A hybrid machine learning approach to localizing the origin of ventricular tachycardia using 12-lead electrocardiograms. (November 2020)

• Record Type: Journal Article
• Authors: Missel, Ryan; Gyawali, Prashnna K.; Murkute, Jaideep Vitthal; Li, Zhiyuan; Zhou, Shijie; AbdelWahab, Amir; Davis, Jason; Warren, James; Sapp, John L.; Wang, Linwei
• Is Part Of: Computers in biology and medicine. Volume 126(2020)
• Publication Date: 2020-11
• Subjects: Ventricular tachycardia -- Electrocardiogram -- Disentangled representation learning -- Active learning -- Pace-mapping; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2020.104013
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Background: Machine learning models may help localize the site of origin of ventricular tachycardia (VT) using 12-lead electrocardiograms. However, population-based models suffer from inter-subject anatomical variations within ECG data, while patient-specific models face the open challenge of what pacing data to collect for training. Methods: This study presents and validates the first hybrid model that combines population and patient-specific machine learning for rapid "computer-guided pace-mapping". A population-based deep learning model was first trained offline to disentangle inter-subject variations and regionalize the site of VT origin. Given a new patient with a target VT, an on-line patient-specific model -- after being initialized by the population-based prediction -- was then built in real time by actively suggesting where to pace next and improving the prediction with each added pacing data, progressively guiding pace-mapping towards the site of VT origin. Results: The population model was trained on pace-mapping data from 38 patients and the patient-specific model was subsequently tuned on one patient. The resulting hybrid model was tested on a separate cohort of eight patients in localizing 1) 193 LV endocardial pacing sites, and 2) nine VTs with clinically determined exit sites. The hybrid model achieved a localization error of 5.3 ± 2.6 mm using 5.4 ± 2.5 pacing sites in localizing LV pacing sites, achieving a significantly higher accuracy with a significantly smaller amount of training sites in comparison to models without active guidance. Conclusion: The presented hybrid model has the potential to assist rapid pace-mapping of interventional targets in VT. Highlights: A novel hybrid model combining the advantage of population-based deep learning and patient-specific model. A novel population model that disentangles inter-subject variations when localizing the sites of origins. A novel patient-specific model that actively suggests where to pace in order to minimize the number of pacing training data.