Teses de Mestrado ESTiG
Permanent URI for this community
Browse
Browsing Teses de Mestrado ESTiG by Field of Science and Technology (FOS) "Ciências Médicas"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- 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.
- Removal of metformin from aquatic matrices using cork-based adsorbentsPublication . Morizaki, Gabrielle Tokawa; Queiroz , Ana Maria; Ribeiro , António; Brito , Paulo; Gomes, Maria Carolina SérgiMetformin is a widely prescribed pharmaceutical for the treatment of type II diabetes. It is classified as an emerging micropollutant due to its incomplete metabolism in the human body and high prescription rates, especially for preventing chronic diseases. Consequently, it is frequently detected in aquatic environments. This study aimed to evaluate the efficiency of metformin removal from aqueous matrices through adsorption using activated carbons produced from cork waste. Adsorbents were prepared via carbonization and chemical activation using potassium hydroxide (KOH). They were characterized in terms of carbonization yield, moisture and ash content, point of zero charge (pHPZC), surface acidity/basicity, and Fourier-transform infrared spectroscopy (FTIR). Metformin quantification was performed using high-performance liquid chromatography with diode array detection (HPLC-DAD). Adsorption studies included removal efficiency, adsorption kinetics, activation energy estimation, and optimization of operational parameters. Among the parameters investigated, pH had the most significant influence, with higher removal observed under alkaline conditions for both materials. For the carbonized carbon (CC), the pseudo-second-order and Elovich kinetic models provided the best fit, suggesting a chemisorption-controlled process. In equilibrium studies, the Freundlich model best represented experimental adsorption behavior using CC adsorbent, while the Langmuir model was more appropriate when chemically activated carbon (CQ) was used, which exhibited a maximum removal efficiency of 99% at pH 11. These findings demonstrate the high adsorption performance of cork-based activated carbons, particularly those chemically activated. This highlights their potential as sustainable materials for removing metformin from aqueous systems and promoting the valorization of industrial by-products in water treatment applications.