Photoplethysmography-Based Machine Learning Approaches for Atrial Fibrillation Prediction: A Report From the Huawei Heart Study

Yutao Guo; Hao Wang; Hui Zhang; Tong Liu; Luping Li; Lingjie Liu; Maolin Chen; Yundai Chen; Gregory Y H Lip

doi:10.1016/j.jacasi.2021.09.004

Photoplethysmography-Based Machine Learning Approaches for Atrial Fibrillation Prediction: A Report From the Huawei Heart Study

JACC Asia. 2021 Dec 21;1(3):399-408. doi: 10.1016/j.jacasi.2021.09.004. eCollection 2021 Dec.

Authors

Yutao Guo¹, Hao Wang², Hui Zhang¹, Tong Liu³, Luping Li⁴, Lingjie Liu⁴, Maolin Chen⁴, Yundai Chen¹, Gregory Y H Lip^{5

6}

Affiliations

¹ Department of Pulmonary Vessel and Thrombotic Disease, Sixth Medical Center, Chinese PLA General Hospital, Beijing, China.
² Department of Cardiology, Second Medical Center, Chinese PLA General Hospital, Beijing, China.
³ Tianjin Key Laboratory of Ionic-Molecular Function of Cardiovascular Disease, Tianjin Institute of Cardiology, Second Hospital of Tianjin Medical University, Tianjin, China.
⁴ Huawei Technologies Co, Shenzhen, China.
⁵ Liverpool Centre for Cardiovascular Sciences, University of Liverpool, Liverpool, United Kingdom.
⁶ Aalborg Thrombosis Research Unit, Department of Clinical Medicine, Aalborg University, Aalborg, Denmark.

Abstract

Background: Current wearable devices enable the detection of atrial fibrillation (AF), but a machine learning (ML)-based approach may facilitate accurate prediction of AF onset.

Objectives: The present study aimed to develop, optimize, and validate an ML-based model for real-time prediction of AF onset in a population at high risk of incident AF.

Methods: A primary ML-based prediction model of AF onset (M1) was developed on the basis of the Huawei Heart Study, a general-population AF screening study using photoplethysmography (PPG)-based smart devices. After optimization in 554 individuals with 469,267 PPG data sets, the optimized ML-based model (M2) was further prospectively validated in 50 individuals with paroxysmal AF at high risk of AF onset, and compared with 72-hour Holter electrocardiographic (ECG) monitoring, a criterion standard, from September 1, 2019, to November 5, 2019.

Results: Among 50 patients with paroxysmal AF (mean age 67 ± 12 years, 40% women), there were 2,808 AF events from a total of 14,847,356 ECGs over 72 hours and 6,860 PPGs (45.83 ± 13.9 per subject per day). The best performance of M1 for AF onset prediction was achieved 4 hours before AF onset (area under the receiver operating characteristic curve: 0.94; 95% confidence interval: 0.93-0.94). M2 sensitivity, specificity, positive predictive value, negative predictive value, and accuracy (at 0 to 4 hours before AF onset) were 81.9%, 96.6%, 96.4%, 83.1%, and 88.9%, respectively, compared with 72-hour Holter ECG.

Conclusions: The PPG- based ML model demonstrated good ability for AF prediction in advance. (Mobile Health [mHealth] technology for improved screening, patient involvement and optimizing integrated care in atrial fibrillation; ChiCTR-OOC-17014138).

Keywords: AF, atrial fibrillation; AUC, area under receiver operating characteristic curve; ECG, electrocardiography; NPV, negative predictive value; PPG, photoplethysmography; PPV, positive predictive value; ROC, receiver operating characteristic; artificial intelligence; atrial fibrillation; machine learning; risk prediction.