Prediction of ABP and ECG signal from PPG signal using deep learning

Sinha, Sarthak (2023) Prediction of ABP and ECG signal from PPG signal using deep learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (6MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Heart disease risk factors have long and most commonly been associated with arterial blood pressure (ABP). Arterial blood pressure measurement is one of the most helpful metrics for the early diagnosis, prevention, and treatment of cardiovascular diseases. Inconvenient and painful for users, cuff-based systems for measuring blood pressure remain the norm today. The monitoring of the electrocardiogram (ECG) has a similar related problem. Electrodes are affixed to the body as part of the ECG measurement process, which irritates the skin and restricts the patient's movement while they are being continuously monitored. Due to these difficulties, it is required to provide a dependable and practical way to track these essential physiological markers.

This paper investigates the previous research carried out in this field; however, the studies have not yet developed a complete heart monitoring system using a Photoplethysmography signal as the only input. This study aims to develop an effective deep-learning model to predict both ABP and ECG signals from PPG signals using minimal patient data because previous research has only been done to predict one physiological parameter (ABP or ECG). Additionally, the estimation accuracy for three different models would be evaluated based on mean absolute error (MAE) and root mean square error (RMSE).

Item Type:	Thesis (Masters)
Supervisors:	Name Email Menghwar, Teerath Kumar UNSPECIFIED
Uncontrolled Keywords:	Arterial Blood pressure (ABP); Photoplethysmography (PPG); Electrocardiography (ECG); Convolutional Neural Network (CNN); Long Short-Term Memory (LSTM); multi-output regression; Transformers; signal processing
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RC Internal medicine Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	06 Jan 2025 17:42
Last Modified:	06 Jan 2025 17:42
URI:	https://norma.ncirl.ie/id/eprint/7275

Actions (login required)

View Item