This work presents a Field-Programmable Gate Array (FPGA) implementation of a U-Net-based model for heart sound segmentation, building on previous hardware optimization efforts. By converting model parameters to Read-Only Memories instead of Advanced eXtensible Interface (AXI) ports, Block Random Access Memory consumption decreased significantly, from 99% to 58%. Additionally, latency was reduced from 29.27 to 17.66 ms as estimated during High-Level Synthesis (HLS) cosimulation. The U-Net block was integrated into a block design, connected to the Zynq Processing System, facilitating model evaluation on the PYNQ-Z2 board. Model accuracy reached 91.14%, close to HLS C simulation results and high-level Python description. FPGA measured latency was 17.77±0.01 ms, achieving real-time performance, with power consumption estimated at 134±14 mW. Energy per inference was calculated at 2.38±0.07 mJ. A power reduction study showed a 22 % decrease in minimum power consumption compared to default settings, but no significant reduction in energy consumption was observed. This study offers insights for future optimizations, highlighting the applicability of FPGA-based heart sound segmentation in real-world scenarios, and setting the specifications for a potential hand-held device based on this design.

Cardiovascular Diseases (CVDs) stand as the leading cause of mortality worldwide. Detecting subtle heart sounds alterations in the early stages of CVDs can be crucial for an initial effective treatment. Accordingly, the analysis of Phonocardiograms (PCGs) through segmentation could be helpful for CVDs screening. A well-established algorithm for this task is based on a Convolutional Neural Network (CNN) with an encoding-decoding topology. Prior to the CNN processing., a computationally intensive input pre-processing., based on envelopes extraction, is needed. Thus., achieving real-time performance can be challenging. The main goal of this study is the hardware design., implementation, and evaluation of four PCG pre-processing circuits to be employed together in the design of a low-power point-of-care device for real-time Artificial Intelligence (AI)-based PCG segmentation. Results have shown that the approximations introduced by the fixed-point format and this innovative architecture have a negligible impact on the AI segmentation quality. Finally, the pre-processing chain is real-time compliant., achieving a maximum latency of 257 ms for an available processing window of 1.28 s., while dissipating only 61 mW of power.

Cardiovascular diseases (CVDs) are currently one of the leading causes of death worldwide. Being able to detect their symptoms at early stages, even the most hidden ones, is crucial to shorten the diagnosis time and facilitate an early treatment. Currently, the use of continuous tracking systems, mainly based on wearable devices that analyze data using artificial intelligence (AI) algorithms, is being explored to automatically identify, in real time, CVDs symptoms. This could be especially relevant in lowincome countries where there is a shortage of specialized doctors. Therefore, this work focuses on analyzing the real-time execution of the state-of-the-art convolutional neural network (CNN) for heart sound segmentation (HSS) on platforms such as traditional CPU/GPU and the Fraunhofer IMS © AIRISC Core Complex (a RISC-V processor developed for AI). Results revealed that, while all implementations exploiting the CPU/GPU platform proved to be useful in real-time diagnosis from a fixed location, the AIRISC demonstrated its goodness, as a system on a chip (SoC) for a real-time wearable application, when executing a quantized version of the CNN.

Noncommunicable Diseases (NCDs), like Cardiovascular Diseases (CVD) or Diabetes Mellitus (DM) are defined as chronic conditions caused by the combination of genetic, physiological, behavioral, and environmental factors that can affect an individual's health, being a major issue for the public health system globally. Sometimes, these conditions share some of their risk factors, as occurs between CVD and DM. Current clinically validated risk calculators have been developed using different regression approaches, targeting different populations and having significant differences between their outputs and the risk factors they use to compute the risk. In this work, we present a methodology for the design of risk calculator based on Machine Learning (ML), combining the knowledge of different clinically validated cardiovascular risk calculators using transfer learning for more personalized NCD risk estimation. Besides, a hardware profiling in terms of latency and model size is performed, targeting its real-time implementation in an embedded system. Results suggest that re-training an already developed ML model with a different dataset can improve its generalization capability, being a suitable way to avoid overfitting. Moreover, profiling results shown that this type of ML-based algorithms are suitable for embedded systems implementations., having model sizes lower than 1 KB and average inference times lower than$75\ \mu\mathrm{s}$.

The increasing prevalence of chronic non-communicable diseases makes it a priority to develop tools for enhancing their management. On this matter, Artificial Intelligence algorithms have proven to be successful in early diagnosis, prediction and analysis in the medical field. Nonetheless, two main issues arise when dealing with medical data: lack of high-fidelity datasets and maintenance of patient's privacy. To face these problems, different techniques of synthetic data generation have emerged as a possible solution. In this work, a framework based on synthetic data generation algorithms was developed. Eight medical datasets containing tabular data were used to test this framework. Three different statistical metrics were used to analyze the preservation of synthetic data integrity and six different synthetic data generation sizes were tested. Besides, the generated synthetic datasets were used to train four different supervised Machine Learning classifiers alone, and also combined with the real data. F1-score was used to evaluate classification performance. The main goal of this work is to assess the feasibility of the use of synthetic data generation in medical data in two ways: preservation of data integrity and maintenance of classification performance.