Percorrer por autor "Chaabani, Mohamed Khalil"
A mostrar 1 - 3 de 3
Resultados por página
Opções de ordenação
- Binary classification of cardiac pathologies using deep learning: a PTB-XL dataset approachPublication . Chaabani, Mohamed Khalil; Teixeira, João Paulo; Slim , Mohamed AymenCardiovascular diseases, including myocardial infarction, remain among the leading causes of mortality worldwide. Timely and accurate diagnosis is critical for effective treatment but often requires labour-intensive manual analysis of clinical-grade electrocardiograms (ECGs). This dissertation proposes a novel deep learning-based approach for binary classification of cardiac pathologies, using the PTB-XL dataset. The final model architecture integrates EfficientNetB3 for spatial feature extraction and a Linformer block to capture long-range dependencies between ECG leads, the results prove its adaptability for ECG image classification tasks. Extensive experimentation and iterative model development were conducted to reach the final design. Early trials involved exploring different hyperparameter tuning like Optuna and Adam optimizer and a wide range of hyperparameter configurations, including different learning rates, dropout rates, batch sizes, and numbers of Linformer layers. These experiments were critical in finding the optimal combination of parameters that balanced computational efficiency and model accuracy. Comprehensive details of these trials and evaluations are provided in the report. The preprocessing pipeline involves selecting the ECGs and converting them to 11 images (aVR was excluded) each representing a lead, converting RGBA ECG images to RGB format and applying normalization to ensure compatibility with model input requirements. This preprocessing step addresses the unique format of the dataset and prepares it for high-performance neural network training. Initial results from the finalized model architecture have demonstrated promising performance, achieving an AUC (Area Under the Curve) of 85.02% and a F1-score of 78.94%. The achieved results are comparable to recent state-of-the-art models reported on the PTB-XL dataset, which typically range between 85% and 95% AUC for similar binary classification tasks. These results indicate that the model's AUC of 85.02% is promising but on the edge of the current state-of-the-art. These findings indicate strong potential for the system to support clinical decision-making by automating the classification of ECG data. Ongoing research aims to extend the current binary classification framework to multi-class scenarios, further enhancing its clinical applicability. Additionally, efforts are being made to improve the model for faster inference times, enabling real-time ECG analysis and improving its feasibility for deployment in healthcare settings.
- Congestive heart failure detection in ECG using LSTM and CNNPublication . Ribeiro, Luiz; Guerreiro, Nathan; Chaabani, Mohamed Khalil; Luiz, Luiz E.; Lazzaretti, André; Teixeira, João PauloCongestive Heart Failure (CHF) is a chronic condition inm which the heart does not pump blood efficiently. This pathology causes fatigue, dyspnea, oedema, nausea, and memory problems, affecting patients’ quality of life. The causes include coronary artery disease, cardiomyopathy, arterial hypertension, and myocarditis. The diagnosis is usually based on the patient’s medical history, physical exams, echocardiogram, electrocardiogram, and other methods. Aiming to improve diagnostic tools, this study proposes an artificial intelligence model based on deep learning to classify pathological ECG signals indicative of CHF. The selected models were LSTM and CNN. The training was conducted using a personalised dataset created from the public databases BIDMC Congestive Heart Failure and PTB Diagnostic ECG from Physionet. ECG data from 28 individuals aged 22 to 71 were selected, including 14 with severe CHF (NYHA class 3 and 4) and 14 control samples without ECG abnormalities. The database architecture was designed so that the input to the neural networks was raw ECG signals without filtering or feature extraction. The results showed an accuracy of 98.21% for the CNN model and 92.26% for the LSTM model.
- Graphical user interface to acquire ECG using MATLAB and BITalinoPublication . Guerreiro, Nathan; Ribeiro, Luiz; Chaabani, Mohamed Khalil; Luiz, Luiz E.; Dajer, Maria Eugenia; Teixeira, João PauloThis study presents a MATLAB-based graphical user interface (GUI) designed to acquire, process, and visualise electrocardiogram (ECG) signals using the BITalino platform. The interface allows users, including healthcare professionals and researchers, to interactively monitor ECG signals in real-time, providing an accessible and effective tool for cardiac assessment. The system ensures noise reduction and signal clarity using a three-electrode configuration, Butterworth, and notch filters. Results highlight the GUI’s ability to display detailed and comprehensive ECG visualizations, aiding in identifying key ECG characteristics. This work demonstrates the potential for extending the system with machine learning algorithms for automated ECG pattern recognition.