Artificial intelligence-assisted diagnosis and prognostication in low ejection fraction using electrocardiograms in inpatient department: a pragmatic randomized controlled trial

Abstract Background Early diagnosis of low ejection fraction (EF) remains challenging despite being a treatable condition. This study aimed to evaluate the effectiveness of an electrocardiogram (ECG)-based artificial intelligence (AI)-assisted clinical decision support tool in improving the early di...

Full description

Saved in:
Bibliographic Details
Main Authors: Dung-Jang Tsai, Chin Lin, Wei-Ting Liu, Chiao-Chin Lee, Chiao-Hsiang Chang, Wen-Yu Lin, Yu-Lan Liu, Da-Wei Chang, Ping-Hsuan Hsieh, Chien-Sung Tsai, Yuan-Hao Chen, Yi-Jen Hung, Chin-Sheng Lin
Format: Article
Language:English
Published: BMC 2025-06-01
Series:BMC Medicine
Subjects:
Online Access:https://doi.org/10.1186/s12916-025-04190-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850102444708593664
author Dung-Jang Tsai
Chin Lin
Wei-Ting Liu
Chiao-Chin Lee
Chiao-Hsiang Chang
Wen-Yu Lin
Yu-Lan Liu
Da-Wei Chang
Ping-Hsuan Hsieh
Chien-Sung Tsai
Yuan-Hao Chen
Yi-Jen Hung
Chin-Sheng Lin
author_facet Dung-Jang Tsai
Chin Lin
Wei-Ting Liu
Chiao-Chin Lee
Chiao-Hsiang Chang
Wen-Yu Lin
Yu-Lan Liu
Da-Wei Chang
Ping-Hsuan Hsieh
Chien-Sung Tsai
Yuan-Hao Chen
Yi-Jen Hung
Chin-Sheng Lin
author_sort Dung-Jang Tsai
collection DOAJ
description Abstract Background Early diagnosis of low ejection fraction (EF) remains challenging despite being a treatable condition. This study aimed to evaluate the effectiveness of an electrocardiogram (ECG)-based artificial intelligence (AI)-assisted clinical decision support tool in improving the early diagnosis of low EF among inpatient patients under non-cardiologist care. Methods We conducted a pragmatic randomized controlled trial at an academic medical center in Taiwan. 13,631 inpatient patients were randomized to either the intervention group (n = 6,840) receiving AI-generated ECG results or the control group (n = 6,791) following standard care. The primary outcome was the incidence of newly diagnosed low EF (≤ 50%) within 30 days following the ECG. Secondary outcomes included echocardiogram utilization rates, positive predictive value for low EF detection, and cardiology consultation rates. Statistical analysis included hazard ratios (HR) with 95% confidence intervals (CI) for time-to-event outcomes and chi-square tests for categorical variables. Results The intervention significantly increased the detection of newly diagnosed low EF in the overall cohort (1.5% vs. 1.1%, HR 1.50, 95% CI: 1.11–2.03, P = 0.023), with a more pronounced effect among AI-identified high-risk patients (13.0% vs. 8.9%, HR 1.55, 95% CI: 1.08–2.21). While overall echocardiogram utilization remained similar between groups (17.1% vs. 17.3%, HR 1.00, 95% CI: 0.92–1.09), the intervention group demonstrated higher positive predictive value for identifying low EF among patients receiving echocardiogram (34.2% vs. 20.2%, p < 0.001). Post-hoc analysis revealed increased cardiology consultation rates among high-risk patients in the intervention group (29.3% vs. 23.5%, p = 0.027). Conclusions Implementation of an AI-ECG algorithm enhanced the early diagnosis of low EF in the inpatient setting, primarily by improving diagnostic efficiency rather than increasing overall healthcare utilization. The tool was particularly effective in identifying high-risk patients who benefited from increased specialist consultation and more targeted diagnostic testing. Trial registration ClinicalTrials.gov Identifier: NCT05117970.
format Article
id doaj-art-da43eb82bd8946669e11ebece30a0397
institution DOAJ
issn 1741-7015
language English
publishDate 2025-06-01
publisher BMC
record_format Article
series BMC Medicine
spelling doaj-art-da43eb82bd8946669e11ebece30a03972025-08-20T02:39:44ZengBMCBMC Medicine1741-70152025-06-0123111210.1186/s12916-025-04190-zArtificial intelligence-assisted diagnosis and prognostication in low ejection fraction using electrocardiograms in inpatient department: a pragmatic randomized controlled trialDung-Jang Tsai0Chin Lin1Wei-Ting Liu2Chiao-Chin Lee3Chiao-Hsiang Chang4Wen-Yu Lin5Yu-Lan Liu6Da-Wei Chang7Ping-Hsuan Hsieh8Chien-Sung Tsai9Yuan-Hao Chen10Yi-Jen Hung11Chin-Sheng Lin12Medical Technology Education Center, School of Medicine, National Defense Medical CenterMedical Technology Education Center, School of Medicine, National Defense Medical CenterDivision of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical CenterDivision of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical CenterDivision of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical CenterDivision of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical CenterDivision of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical CenterDivision of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical CenterSchool of Pharmacy, National Defense Medical CenterDivision of Cardiovascular Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical CenterDepartment of Neurological Surgery, Tri-Service General Hospital, National Defense Medical CenterDivision of Endocrinology and Metabolism, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical CenterDivision of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical CenterAbstract Background Early diagnosis of low ejection fraction (EF) remains challenging despite being a treatable condition. This study aimed to evaluate the effectiveness of an electrocardiogram (ECG)-based artificial intelligence (AI)-assisted clinical decision support tool in improving the early diagnosis of low EF among inpatient patients under non-cardiologist care. Methods We conducted a pragmatic randomized controlled trial at an academic medical center in Taiwan. 