Advanced repeated structuring and learning procedure to detect acute myocardial ischemia in serial 12-lead ECGs
Agnese Sbrollini1, C Cato Ter Haar2,3, Chiara Leoni1
1Department of Information Engineering, Università Politecnica delle Marche, Ancona, Italy.
Insights
This study shows that a novel deep learning method, Advanced Repeated Structuring and Learning Procedure (AdvRS&LP), effectively detects acute myocardial ischemia using serial electrocardiograms (ECGs) in pre-hospital settings. The deep learning approach significantly outperformed traditional methods in identifying critical cardiac events.
Area of Science:
- Cardiology and Medical Informatics
- Application of artificial intelligence in healthcare diagnostics
- Pre-hospital emergency medicine
Background:
- Acute myocardial ischemia in acute coronary syndrome (ACS) can lead to myocardial infarction, necessitating rapid pre-hospital interventions.
- Serial electrocardiography (ECG) comparison enhances ischemia detection by accounting for individual patient variability.
- Deep learning combined with serial ECGs shows promise for early disease detection.
Purpose of the Study:
- To apply a novel deep learning method, Advanced Repeated Structuring and Learning Procedure (AdvRS&LP), for detecting acute myocardial ischemia.
- To utilize serial ECG features for improved accuracy in the pre-hospital phase.
- To evaluate the performance of AdvRS&LP against established methods like logistic regression and the Glasgow program.
Main Methods:
- Utilized 1425 ECG pairs from the SUBTRACT study, including 194 ACS patients and 1035 controls.
- Extracted 28 serial ECG features, along with sex and age, as inputs for the AdvRS&LP.
- Developed 100 neural networks (NNs) using AdvRS&LP and compared their performance (AUC, SE, SP) against logistic regression (LR) and the Uni-G algorithm.
Main Results:
- Neural networks created by AdvRS&LP demonstrated superior performance with a median AUC of 83%, median sensitivity (SE) of 77%, and median specificity (SP) of 89%.
- AdvRS&LP significantly outperformed logistic regression (median AUC 80%, SE 67%, SP 81%) and the Uni-G algorithm (SE 72%, SP 82%) (P < 0.05).
- The developed NNs showed strong generalization and clinical applicability.
Conclusions:
- Serial ECG comparison is a valuable technique for ischemia detection.
- Neural networks generated by the AdvRS&LP are reliable and effective tools for acute myocardial ischemia detection in pre-hospital settings.
- The findings support the clinical applicability of advanced deep learning methods in emergency cardiology.
Abstract:
Objectives. Acute myocardial ischemia in the setting of acute coronary syndrome (ACS) may lead to myocardial infarction. Therefore, timely decisions, already in the pre-hospital phase, are crucial to preserving cardiac function as much as possible. Serial electrocardiography, a comparison of the acute electrocardiogram with a previously recorded (reference) ECG of the same patient, aids in identifying ischemia-induced electrocardiographic changes by correcting for interindividual ECG variability. Recently, the combination of deep learning and serial electrocardiography provided promising results in detecting emerging cardiac diseases; thus, the aim of our current study is the application of our novel Advanced Repeated Structuring and Learning Procedure (AdvRS&LP), specifically designed for acute myocardial ischemia detection in the pre-hospital phase by using serial ECG features.Approach. Data belong to the SUBTRACT study, which includes 1425 ECG pairs, 194 (14%) ACS patients, and 1035 (73%) controls. Each ECG pair was characterized by 28 serial features that, with sex and age, constituted the inputs of the AdvRS&LP, an automatic constructive procedure for creating supervised neural networks (NN). We created 100 NNs to compensate for statistical fluctuations due to random data divisions of a limited dataset. We compared the performance of the obtained NNs to a logistic regression (LR) procedure and the Glasgow program (Uni-G) in terms of area-under-the-curve (AUC) of the receiver-operating-characteristic curve, sensitivity (SE), and specificity (SP).Main Results. NNs (median AUC = 83%, median SE = 77%, and median SP = 89%) presented a statistically (Pvalue lower than 0.05) higher testing performance than those presented by LR (median AUC = 80%, median SE = 67%, and median SP = 81%) and by the Uni-G algorithm (median SE = 72% and median SP = 82%).Significance. In conclusion, the positive results underscore the value of serial ECG comparison in ischemia detection, and NNs created by AdvRS&LP seem to be reliable tools in terms of generalization and clinical applicability.
Related Concept Videos
01:29Electrocardiogram
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:28Electrocardiogram Fundamentals
An electrocardiogram (ECG) is a diagnostic tool for identifying cardiac conditions such as arrhythmias, conduction abnormalities, and myocardial ischemia.
Definition
An electrocardiogram (ECG) visualizes the heart's electrical activity by tracing the electrical movement associated with each heartbeat on a graph or monitor. As the heart beats, an electrical wave passes through it, correlating with the cardiac cycle events.
Parts of an ECG
An ECG utilizes electrodes on the skin...
01:19Acute Coronary Syndrome II: Pathophysiology and Clinical Manifestations
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
01:30Acute Coronary Syndrome I: Introduction