A multicenter pragmatic implementation study of AI-ECG-based clinical decision support software to identify low LVEF: Clinical trial design and methods

Background: Artificial intelligence (AI) enabled algorithms can detect or predict cardiovascular conditions using electrocardiogram (ECG) data. Clinical studies have evaluated ECG-AI algorithms, including a recent single-center study which evaluated outcomes when clinicians were provided with ECG-AI...

Full description

Saved in:
Bibliographic Details
Main Authors: Francisco Lopez-Jimenez, Heather M. Alger, Zachi I. Attia, Barbara Barry, Ranee Chatterjee, Rowena Dolor, Paul A. Friedman, Stephen J. Greene, Jason Greenwood, Vinay Gundurao, Sarah Hackett, Prerak Jain, Anja Kinaszczuk, Ketan Mehta, Jason O'Grady, Ambarish Pandey, Christopher Pullins, Arjun R. Puranik, Mohan Krishna Ranganathan, David Rushlow, Mark Stampehl, Vinayak Subramanian, Kitzner Vassor, Xuan Zhu, Samir Awasthi
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:American Heart Journal Plus
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S266660222500031X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850144523001266176
author Francisco Lopez-Jimenez
Heather M. Alger
Zachi I. Attia
Barbara Barry
Ranee Chatterjee
Rowena Dolor
Paul A. Friedman
Stephen J. Greene
Jason Greenwood
Vinay Gundurao
Sarah Hackett
Prerak Jain
Anja Kinaszczuk
Ketan Mehta
Jason O'Grady
Ambarish Pandey
Christopher Pullins
Arjun R. Puranik
Mohan Krishna Ranganathan
David Rushlow
Mark Stampehl
Vinayak Subramanian
Kitzner Vassor
Xuan Zhu
Samir Awasthi
author_facet Francisco Lopez-Jimenez
Heather M. Alger
Zachi I. Attia
Barbara Barry
Ranee Chatterjee
Rowena Dolor
Paul A. Friedman
Stephen J. Greene
Jason Greenwood
Vinay Gundurao
Sarah Hackett
Prerak Jain
Anja Kinaszczuk
Ketan Mehta
Jason O'Grady
Ambarish Pandey
Christopher Pullins
Arjun R. Puranik
Mohan Krishna Ranganathan
David Rushlow
Mark Stampehl
Vinayak Subramanian
Kitzner Vassor
Xuan Zhu
Samir Awasthi
author_sort Francisco Lopez-Jimenez
collection DOAJ
description Background: Artificial intelligence (AI) enabled algorithms can detect or predict cardiovascular conditions using electrocardiogram (ECG) data. Clinical studies have evaluated ECG-AI algorithms, including a recent single-center study which evaluated outcomes when clinicians were provided with ECG-AI results. A Multicenter Pragmatic IMplementation Study of ECG-AI-Based Clinical Decision Support Software to Identify Low LVEF (AIM ECG-AI) will evaluate clinical impacts of clinical decision support software (CDSS) integrated within the electronic health record (EHR) to provide point-of-care ECG-AI results to clinicians during routine outpatient care. Methods: AIM ECG-AI is a multicenter, cluster-randomized trial recruiting and randomizing clinicians to receive access to the CDSS (intervention) or provide usual care. Clinicians are recruited from 5 geographically distinct health systems and clustered at the care team level. AIM ECG-AI will evaluate clinical care provided during >32,000 eligible clinical encounters with adult patients with no history of low LVEF and who have a digital ECG documented within the health system's EHR, with 90 day follow up. Results: Study data includes clinician surveys, study software metrics, and EHR data as a read-out for clinician decision-making. AIM ECG-AI will evaluate detection of left ventricular ejection fraction ≤40 % by echocardiography, with exploratory endpoints. Subgroup analyses will evaluate the health system, clinician, and patient-level characteristics associated with outcomes (NCT05867407). Conclusion: AIM ECG-AI is the first multisite clinical evaluation of an EHR-integrated, point-of-care CDSS to provide ECG-AI results in the clinical workflow. The findings will provide valuable insights for clinically focused software design to bring AI into routine clinical practice.
