Sofia Galici
Blood pressure monitoring in a non-invasive way using Regression techniques.
Rel. Monica Visintin, Guido Pagana. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Biomedica, 2022
|
PDF (Tesi_di_laurea)
- Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (7MB) | Preview |
Abstract: |
Hypertension is one of the main risk factors for cardiovascular diseases (CVDs), leading cause of death in all over the world. The continuous blood pressure (BP) monitoring can offer a valid tool for patient care, and using it together with other parameters, such as heart rate, breath frequency, physical activity, etc, could strongly improve prevention of CVDs. Nowadays, invasive methods are the only reliable methods for BP continuous monitoring, despite they may cause several damage and discomfort to the patient. Instead non-invasive techniques are able to return BP values every few minutes, thus today they are not considered as optimal methods to continuously monitor BP trend. In this thesis work, the cuff-less estimation of continuous BP through the pulse transit time (PTT) and the heart rate (HR) using regression techniques is investigated. This method achieves the non-invasive estimation of the BP with an acceptable low error, according to the AAMI/ISO/ESH guidelines and taking into account the accuracy of the control device, which returns the reference BP values. Several novelties are introduced in this work. First of all, the use of electrocardiographic (ECG) and photopletismographic (PPG) signals acquired from healthy subjects with wearable devices: the SHIMMER (Sensing Health with Intelligence, Modularity, Mobility and Experimental Reusability ). In literature, similar methods have been implemented but they exploited physiological signals extracted mostly from online databases (e.g. MIMIC database). Another novelty is represented by the implementation of preprocessing of the ECG and PPG signals, and by the research and processing of the features related to them in order to continuously monitor BP in a non-invasive way, exploiting linear regression techniques. In fact, recent studies have been demonstrated that HR and PTT can be linearly combined to obtain BP values. So, the manipulation of these two features is the key point to non-invasively estimate reliable BP values. Definitely, the work described here aims to give an input to the research of a method which allows the continuously monitoring of the BP in a non-invasive way that is equally dependable with respect to the current methods and that is easy for the patient to carry out. The comfort in use results in measuring the BP at different times of the day without causing discomfort to the patient, and wherever he/she is without necessarily being in a clinical setting. Therefore, the proposed method is also intended for the integration of this type of algorithms on wearable devices, in particular on those developed for the European SINTEC project. |
---|---|
Relators: | Monica Visintin, Guido Pagana |
Academic year: | 2021/22 |
Publication type: | Electronic |
Number of Pages: | 102 |
Subjects: | |
Corso di laurea: | Corso di laurea magistrale in Ingegneria Biomedica |
Classe di laurea: | New organization > Master science > LM-21 - BIOMEDICAL ENGINEERING |
Aziende collaboratrici: | FONDAZIONE LINKS-LEADING INNOVATION & KNOWLEDGE |
URI: | http://webthesis.biblio.polito.it/id/eprint/22185 |
Modify record (reserved for operators) |