What is the clinical evidence from this study?

Study design: Observational. Population: Myocardial Infarction (n=290). Intervention: CNN-GRU deep learning model. Primary outcome: Myocardial infarction detection accuracy.

November 4, 2025BMC Medical Informatics and Decision Making2 citationsOpen Access

Optimizing myocardial infarction detection: a hybrid CNN-GRU deep learning approach

ZAZahra Aghababaei LTLeili Tapak MRMahdi Rasoulinia

Key Result

The hybrid CNN-GRU deep learning model achieved 99.73% accuracy, 99.75% sensitivity, and 99.66% specificity for detecting myocardial infarction using lead II alone.

Study Design

Type

Observational (n=290)

Structured PICO

Does a hybrid CNN-GRU deep learning model accurately detect myocardial infarction using ECG signals?

Population

290 individuals (27.9% female) aged 17 to 87 years from the PTB database, providing 56,354 ECG segments to train and validate a diagnostic deep learning model for myocardial infarction.

Intervention

Hybrid CNN-GRU deep learning model using 15-lead ECG or lead II alone

Comparator

CNN model alone

Outcome

Area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, Macro Average, and Weighted Average for MI detectionsurrogate

A hybrid CNN-GRU deep learning model using ECG signals achieved over 99% accuracy and sensitivity for detecting myocardial infarction, offering a highly precise automated diagnostic tool.

Limitations

Focuses on classifying 20-second segments of ECG signals, which may overlook contextual information in longer recordings.
Imbalance between myocardial infarction and healthy cases in the dataset.
Lack of evaluation of the model's generalizability across different ECG acquisition devices and patient demographics due to reliance on a single dataset.
No specific overfitting prevention techniques (such as dropout, regularization, or early stopping) were employed during training.

Abstract

BACKGROUND: Myocardial infarction (MI) is a life-threatening condition caused by sudden interruption of blood supply to the heart. Electrocardiogram (ECG) is the primary tool for MI diagnosis, but interpretation challenges exist. This study aimed to optimize MI detection by developing a hybrid CNN-GRU Deep Learning model (DLM) based on ECG as a diagnostic support tool. METHODS: This retrospective diagnostic study included a total of 56,354 ECGs, comprising 41,871 from patients diagnosed with (MI) and 14,474 from healthy patients. Each ECG record consisted of a 20-second 15-lead recording per individual, sampled at 1000 Hz. The CNN-GRU model was trained on 85% of these ECGs and validated on the remaining 15%. The CNN-GRU model was executed on the pre-processed data using the Pan-Tompkins algorithm obtained from the PhysioNet website (PTB Diagnostic ECG Database), and all recordings were labelled by expert cardiologists. We examined a new model for classifying ECG heartbeats and found that it can compete with advanced models. The performance of the DLM was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, Macro Average, and Weighted Average. RESULTS: The area under the receiver operating characteristic curve (AUC) of the CNN-GRU model for MI detection was close to one. The CNN-GRU model achieved excellent performance with 15 leads (ACC = 99.43%, sensitivity = 99.71%, specificity = 98.59%). Using lead II alone, performance improved slightly (ACC = 99.73%, sensitivity = 99.75%, specificity = 99.66%). The high AUC and other metrics indicate strong diagnostic ability. Based on the reported results, the CNN-GRU model using lead II was the best model. CONCLUSIONS: The findings suggest that the proposed model can support clinical decision-making and guide future research in cardiovascular medicine.

AIに質問

Bookmark

View Full Paper