Dataset Information

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

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).

SUBMITTER: Guo Y

PROVIDER: S-EPMC9627828 | biostudies-literature | 2021 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Guo Yutao Y Wang Hao H Zhang Hui H Liu Tong T Li Luping L Liu Lingjie L Chen Maolin M Chen Yundai Y Lip Gregory Y H GYH

JACC. Asia 20211221 3

<h4>Background</h4>Current wearable devices enable the detection of atrial fibrillation (AF), but a machine learning (ML)-based approach may facilitate accurate prediction of AF onset.<h4>Objectives</h4>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.<h4>Methods</h4>A primary ML-based prediction model of AF onset (M1) was developed on the basis of the Huawei Heart Study, a general-popula ...[more]

PMID: 36341222

Similar Datasets

Project description:Background: Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia and post-operative atrial fibrillation (POAF) is a major healthcare burden, contributing to an increased risk of stroke, kidney failure, heart attack and death. Genetic studies have identified associations with AF, but no molecular diagnostic exists to predict POAF based on pre-operative measurements. Such a tool would be of great value for perioperative planning to improve patient care and reduce healthcare costs. In this pilot study of epigenetic precision medicine in the perioperative period, we carried out bisulfite sequencing to measure DNA methylation status in blood collected from patients prior to cardiac surgery to identify biosignatures of POAF. Methods: We enrolled 221 patients undergoing cardiac surgery in this prospective observational study. DNA methylation measurements were obtained from blood samples drawn from awake patients prior to surgery. After controlling for clinical and methylation covariates, we analyzed DNA methylation loci in the discovery cohort of 110 patients for association with POAF. We also constructed predictive models for POAF using clinical and DNA methylation data. We subsequently performed targeted analyses of a separate cohort of 101 cardiac surgical patients to measure the methylation status solely of significant methylation loci in the discovery cohort. Results: A total of 47 patients in the discovery cohort (42.7%) and 43 patients in the validation cohort (42.6%) developed POAF. We identified 12 CpGs that were statistically significant in the discovery cohort after correcting for multiple hypothesis testing. Of these sites, 6 were amenable to targeted bisulfite sequencing and chr16:24640902 was statistically significant in the validation cohort. In addition, the methylation POAF prediction model had an AUC of 0.79 in the validation cohort. Conclusions: We have identified DNA methylation biomarkers that can predict future occurrence of POAF associated with cardiac surgery. This research demonstrates the use of precision medicine to develop models combining epigenomic and clinical data to predict disease.

Dataset Information

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

Background

Objectives

Methods

Results

Conclusions

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets