tinyCare: A tinyML-based Low-Cost Continuous Blood Pressure Estimation on the Extreme Edge

We propose a solution that deploys Machine Learning (ML) techniques on resource-constrained edge devices (tinyMl)for the healthcare domain. In particular, we construct a complete end-to-end prototyped system that conducts ML inference with various ML techniques on microcontroller unit (MCU)-powered edge devices to predict blood-pressure-related vital metrics such as systolic (SBP), diastolic (DBP), and mean arterial (MAP) blood pressures using electrocardiogram (ECG) and photoplethysmogram (PPG) sensors. The proposed solution is trained and tested using over 500 hours of 12, 000 real intensive care unit data instances. Despite running on an extremely limited computation, power and memory budget, the proposed solution achieves comparable results to server-based state-of-the-art solutions. Furthermore, it meets the British Hypertension Society (BHS) standard for grade B (C in extremely-constrained devices). This is achieved by careful investigation of the correlation between a wide-set of ECG and PPG features and BP. Afterwards, we compress the ML inference models by only incorporating the minimal features that meet i) the edge constraints from one side, and ii) the standard's acceptable accuracy from the other side. Unlike existing solutions, the inference is entirely conducted on MCU-based edge devices without depending on any cloud-based infrastructure. Hence, the proposed solution improves robustness, accessibility, reliability, security, as well as data privacy.