Artificial intelligence augments detection accuracy of cardiac insertable cardiac monitors: Results from a pilot prospective observational study
Background: Insertable cardiac monitors (ICMs) are indicated for long-term monitoring of patients with unexplained syncope or who are at risk for cardiac arrhythmias. The volume of ICM-transmitted information may result in long data review times to identify true and clinically relevant arrhythmias....
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-10-01
|
Series: | Cardiovascular Digital Health Journal |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666693622001189 |
_version_ | 1797985825287307264 |
---|---|
author | Fabio Quartieri, MD Manuel Marina-Breysse, MD, MS Annalisa Pollastrelli, MS Isabella Paini, MScN Carlos Lizcano, MS José María Lillo-Castellano, PhD Andrea Grammatico, PhD |
author_facet | Fabio Quartieri, MD Manuel Marina-Breysse, MD, MS Annalisa Pollastrelli, MS Isabella Paini, MScN Carlos Lizcano, MS José María Lillo-Castellano, PhD Andrea Grammatico, PhD |
author_sort | Fabio Quartieri, MD |
collection | DOAJ |
description | Background: Insertable cardiac monitors (ICMs) are indicated for long-term monitoring of patients with unexplained syncope or who are at risk for cardiac arrhythmias. The volume of ICM-transmitted information may result in long data review times to identify true and clinically relevant arrhythmias. Objective: The purpose of this study was to evaluate whether artificial intelligence (AI) may improve ICM detection accuracy. Methods: We performed a retrospective analysis of consecutive patients implanted with the Confirm RxTM ICM (Abbott) and followed in a prospective observational study. This device continuously monitors subcutaneous electrocardiograms (SECGs) and transmits to clinicians information about detected arrhythmias and patient-activated symptomatic episodes. All SECGs were classified by expert electrophysiologists and by the WillemTM AI algorithm (IDOVEN). Results: During mean follow-up of 23 months, of 20 ICM patients (mean age 68 ± 12 years; 50% women), 19 had 2261 SECGs recordings associated with cardiac arrhythmia detections or patient symptoms. True arrhythmias occurred in 11 patients: asystoles in 2, bradycardias in 3, ventricular tachycardias in 4, and atrial tachyarrhythmias (atrial tachycardia/atrial fibrillation [AT/AF]) in 10; with 6 patients having >1 arrhythmia type. AI algorithm overall accuracy for arrhythmia classification was 95.4%, with 97.19% sensitivity, 94.52% specificity, 89.74% positive predictive value, and 98.55% negative predictive value. Application of AI would have reduced the number of false-positive results by 98.0% overall: 94.0% for AT/AF, 87.5% for ventricular tachycardia, 99.5% for bradycardia, and 98.8% for asystole. Conclusion: Application of AI to ICM-detected episodes is associated with high classification accuracy and may significantly reduce health care staff workload by triaging ICM data. |
first_indexed | 2024-04-11T07:24:16Z |
format | Article |
id | doaj.art-5bef7b92931945e5a9b1f03c38d943b3 |
institution | Directory Open Access Journal |
issn | 2666-6936 |
language | English |
last_indexed | 2024-04-11T07:24:16Z |
publishDate | 2022-10-01 |
publisher | Elsevier |
record_format | Article |
series | Cardiovascular Digital Health Journal |
spelling | doaj.art-5bef7b92931945e5a9b1f03c38d943b32022-12-22T04:37:07ZengElsevierCardiovascular Digital Health Journal2666-69362022-10-0135201211Artificial intelligence augments detection accuracy of cardiac insertable cardiac monitors: Results from a pilot prospective observational studyFabio Quartieri, MD0Manuel Marina-Breysse, MD, MS1Annalisa Pollastrelli, MS2Isabella Paini, MScN3Carlos Lizcano, MS4José María Lillo-Castellano, PhD5Andrea Grammatico, PhD6Department of Cardiology, Azienda Ospedaliera S. Maria Nuova, Reggio Emilia, Italy; Address reprint requests and correspondence: Dr Fabio Quartieri, Department of Cardiology, Ospedale S. Maria Nuova, Viale Risorgimento, Reggio Emilia, RE 42100 Italy.IDOVEN Research, AI Team, Madrid, Spain; Advanced Development in Arrhythmia Mechanisms and Therapy Laboratory, Myocardial Pathophysiology Area, Centro Nacional de Investigaciones Cardiovasculares (CNIC), Madrid, Spain; Centro de Investigación Biomédica en Red de Enfermedades Cardiovasculares (CIBERCV), Madrid, SpainEMEA CRM Medical Affairs, Abbott, Rome, ItalyDepartment of Cardiology, Azienda Ospedaliera S. Maria Nuova, Reggio Emilia, ItalyIDOVEN Research, AI Team, Madrid, SpainIDOVEN Research, AI Team, Madrid, Spain; Advanced Development in Arrhythmia Mechanisms and Therapy Laboratory, Myocardial Pathophysiology Area, Centro Nacional de Investigaciones Cardiovasculares (CNIC), Madrid, Spain; Fundación