A modeling and machine learning approach to ECG feature engineering for the detection of ischemia using pseudo-ECG
- Submitting institution
-
University College London
- Unit of assessment
- 12 - Engineering
- Output identifier
- 10304
- Type
- D - Journal article
- DOI
-
10.1371/journal.pone.0220294
- Title of journal
- PLoS One
- Article number
- ARTN e0220294
- First page
- e0220294
- Volume
- 14
- Issue
- 8
- ISSN
- 1932-6203
- Open access status
- Compliant
- Month of publication
- August
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
https://doi.org/10.1371/journal.pone.0220294.s001
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
4
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper demonstrates how to combine/exploit two very different modelling paradigms -mechanistic models and machine learning- to tackle the problem of early detection of coronary heart disease. Amongst a number of significant contributions, this paper shows that the additive effect of inter-patient variability precludes the detection and classification of ischemic events using simple thresholds or visual inspection, with significant clinical implications. This paper was highlighted by the European Society of Cardiology as something that can "revolutionize cardiology research and care", was finalist in the "STEM for Britain" competition 2018 and provided pilot data for a newly-awarded EPSRC grant (EP/T017791/1)
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
