College of Computing and Information Sciences, Rochester Institute of Technology, Rochester, NY, USA.
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.
Comput Biol Med. 2020 Nov;126:104013. doi: 10.1016/j.compbiomed.2020.104013. Epub 2020 Sep 23.
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.
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.
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.
The presented hybrid model has the potential to assist rapid pace-mapping of interventional targets in VT.
机器学习模型可以帮助使用 12 导联心电图定位室性心动过速 (VT) 的起源部位。然而，基于人群的模型在 ECG 数据中存在个体间解剖差异，而患者特异性模型则面临收集何种起搏数据进行训练的开放性挑战。
本研究提出并验证了第一个混合模型，该模型结合了人群和患者特异性机器学习，用于快速“计算机引导起搏映射”。首先离线训练基于人群的深度学习模型，以分解个体间的差异并对 VT 起源部位进行分区。对于有目标 VT 的新患者，在线患者特异性模型（在基于人群的预测初始化后）然后实时构建，通过主动建议下一步起搏的位置，并通过每次添加起搏数据来改进预测，逐步引导起搏映射到 VT 起源部位。
人群模型在 38 名患者的起搏映射数据上进行训练，随后在一名患者上对患者特异性模型进行调整。由此产生的混合模型在另外 8 名患者的队列中进行了测试，以定位 1) 193 个 LV 心内膜起搏部位，和 2) 9 个临床确定的出口部位的 VT。该混合模型在定位 LV 起搏部位时，使用 5.4±2.5 个起搏部位，定位误差为 5.3±2.6mm，与无主动引导的模型相比，其准确性更高，所需的训练部位更少。
所提出的混合模型有可能协助快速进行 VT 的介入靶点起搏映射。
