Ryan Missel1, Prashnna K Gyawali1, Jaideep Vitthal Murkute1, Zhiyuan Li1, Shijie Zhou2, Amir AbdelWahab3, Jason Davis3, James Warren4, John L Sapp5, Linwei Wang6. 1. College of Computing and Information Sciences, Rochester Institute of Technology, Rochester, NY, USA. 2. Department of Medicine, QEII Health Sciences Centre, Halifax, NS, Canada; Alliance for Cardiovascular Diagnostic and Treatment Innovation, Institute of Computational Medicine, Johns Hopkins University, Baltimore, MD, USA; Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA. 3. Department of Medicine, QEII Health Sciences Centre, Halifax, NS, Canada. 4. Department of Physiology and Biophysics, Dalhousie University, Halifax, NS, Canada. 5. Department of Medicine, QEII Health Sciences Centre, Halifax, NS, Canada; Department of Physiology and Biophysics, Dalhousie University, Halifax, NS, Canada. 6. College of Computing and Information Sciences, Rochester Institute of Technology, Rochester, NY, USA. Electronic address: linwei.wang@rit.edu.
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.
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.
Authors: John L Sapp; Meir Bar-Tal; Adam J Howes; Jonathan E Toma; Ahmed El-Damaty; James W Warren; Paul J MacInnis; Shijie Zhou; B Milan Horáček Journal: JACC Clin Electrophysiol Date: 2017-07-17
Authors: Shijie Zhou; John L Sapp; B Milan Horáček; James W Warren; Paul J MacInnis; Jason Davis; Ihab Elsokkari; Rajin Choudhury; Ratika Parkash; Chris Gray; Martin Gardner; Ciorsti J MacIntyre; Amir AbdelWahab Journal: Heart Rhythm Date: 2019-10-25 Impact factor: 6.343
Authors: Georgios Petmezas; Leandros Stefanopoulos; Vassilis Kilintzis; Andreas Tzavelis; John A Rogers; Aggelos K Katsaggelos; Nicos Maglaveras Journal: JMIR Med Inform Date: 2022-08-15