format Article
id doaj-art-f851bf9b51e3401a94fb9e9f5c0a2521
institution OA Journals
issn 2666-6022
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series American Heart Journal Plus
spelling doaj-art-f851bf9b51e3401a94fb9e9f5c0a25212025-08-20T02:28:20ZengElsevierAmerican Heart Journal Plus2666-60222025-06-015410052810.1016/j.ahjo.2025.100528A multicenter pragmatic implementation study of AI-ECG-based clinical decision support software to identify low LVEF: Clinical trial design and methodsFrancisco Lopez-Jimenez0Heather M. Alger1Zachi I. Attia2Barbara Barry3Ranee Chatterjee4Rowena Dolor5Paul A. Friedman6Stephen J. Greene7Jason Greenwood8Vinay Gundurao9Sarah Hackett10Prerak Jain11Anja Kinaszczuk12Ketan Mehta13Jason O'Grady14Ambarish Pandey15Christopher Pullins16Arjun R. Puranik17Mohan Krishna Ranganathan18David Rushlow19Mark Stampehl20Vinayak Subramanian21Kitzner Vassor22Xuan Zhu23Samir Awasthi24Mayo Clinic, Rochester, MN, United States of AmericaAnumana, Inc., Cambridge, MA, United States of America; nference, Inc., Cambridge, MA, United States of America and Bengaluru, India; Corresponding author at: Anumana, Inc., Cambridge, MA, United States of AmericaMayo Clinic, Rochester, MN, United States of AmericaMayo Clinic, Rochester, MN, United States of AmericaDuke University School of Medicine, Durham, NC, United States of AmericaDuke University School of Medicine, Durham, NC, United States of AmericaMayo Clinic, Rochester, MN, United States of AmericaDuke University School of Medicine, Durham, NC, United States of America; Duke Clinical Research Institute, United States of AmericaMayo Clinic, Rochester, MN, United States of AmericaAnumana, Inc., Cambridge, MA, United States of America; nference, Inc., Cambridge, MA, United States of America and Bengaluru, IndiaAnumana, Inc., Cambridge, MA, United States of America; nference, Inc., Cambridge, MA, United States of America and Bengaluru, IndiaAnumana, Inc., Cambridge, MA, United States of America; nference, Inc., Cambridge, MA, United States of America and Bengaluru, IndiaMayo Clinic, Jacksonville, FL, United States of AmericaAnumana, Inc., Cambridge, MA, United States of America; nference, Inc., Cambridge, MA, United States of America and Bengaluru, IndiaMayo Clinic, Rochester, MN, United States of AmericaUT Southwestern Medical Center, Dallas, TX, United States of AmericaMayo Clinic Arrowhead, AZ, United States of AmericaAnumana, Inc., Cambridge, MA, United States of America; nference, Inc., Cambridge, MA, United States of America and Bengaluru, IndiaAnumana, Inc., Cambridge, MA, United States of America; nference, Inc., Cambridge, MA, United States of America and Bengaluru, IndiaMayo Clinic, Rochester, MN, United States of AmericaNovartis Pharmaceuticals Corp, East Hanover, NJ, United States of AmericaUT Southwestern Medical Center, Dallas, TX, United States of AmericaAnumana, Inc., Cambridge, MA, United States of America; nference, Inc., Cambridge, MA, United States of America and Bengaluru, IndiaMayo Clinic, Rochester, MN, United States of AmericaAnumana, Inc., Cambridge, MA, United States of America; nference, Inc., Cambridge, MA, United States of America and Bengaluru, IndiaBackground: Artificial intelligence (AI) enabled algorithms can detect or predict cardiovascular conditions using electrocardiogram (ECG) data. Clinical studies have evaluated ECG-AI algorithms, including a recent single-center study which evaluated outcomes when clinicians were provided with ECG-AI results. A Multicenter Pragmatic IMplementation Study of ECG-AI-Based Clinical Decision Support Software to Identify Low LVEF (AIM ECG-AI) will evaluate clinical impacts of clinical decision support software (CDSS) integrated within the electronic health record (EHR) to provide point-of-care ECG-AI results to clinicians during routine outpatient care. Methods: AIM ECG-AI is a multicenter, cluster-randomized trial recruiting and randomizing clinicians to receive access to the CDSS (intervention) or provide usual care. Clinicians are recruited from 5 geographically distinct health systems and clustered at the care team level. AIM ECG-AI will evaluate clinical care provided during >32,000 eligible clinical encounters with adult patients with no history of low LVEF and who have a digital ECG documented within the health system's EHR, with 90 day follow up. Results: Study data includes clinician surveys, study software metrics, and EHR data as a read-out for clinician decision-making. AIM ECG-AI will evaluate detection of left ventricular ejection fraction ≤40 % by echocardiography, with exploratory endpoints. Subgroup analyses will evaluate the health system, clinician, and patient-level characteristics associated with outcomes (NCT05867407). Conclusion: AIM ECG-AI is the first multisite clinical evaluation of an EHR-integrated, point-of-care CDSS to provide ECG-AI results in the clinical workflow. The findings will provide valuable insights for clinically focused software design to bring AI into routine clinical practice.http://www.sciencedirect.com/science/article/pii/S266660222500031XElectrocardiogramArtificial intelligenceLeft ventricular ejection fractionHeart failureClinical decision supportBest practice alerts
spellingShingle Francisco Lopez-Jimenez
Heather M. Alger
Zachi I. Attia
Barbara Barry
Ranee Chatterjee
Rowena Dolor
Paul A. Friedman
Stephen J. Greene
Jason Greenwood
Vinay Gundurao
Sarah Hackett
Prerak Jain
Anja Kinaszczuk
Ketan Mehta
Jason O'Grady
Ambarish Pandey
Christopher Pullins
Arjun R. Puranik
Mohan Krishna Ranganathan
David Rushlow
Mark Stampehl
Vinayak Subramanian
Kitzner Vassor
Xuan Zhu
Samir Awasthi
A multicenter pragmatic implementation study of AI-ECG-based clinical decision support software to identify low LVEF: Clinical trial design and methods
American Heart Journal Plus
Electrocardiogram
Artificial intelligence
Left ventricular ejection fraction
Heart failure
Clinical decision support
Best practice alerts
title A multicenter pragmatic implementation study of AI-ECG-based clinical decision support software to identify low LVEF: Clinical trial design and methods
title_full A multicenter pragmatic implementation study of AI-ECG-based clinical decision support software to identify low LVEF: Clinical trial design and methods
title_fullStr A multicenter pragmatic implementation study of AI-ECG-based clinical decision support software to identify low LVEF: Clinical trial design and methods
title_full_unstemmed A multicenter pragmatic implementation study of AI-ECG-based clinical decision support software to identify low LVEF: Clinical trial design and methods
title_short A multicenter pragmatic implementation study of AI-ECG-based clinical decision support software to identify low LVEF: Clinical trial design and methods
title_sort multicenter pragmatic implementation study of ai ecg based clinical decision support software to identify low lvef clinical trial design and methods
topic Electrocardiogram
Artificial intelligence
Left ventricular ejection fraction
Heart failure
Clinical decision support
Best practice alerts
url http://www.sciencedirect.com/science/article/pii/S266660222500031X
work_keys_str_mv AT franciscolopezjimenez amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT heathermalger amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT zachiiattia amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT barbarabarry amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT raneechatterjee amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT rowenadolor amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT paulafriedman amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT stephenjgreene amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT jasongreenwood amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT vinaygundurao amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT sarahhackett amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT prerakjain amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT anjakinaszczuk amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT ketanmehta amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT jasonogrady amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT ambarishpandey amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT christopherpullins amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT arjunrpuranik amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT mohankrishnaranganathan amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT davidrushlow amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT markstampehl amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT vinayaksubramanian amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT kitznervassor amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT xuanzhu amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT samirawasthi amulticenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT franciscolopezjimenez multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT heathermalger multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT zachiiattia multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT barbarabarry multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT raneechatterjee multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT rowenadolor multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT paulafriedman multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT stephenjgreene multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT jasongreenwood multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT vinaygundurao multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT sarahhackett multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT prerakjain multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT anjakinaszczuk multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT ketanmehta multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT jasonogrady multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT ambarishpandey multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT christopherpullins multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT arjunrpuranik multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT mohankrishnaranganathan multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT davidrushlow multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT markstampehl multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT vinayaksubramanian multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT kitznervassor multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT xuanzhu multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods
AT samirawasthi multicenterpragmaticimplementationstudyofaiecgbasedclinicaldecisionsupportsoftwaretoidentifylowlvefclinicaltrialdesignandmethods