13,631 inpatient patients were randomized to either the intervention group (n = 6,840) receiving AI-generated ECG results or the control group (n = 6,791) following standard care. The primary outcome was the incidence of newly diagnosed low EF (≤ 50%) within 30 days following the ECG. Secondary outcomes included echocardiogram utilization rates, positive predictive value for low EF detection, and cardiology consultation rates. Statistical analysis included hazard ratios (HR) with 95% confidence intervals (CI) for time-to-event outcomes and chi-square tests for categorical variables. Results The intervention significantly increased the detection of newly diagnosed low EF in the overall cohort (1.5% vs. 1.1%, HR 1.50, 95% CI: 1.11–2.03, P = 0.023), with a more pronounced effect among AI-identified high-risk patients (13.0% vs. 8.9%, HR 1.55, 95% CI: 1.08–2.21). While overall echocardiogram utilization remained similar between groups (17.1% vs. 17.3%, HR 1.00, 95% CI: 0.92–1.09), the intervention group demonstrated higher positive predictive value for identifying low EF among patients receiving echocardiogram (34.2% vs. 20.2%, p < 0.001). Post-hoc analysis revealed increased cardiology consultation rates among high-risk patients in the intervention group (29.3% vs. 23.5%, p = 0.027). Conclusions Implementation of an AI-ECG algorithm enhanced the early diagnosis of low EF in the inpatient setting, primarily by improving diagnostic efficiency rather than increasing overall healthcare utilization. The tool was particularly effective in identifying high-risk patients who benefited from increased specialist consultation and more targeted diagnostic testing. Trial registration ClinicalTrials.gov Identifier: NCT05117970.https://doi.org/10.1186/s12916-025-04190-zArtificial intelligenceElectrocardiogramRapid response systemsLow Ejection FractionRandomized clinical trialHigh-intensity care
spellingShingle Dung-Jang Tsai
Chin Lin
Wei-Ting Liu
Chiao-Chin Lee
Chiao-Hsiang Chang
Wen-Yu Lin
Yu-Lan Liu
Da-Wei Chang
Ping-Hsuan Hsieh
Chien-Sung Tsai
Yuan-Hao Chen
Yi-Jen Hung
Chin-Sheng Lin
Artificial intelligence-assisted diagnosis and prognostication in low ejection fraction using electrocardiograms in inpatient department: a pragmatic randomized controlled trial
BMC Medicine
Artificial intelligence
Electrocardiogram
Rapid response systems
Low Ejection Fraction
Randomized clinical trial
High-intensity care
title Artificial intelligence-assisted diagnosis and prognostication in low ejection fraction using electrocardiograms in inpatient department: a pragmatic randomized controlled trial
title_full Artificial intelligence-assisted diagnosis and prognostication in low ejection fraction using electrocardiograms in inpatient department: a pragmatic randomized controlled trial
title_fullStr Artificial intelligence-assisted diagnosis and prognostication in low ejection fraction using electrocardiograms in inpatient department: a pragmatic randomized controlled trial
title_full_unstemmed Artificial intelligence-assisted diagnosis and prognostication in low ejection fraction using electrocardiograms in inpatient department: a pragmatic randomized controlled trial
title_short Artificial intelligence-assisted diagnosis and prognostication in low ejection fraction using electrocardiograms in inpatient department: a pragmatic randomized controlled trial
title_sort artificial intelligence assisted diagnosis and prognostication in low ejection fraction using electrocardiograms in inpatient department a pragmatic randomized controlled trial
topic Artificial intelligence
Electrocardiogram
Rapid response systems
Low Ejection Fraction
Randomized clinical trial
High-intensity care
url https://doi.org/10.1186/s12916-025-04190-z
work_keys_str_mv AT dungjangtsai artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial
AT chinlin artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial
AT weitingliu artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial
AT chiaochinlee artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial
AT chiaohsiangchang artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial
AT wenyulin artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial
AT yulanliu artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial
AT daweichang artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial
AT pinghsuanhsieh artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial
AT chiensungtsai artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial
AT yuanhaochen artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial
AT yijenhung artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial
AT chinshenglin artificialintelligenceassisteddiagnosisandprognosticationinlowejectionfractionusingelectrocardiogramsininpatientdepartmentapragmaticrandomizedcontrolledtrial