Dataset Information

Diagnostic Accuracy of the Deep Learning Model for the Detection of ST Elevation Myocardial Infarction on Electrocardiogram.

ABSTRACT: We aimed to measure the diagnostic accuracy of the deep learning model (DLM) for ST-elevation myocardial infarction (STEMI) on a 12-lead electrocardiogram (ECG) according to culprit artery sorts. From January 2017 to December 2019, we recruited patients with STEMI who received more than one stent insertion for culprit artery occlusion. The DLM was trained with STEMI and normal sinus rhythm ECG for external validation. The primary outcome was the diagnostic accuracy of DLM for STEMI according to the three different culprit arteries. The outcomes were measured using the area under the receiver operating characteristic curve (AUROC), sensitivity (SEN), and specificity (SPE) using the Youden index. A total of 60,157 ECGs were obtained. These included 117 STEMI-ECGs and 60,040 normal sinus rhythm ECGs. When using DLM, the AUROC for overall STEMI was 0.998 (0.996-0.999) with SEN 97.4% (95.7-100) and SPE 99.2% (98.1-99.4). There were no significant differences in diagnostic accuracy within the three culprit arteries. The baseline wanders in false positive cases (83.7%, 345/412) significantly interfered with the accurate interpretation of ST elevation on an ECG. DLM showed high diagnostic accuracy for STEMI detection, regardless of the type of culprit artery. The baseline wanders of the ECGs could affect the misinterpretation of DLM.

SUBMITTER: Choi HY

PROVIDER: S-EPMC8956114 | biostudies-literature | 2022 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Diagnostic Accuracy of the Deep Learning Model for the Detection of ST Elevation Myocardial Infarction on Electrocardiogram.

Choi Hyun Young HY Kim Wonhee W Kang Gu Hyun GH Jang Yong Soo YS Lee Yoonje Y Kim Jae Guk JG Lee Namho N Shin Dong Geum DG Bae Woong W Song Youngjae Y

Journal of personalized medicine 20220223 3

We aimed to measure the diagnostic accuracy of the deep learning model (DLM) for ST-elevation myocardial infarction (STEMI) on a 12-lead electrocardiogram (ECG) according to culprit artery sorts. From January 2017 to December 2019, we recruited patients with STEMI who received more than one stent insertion for culprit artery occlusion. The DLM was trained with STEMI and normal sinus rhythm ECG for external validation. The primary outcome was the diagnostic accuracy of DLM for STEMI according to ...[more]

PMID: 35330336

Similar Datasets

Project description:IntroductionInterruptions in the emergency department (ED) are associated with clinical errors, yet are important when providing care to multiple patients. Screening triage electrocardiograms (ECG) for ST-segment elevation myocardial infarction (STEMI) represent a critical interrupting task that emergency physicians (EP) frequently encounter. To address interruptions such as ECG interpretation, many EPs engage in task switching, pausing their primary task to address an interrupting task. The impact of task switching on clinical errors in interpreting screening ECGs for STEMI remains unknown.MethodsResident and attending EPs were invited to participate in a crossover simulation trial. Physicians first completed a task-switching simulation in which they viewed patient presentations interrupted by clinical tasks, including screening ECGs requiring immediate interpretation before resuming the patient presentation. Participants then completed an uninterrupted simulation in which patient presentations and clinical tasks were completed sequentially without interruption. The primary outcome was accuracy of ECG interpretation for STEMI during task switching and uninterrupted simulations.ResultsThirty-five participants completed the study. We found no significant difference in accuracy of ECG interpretation for STEMI (task switching 0.89, uninterrupted 0.91, paired t-test p=0.21). Attending physician status (odds ratio [OR] [2.56], confidence interval [CI] [1.66-3.94], p<0.01) and inferior STEMI (OR [0.08], CI [0.04-0.14], p<0.01) were associated with increased and decreased odds of correct interpretation, respectively. Low self-reported confidence in interpretation was associated with decreased odds of correct interpretation in the task-switching simulation, but not in the uninterrupted simulation (interaction p=0.02).ConclusionIn our simulation, task switching was not associated with overall accuracy of ECG interpretation for STEMI. However, odds of correct interpretation decreased with inferior STEMI ECGs and when participants self-reported low confidence when interrupted. Our study highlights opportunities to improve through focused ECG training, as well as self-identification of "high-risk" screening ECGs prone to error during interrupted clinical workflow.

Dataset Information

Diagnostic Accuracy of the Deep Learning Model for the Detection of ST Elevation Myocardial Infarction on Electrocardiogram.

Publications

Diagnostic Accuracy of the Deep Learning Model for the Detection of ST Elevation Myocardial Infarction on Electrocardiogram.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets