The development of non-invasive easily available blood pressure estimation methods using electrocardiogram - ECG and/or photoplethysmogram - PPG signals has gained increasing attention. However, there is a lack of consistency in the evaluation of these methods due to variations in the size and availability of data in published datasets. Our research involves retrieving, cleaning, and storing a portion of the MIMIC-III database for utilization in model training and testing. This paper outlines our methodology for processing the MIMIC-III database, along with the challenges encountered during the process.
MIMIC-III · electrocardiogram · photoplethysmogram · blood pressure estimation · artificial neural network · deep learning