Wanyana, Tezira and Nzomo, Mbithe and Price, C Sue and Moodley, Deshendran (2022) Combining machine learning and Bayesian networks for ECG interpretation and explanation, Proceedings of the 8th International Conference on Information and Communication Technologies for Ageing Well and e-Health (ICT4AWE), 23 - 25 April 2022, Online Digital Conference, 81-92, SciTePress.
![[thumbnail of Combining Machine Learning and Bayesian Networks for ECG Interpretation and Explanation.pdf]](https://pubs.cs.uct.ac.za/style/images/fileicons/text.png) |
Text
Combining Machine Learning and Bayesian Networks for ECG Interpretation and Explanation.pdf - Published Version Download (770kB) |
Abstract
We explore how machine learning (ML) and Bayesian networks (BNs) can be combined in an 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.
| Item Type: | Conference paper |
|---|---|
| Uncontrolled Keywords: | Agent Architecture, Machine Learning, Bayesian Networks, ECG, Atrial Fibrillation, Wearable Devices |
| Subjects: | Computing methodologies > Artificial intelligence > Distributed artificial intelligence > Intelligent agents |
| Alternate Locations: | https://www.scitepress.org/Link.aspx?doi=10.5220/0011046100003188, https://www.cair.org.za/group/1/research-publications, https://www.researchgate.net/publication/360228758_Combining_Machine_Learning_and_Bayesian_Networks_for_ECG_Interpretation_and_Explanation |
| Date Deposited: | 07 Jun 2022 09:56 |
| Last Modified: | 07 Jun 2022 09:56 |
| URI: | https://pubs.cs.uct.ac.za/id/eprint/1527 |
Actions (login required)
 |
View Item |