Abstract:
High Blood pressure is considered as one of the main factors that affect human health. In addition,
it leads to many other complications, risks and other cardiovascular diseases in the human body.
Arterial Blood Pressure changes very frequently. Variability of Arterial Blood Pressure over a
certain period is related to the cardiovascular risk. Therefore, continuous measurements of blood
pressure is a significant input for diagnosis and treatments. There is an immense motivation
towards building a cuff-less blood pressure monitoring system which can determine the Systolic
Blood Pressure and Diastolic Blood Pressure with minimal settings. With the removal of cuff, the
system could be used for continuous measuring. Photoplethysmography is one of the low-cost
optical methods that could be used in measuring arterial blood pressure continuously and
noninvasively. Features of several different categories can be extracted from PPG signals including
width-based features, frequency domain features and features extracted from the second derivative
of the signal (Accelerated PPG). Existing methods primarily use one category of features or
another. A method to extract a combination of characteristics from multiple categories of PPG
signal is proposed under this research. Furthermore, it is been evaluated using a benchmark dataset
(MIMIC II) collected in a clinical setting as well as a dataset collected using a consumer-grade
device in a nonclinical setting. From the results of the method that is tested, 53 features achieved
Mean Absolute Errors of 4.8 mmHg & 2.5 mmHg for Systolic Blood Pressure value and Diastolic
Blood Pressure value respectively while reaching grade A for both the estimates under the standard
British Hypertension Society for the MIMIC II dataset. The same methodology applied to the
second dataset showed good agreement (MAE 4.1, 1.7 mmHg for SBP and DBP respectively) with
readings taken using a standard oscillometric device, which suggests the robustness of the
approach.
Citation:
Manamperi, B.M. (2020). Cuff-less arterial blood pressure estimation using machine learning techniques [Master's theses, University of Moratuwa]. Institutional Repository University of Moratuwa. http://dl.lib.uom.lk/handle/123/22272