External validation of a machine learning based classification algorithm for ambulatory heart rhythm diagnostics in pericardioversion atrial fibrillation patients using smartphone photoplethysmography: the SMARTBEATS-ALGO study.

IF 7.9 1区医学 Q1 CARDIAC & CARDIOVASCULAR SYSTEMS

Europace Pub Date : 2025-02-17 DOI:10.1093/europace/euaf031

Jonatan Fernstad, Emma Svennberg, Peter Åberg, Katrin Kemp Gudmundsdottir, Anders Jansson, Johan Engdahl

{"title":"External validation of a machine learning based classification algorithm for ambulatory heart rhythm diagnostics in pericardioversion atrial fibrillation patients using smartphone photoplethysmography: the SMARTBEATS-ALGO study.","authors":"Jonatan Fernstad, Emma Svennberg, Peter Åberg, Katrin Kemp Gudmundsdottir, Anders Jansson, Johan Engdahl","doi":"10.1093/europace/euaf031","DOIUrl":null,"url":null,"abstract":"Aims: The aim of this study was to perform an external validation of an automatic machine learning algorithm for heart rhythm diagnostics using smartphone photoplethysmography (PPG) recorded by patients with atrial fibrillation (AF) and atrial flutter (AFL) pericardioversion in an unsupervised ambulatory setting.Methods and results: Patients undergoing cardioversion for AF or AFL performed 1-min heart rhythm recordings peri-cardioversion at least twice daily for 4-6 weeks, using an iPhone 7 smartphone running a PPG application (CORAI Heart Monitor) simultaneously with a single-lead ECG recording (KardiaMobile). The algorithm uses support vector machines (SVM) to classify heart rhythm from smartphone-PPG. The algorithm was trained on PPG recordings made by patients in a separate cardioversion cohort. Photoplethysmography recordings in the external validation cohort were analysed by the algorithm. Diagnostic performance was calculated by comparing the heart rhythm classification output to the diagnosis from the simultaneous ECG recordings (gold standard).In total 460 patients performed 34 097 simultaneous PPG and ECG recordings, divided into 180 patients with 16 092 recordings in the training cohort and 280 patients with 18 005 recordings in the external validation cohort. Algorithm classification of the PPG recordings in the external validation cohort diagnosed AF with sensitivity, specificity and accuracy of 99.7/99.7/99.7%, and AF/AFL with sensitivity, specificity and accuracy of 99.3/99.1/99.2%.Conclusion: A machine learning based algorithm demonstrated excellent performance in diagnosing atrial fibrillation and atrial flutter from smartphone-PPG recordings in an unsupervised ambulatory setting, minimizing the need for manual review and ECG verification, in elderly cardioversion populations.","PeriodicalId":11981,"journal":{"name":"Europace","volume":" ","pages":""},"PeriodicalIF":7.9000,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Europace","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/europace/euaf031","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

Aims: The aim of this study was to perform an external validation of an automatic machine learning algorithm for heart rhythm diagnostics using smartphone photoplethysmography (PPG) recorded by patients with atrial fibrillation (AF) and atrial flutter (AFL) pericardioversion in an unsupervised ambulatory setting.

Methods and results: Patients undergoing cardioversion for AF or AFL performed 1-min heart rhythm recordings peri-cardioversion at least twice daily for 4-6 weeks, using an iPhone 7 smartphone running a PPG application (CORAI Heart Monitor) simultaneously with a single-lead ECG recording (KardiaMobile). The algorithm uses support vector machines (SVM) to classify heart rhythm from smartphone-PPG. The algorithm was trained on PPG recordings made by patients in a separate cardioversion cohort. Photoplethysmography recordings in the external validation cohort were analysed by the algorithm. Diagnostic performance was calculated by comparing the heart rhythm classification output to the diagnosis from the simultaneous ECG recordings (gold standard).In total 460 patients performed 34 097 simultaneous PPG and ECG recordings, divided into 180 patients with 16 092 recordings in the training cohort and 280 patients with 18 005 recordings in the external validation cohort. Algorithm classification of the PPG recordings in the external validation cohort diagnosed AF with sensitivity, specificity and accuracy of 99.7/99.7/99.7%, and AF/AFL with sensitivity, specificity and accuracy of 99.3/99.1/99.2%.

Conclusion: A machine learning based algorithm demonstrated excellent performance in diagnosing atrial fibrillation and atrial flutter from smartphone-PPG recordings in an unsupervised ambulatory setting, minimizing the need for manual review and ECG verification, in elderly cardioversion populations.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Europace 医学-心血管系统

CiteScore

10.30

自引率

8.20%

发文量

851

审稿时长

3-6 weeks

期刊介绍： EP - Europace - European Journal of Pacing, Arrhythmias and Cardiac Electrophysiology of the European Heart Rhythm Association of the European Society of Cardiology. The journal aims to provide an avenue of communication of top quality European and international original scientific work and reviews in the fields of Arrhythmias, Pacing and Cellular Electrophysiology. The Journal offers the reader a collection of contemporary original peer-reviewed papers, invited papers and editorial comments together with book reviews and correspondence.