Interhospitalaria para la Investigación Cardiovascular (FIC), Madrid, SpainEMEA CRM Medical Affairs, Abbott, Rome, ItalyBackground: Insertable cardiac monitors (ICMs) are indicated for long-term monitoring of patients with unexplained syncope or who are at risk for cardiac arrhythmias. The volume of ICM-transmitted information may result in long data review times to identify true and clinically relevant arrhythmias. Objective: The purpose of this study was to evaluate whether artificial intelligence (AI) may improve ICM detection accuracy. Methods: We performed a retrospective analysis of consecutive patients implanted with the Confirm RxTM ICM (Abbott) and followed in a prospective observational study. This device continuously monitors subcutaneous electrocardiograms (SECGs) and transmits to clinicians information about detected arrhythmias and patient-activated symptomatic episodes. All SECGs were classified by expert electrophysiologists and by the WillemTM AI algorithm (IDOVEN). Results: During mean follow-up of 23 months, of 20 ICM patients (mean age 68 ± 12 years; 50% women), 19 had 2261 SECGs recordings associated with cardiac arrhythmia detections or patient symptoms. True arrhythmias occurred in 11 patients: asystoles in 2, bradycardias in 3, ventricular tachycardias in 4, and atrial tachyarrhythmias (atrial tachycardia/atrial fibrillation [AT/AF]) in 10; with 6 patients having >1 arrhythmia type. AI algorithm overall accuracy for arrhythmia classification was 95.4%, with 97.19% sensitivity, 94.52% specificity, 89.74% positive predictive value, and 98.55% negative predictive value. Application of AI would have reduced the number of false-positive results by 98.0% overall: 94.0% for AT/AF, 87.5% for ventricular tachycardia, 99.5% for bradycardia, and 98.8% for asystole. Conclusion: Application of AI to ICM-detected episodes is associated with high classification accuracy and may significantly reduce health care staff workload by triaging ICM data.http://www.sciencedirect.com/science/article/pii/S2666693622001189Artificial intelligenceDetection accuracyInsertable cardiac monitors |
spellingShingle | Fabio Quartieri, MD Manuel Marina-Breysse, MD, MS Annalisa Pollastrelli, MS Isabella Paini, MScN Carlos Lizcano, MS José María Lillo-Castellano, PhD Andrea Grammatico, PhD Artificial intelligence augments detection accuracy of cardiac insertable cardiac monitors: Results from a pilot prospective observational study Cardiovascular Digital Health Journal Artificial intelligence Detection accuracy Insertable cardiac monitors |
title | Artificial intelligence augments detection accuracy of cardiac insertable cardiac monitors: Results from a pilot prospective observational study |
title_full | Artificial intelligence augments detection accuracy of cardiac insertable cardiac monitors: Results from a pilot prospective observational study |
title_fullStr | Artificial intelligence augments detection accuracy of cardiac insertable cardiac monitors: Results from a pilot prospective observational study |
title_full_unstemmed | Artificial intelligence augments detection accuracy of cardiac insertable cardiac monitors: Results from a pilot prospective observational study |
title_short | Artificial intelligence augments detection accuracy of cardiac insertable cardiac monitors: Results from a pilot prospective observational study |
title_sort | artificial intelligence augments detection accuracy of cardiac insertable cardiac monitors results from a pilot prospective observational study |
topic | Artificial intelligence Detection accuracy Insertable cardiac monitors |
url | http://www.sciencedirect.com/science/article/pii/S2666693622001189 |
work_keys_str_mv | AT fabioquartierimd artificialintelligenceaugmentsdetectionaccuracyofcardiacinsertablecardiacmonitorsresultsfromapilotprospectiveobservationalstudy AT manuelmarinabreyssemdms artificialintelligenceaugmentsdetectionaccuracyofcardiacinsertablecardiacmonitorsresultsfromapilotprospectiveobservationalstudy AT annalisapollastrellims artificialintelligenceaugmentsdetectionaccuracyofcardiacinsertablecardiacmonitorsresultsfromapilotprospectiveobservationalstudy AT isabellapainimscn artificialintelligenceaugmentsdetectionaccuracyofcardiacinsertablecardiacmonitorsresultsfromapilotprospectiveobservationalstudy AT carloslizcanoms artificialintelligenceaugmentsdetectionaccuracyofcardiacinsertablecardiacmonitorsresultsfromapilotprospectiveobservationalstudy AT josemarialillocastellanophd artificialintelligenceaugmentsdetectionaccuracyofcardiacinsertablecardiacmonitorsresultsfromapilotprospectiveobservationalstudy AT andreagrammaticophd artificialintelligenceaugmentsdetectionaccuracyofcardiacinsertablecardiacmonitorsresultsfromapilotprospectiveobservationalstudy |