Authors:
Tezira Wanyana
1
;
2
;
Mbithe Nzomo
1
;
2
;
C. Sue Price
1
;
3
and
Deshendran Moodley
1
;
2
Affiliations:
1
Centre for Artificial Intelligence Research (CAIR), South Africa
;
2
University of Cape Town (UCT), Cape Town, South Africa
;
3
University of KwaZulu-Natal (UKZN), Durban, South Africa
Keyword(s):
Agent Architecture, Machine Learning, Bayesian Networks, ECG, Atrial Fibrillation, Wearable Devices.
Abstract:
We explore how machine learning (ML) and Bayesian networks (BNs) can be combined in a personal health agent (PHA) for the detection and interpretation of electrocardiogram (ECG) characteristics. We propose a PHA that uses ECG data from wearables to monitor heart activity, and interprets and explains the observed readings. We focus on atrial fibrillation (AF), the commonest type of arrhythmia. The absence of a P-wave in an ECG is the hallmark indication of AF. Four ML models are trained to classify an ECG signal based on the presence or absence of the P-wave: multilayer perceptron (MLP), logistic regression, support vector machine, and random forest. The MLP is the best performing model with an accuracy of 89.61% and an F1 score of 88.68%. A BN representing AF risk factors is developed based on expert knowledge from the literature and evaluated using Pitchforth and Mengersen’s validation framework. The P-wave presence or absence as determined by the ML model is input into the BN. The
PHA is evaluated using sample use cases to illustrate how the BN can explain the occurrence of AF using diagnostic reasoning. This gives the most likely AF risk factors for the individual.
(More)