Prediction of premature ventricular complex origins using artificial intelligence–enabled algorithms

Tomofumi Nakamura, MD, PhD; Yasutoshi Nagata, MD; Giichi Nitta, MD; Shinichiro Okata, MD, PhD; Masashi Nagase, MD; Kentaro Mitsui, MD; Keita Watanabe, MD; Ryoichi Miyazaki, MD; Masakazu Kaneko, MD; Sho Nagamine, MD, PhD; Nobuhiro Hara, MD; Tetsumin Lee, MD, PhD; Toshihiro Nozato, MD, PhD; Takashi Ashikaga, MD, PhD; Masahiko Goya, MD, PhD; Tetsuo Sasano, MD, PhD

Cardiovascular Digital Health Journal (Feb 2021)

Prediction of premature ventricular complex origins using artificial intelligence–enabled algorithms

Tomofumi Nakamura, MD, PhD,
Yasutoshi Nagata, MD,
Giichi Nitta, MD,
Shinichiro Okata, MD, PhD,
Masashi Nagase, MD,
Kentaro Mitsui, MD,
Keita Watanabe, MD,
Ryoichi Miyazaki, MD,
Masakazu Kaneko, MD,
Sho Nagamine, MD, PhD,
Nobuhiro Hara, MD,
Tetsumin Lee, MD, PhD,
Toshihiro Nozato, MD, PhD,
Takashi Ashikaga, MD, PhD,
Masahiko Goya, MD, PhD,
Tetsuo Sasano, MD, PhD

Affiliations

Tomofumi Nakamura, MD, PhD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan; Address reprint requests and correspondence: Dr Tomofumi Nakamura, Japanese Red Cross Musashino Hospital, 1-26-1, Kyonancho, Musashino City, Tokyo, Japan.
Yasutoshi Nagata, MD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Giichi Nitta, MD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Shinichiro Okata, MD, PhD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Masashi Nagase, MD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Kentaro Mitsui, MD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Keita Watanabe, MD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Ryoichi Miyazaki, MD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Masakazu Kaneko, MD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Sho Nagamine, MD, PhD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Nobuhiro Hara, MD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Tetsumin Lee, MD, PhD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Toshihiro Nozato, MD, PhD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Takashi Ashikaga, MD, PhD: Department of Cardiology, Japanese Red Cross Musashino Hospital, Tokyo, Japan
Masahiko Goya, MD, PhD: Department of Cardiovascular Medicine, Tokyo Medical and Dental University Hospital, Tokyo, Japan
Tetsuo Sasano, MD, PhD: Department of Cardiovascular Medicine, Tokyo Medical and Dental University Hospital, Tokyo, Japan

Journal volume & issue: Vol. 2, no. 1
pp. 76 – 83

Abstract

Read online

Background: Catheter ablation is a standard therapy for frequent premature ventricular complex (PVCs). Predicting their origin from a 12-lead electrocardiogram (ECG) is crucial but it requires specialized knowledge and experience. Objective: The objective of the present study was to develop and evaluate machine learning algorithms that predicted PVC origins from an ECG. Methods: We developed the algorithms utilizing a support vector machine (SVM) and a convolutional neural network (CNN). The training, validating, and testing data consisted of 116 PVCs from 111 patients who underwent catheter ablation. The ECG signals were labeled with the PVC origin, which was confirmed using a 3-dimensional electroanatomical mapping system. We classified the origins into 4 groups: right or left, outflow tract, or other sites. We trained and evaluated the model performance. The testing datasets were also evaluated by board-certified electrophysiologists and an existing classification algorithm. We also developed binary classification models that predicted whether the origin was on the right or left side of the heart. Results: The weighted accuracies of the 4-class classification were as follows: SVM 0.85, CNN 0.80, electrophysiologists 0.73, and existing algorithm 0.86. The precision, recall, and F1 in the machine learning models marked better than physicians and comparable to the existing algorithm. The SVM model scored among the best accuracy in the binary classification (the accuracies were 0.94, 0.87, 0.79, and 0.90, respectively). Conclusion: Artificial intelligence–enabled algorithms that predict the origin of PVCs achieved superior accuracy compared to the electrophysiologists and comparable accuracy to the existing algorithm.

Published in Cardiovascular Digital Health Journal

ISSN: 2666-6936 (Online)
Publisher: Elsevier
Country of publisher: United States
LCC subjects: Medicine: Internal medicine: Specialties of internal medicine: Diseases of the circulatory (Cardiovascular) system; Medicine: Medicine (General): Medical technology
Website: https://www.journals.elsevier.com/cardiovascular-digital-health-journal

About the journal

Abstract

Keywords