Classification Algorithm for Early Detection of Atrial Fibrillation

Classification Algorithm for Early Detection of Atrial Fibrillation: The Development of a Supervised Learning Method Using Photoplethysmography Signals for an ARM Processor

van Es, Tim (TU Delft Electrical Engineering, Mathematics and Computer Science)
Helfferich, Florens (TU Delft Electrical Engineering, Mathematics and Computer Science)

Abdi, Bahareh (mentor)
Hendriks, R.C. (mentor)
Makinwa, K.A.A. (graduation committee)
Vollebregt, S. (graduation committee)

Delft University of Technology

2021-06-29

Atrial fibrillation (AF) is the most common type of cardiac arrhythmia occurring in around 0.5% of the world population. AF is characterized by the rapid and irregular beating of the atrial chambers of the heart, which can cause lead to strokes and other heart-failures. To prevent these consequences the early detection of AF is paramount. Using photoplethysmography (PPG) heart activity can be measured from which the inter-beat-interval (IBI), the time between heart beats, can be estimated. Using data collected by a PPG sensor the aim is to classify the heart activity as either AF or Normal Sinus Rhythm in real time using machine learning and collect the outcomes for further analysis by medical professionals. For this a classification method is suggested which is able to be implemented on an ARM based processor. Using a Support Vector Machine and 10 features derived from the IBI's and the PPG signal this algorithm achieves the following accuracy metrics: balanced accuracy = 0.853, sensitivity = 0.850, specificity = 0.856 and Matthews Correlation Coefficient (MCC) = 0.643. Compared to similar studies these results are substandard and should be improved.

Atrial Fibrillation
Machine Learning
Binary Classification
Photoplethysmography
Support Vector Machine
Supervised Learning

http://resolver.tudelft.nl/uuid:75534c7b-8fff-4337-8adf-bcd063c74889

Student theses

bachelor thesis

© 2021 Tim van Es, Florens Helfferich