyML Design Contest (TDC) held at the 41st International Conference on Computer-Aided Design (ICCAD) in 2022 is a challenging, multimonth, research and development competition. TDC’22 focuses on real-world medical problems that require the innovation and implementation of artificial intelligence/machine learning (AI/ML) algorithms on implantable devices. The challenge problem of TDC’22 is to develop a novel AI/ML-based real-time detection algorithm for life-threatening ventricular arrhythmia (VA) over low-power microcontrollers utilized in implantable cardioverter-defibrillators (ICDs). The dataset contains more than 38000 5-s intracardiac electrograms (IEGMs) segments over eight different types of rhythm from 90 subjects. The dedicated hardware platform is NUCLEO-L432KC manufactured by STMicroelectronics. TDC’22, which is open to multiperson teams world-wide, attracted more than 150 teams from over 50 organizations. This article first presents the medical problem, dataset, and evaluation procedure in detail. It further demonstrates and discusses the designs developed by the leading teams as well as representative results. This article concludes with the direction of improvement for the future TinyML design for health monitoring applications.

The organizers of the TinyML Design Contest describe the top machine-learning-based real-time detection algorithms for ventricular arrhythmia.

The application of Wireless Power Transmission (WPT) has attracted more and more attention, but the energy efficiency cannot be high due to the inevitable loss. Energy efficient WPT is increasingly demanded especially in implantable devices due to their wireless inefficiency nature. In addition, many implantable devices include digital circuits such as a Microcontroller Unit (MCU) in which the supply voltage may fluctuate severely with the driving clock of digital circuits switches between ground (Gnd) and supply voltage (Vdd), since the power transmitted wirelessly is limited, and the system may even cut off under wireless charging conditions. Therefore, the load regulation is also required in a WPT system. This paper presents a WPT system with load regulation and optimized antenna design for implantable devices, for which measurement results show that the maximum transmission efficiency can reach 79.3% and it can still necessitate a large dynamic load current range. When the load current is switched between 12 uA and 5 mA, the overshoot and undershoot of the output voltage are 150 mV and 80 mV, respectively. Finally, several state-of-the-art WPT applications in biomedical devices are introduced.