Adriana Leal

Adriana Leal

Auto-generated profile, based on publicly available information

Adriana Leal

Center for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, University of Coimbra, Portugal

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 March 2021 in Scientific Reports
Verified
Journal Article
Open access
PDF file
ALAdriana Leal
Adriana Leal
MPMauro F. Pinto
Mauro F. Pinto
FLFábio Lopes
Fábio Lopes
ABAnna M. Bianchi
Anna M. Bianchi
JHJorge Henriques
Jorge Henriques
CTCésar A. Teixeira
César A. Teixeira
Electrocardiogram (ECG) recordings, lasting hours before epileptic seizures, have been studied in the search for evidence of the existence of a preictal interval that follows a normal ECG trace and precedes the seizure’s clinical manifestation. The preictal interval has not yet been clinically parametrized. Furthermore, the duration of this interval varies for seizures both among patients and from the same patient. In this study, we performed a heart rate variability (HRV) analysis to investigate the discriminative power of the features of HRV in the identification of the preictal interval. HRV information extracted from the linear time and frequency domains as well as from nonlinear dynamics were analysed. We inspected data from 238 temporal lobe seizures recorded from 41 patients with drug-resistant epilepsy from the EPILEPSIAE database. Unsupervised methods were applied to the HRV feature dataset, thus leading to a new perspective in preictal interval characterization. Distinguishable preictal behaviour was exhibited by 41% of the seizures and 90% of the patients. Half of the preictal intervals were identified in the 40 min before seizure onset. The results demonstrate the potential of applying clustering methods to HRV features to deepen the current understanding of the preictal state.

27 April 2023 in Epilepsia Open
Verified
Journal Article
Open access
MPMauro F. Pinto
Mauro F. Pinto
JBJoana Batista
Joana Batista
ALAdriana Leal
Adriana Leal
FLFábio Lopes
Fábio Lopes
AOAna Oliveira
Ana Oliveira
CTCésar A. Teixeira
César A. Teixeira
Many state‐of‐the‐art methods for seizure prediction, using the electroencephalogram, are based on machine learning models that are black boxes, weakening the trust of clinicians in them for high‐risk decisions. Seizure prediction concerns a multidimensional time‐series problem that performs continuous sliding window analysis and classification. In this work, we make a critical review of which explanations increase trust in models' decisions for predicting seizures. We developed three machine learning methodologies to explore their explainability potential. These contain different levels of model transparency: a logistic regression, an ensemble of 15 support vector machines, and an ensemble of three convolutional neural networks. For each methodology, we evaluated quasi‐prospectively the performance in 40 patients (testing data comprised 2055 hours and 104 seizures). We selected patients with good and poor performance to explain the models' decisions. Then, with grounded theory, we evaluated how these explanations helped specialists (data scientists and clinicians working in epilepsy) to understand the obtained model dynamics. We obtained four lessons for better communication between data scientists and clinicians. We found that the goal of explainability is not to explain the system's decisions but to improve the system itself. Model transparency is not the most significant factor in explaining a model decision for seizure prediction. Even when using intuitive and state‐of‐the‐art features, it is hard to understand brain dynamics and their relationship with the developed models. We achieve an increase in understanding by developing, in parallel, several systems that explicitly deal with signal dynamics changes that help develop a complete problem formulation.

16 January 2023 in Scientific Reports
Verified
Journal Article
Open access
PDF file
ALAdriana Leal
Adriana Leal
JCJuliana Curty
Juliana Curty
FLFábio Lopes
Fábio Lopes
MPMauro F. Pinto
Mauro F. Pinto
AOAna Oliveira
Ana Oliveira
CTCésar A. Teixeira
César A. Teixeira
Typical seizure prediction models aim at discriminating interictal brain activity from pre-seizure electrographic patterns. Given the lack of a preictal clinical definition, a fixed interval is widely used to develop these models. Recent studies reporting preictal interval selection among a range of fixed intervals show inter- and intra-patient preictal interval variability, possibly reflecting the heterogeneity of the seizure generation process. Obtaining accurate labels of the preictal interval can be used to train supervised prediction models and, hence, avoid setting a fixed preictal interval for all seizures within the same patient. Unsupervised learning methods hold great promise for exploring preictal alterations on a seizure-specific scale. Multivariate and univariate linear and nonlinear features were extracted from scalp electroencephalography (EEG) signals collected from 41 patients with drug-resistant epilepsy undergoing presurgical monitoring. Nonlinear dimensionality reduction was performed for each group of features and each of the 226 seizures. We applied different clustering methods in searching for preictal clusters located until 2 h before the seizure onset. We identified preictal patterns in 90% of patients and 51% of the visually inspected seizures. The preictal clusters manifested a seizure-specific profile with varying duration (22.9 ± 21.0 min) and starting time before seizure onset (47.6 ± 27.3 min). Searching for preictal patterns on the EEG trace using unsupervised methods showed that it is possible to identify seizure-specific preictal signatures for some patients and some seizures within the same patient.

1 July 2018 in Biomedical Signal Processing and Control
Verified
Journal Article
Open access
ALAdriana Leal
Adriana Leal
DNDiogo Nunes
Diogo Nunes
RCRicardo Couceiro
Ricardo Couceiro
JHJorge Henriques
Jorge Henriques
PCPaulo Carvalho
Paulo Carvalho
CTCesar Teixeira
Cesar Teixeira

25 February 2022 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
FLFabio Lopes
Fabio Lopes
ALAdriana Leal
Adriana Leal
JMJúlio Medeiros
Júlio Medeiros
MPMauro F. Pinto
Mauro F. Pinto
Antonio DouradoAntonio Dourado
Antonio Dourado
CTCesar Teixeira
Cesar Teixeira
Objective: Independent component analysis (ICA) is commonly used to remove noisy artifacts from multi-channel scalp electroencephalogram (EEG) signals. ICA decomposes EEG into different independent components (ICs) and then, experts remove the noisy ones. This process is highly time-consuming and experts are not always available. To surpass this drawback, research is going on to develop models to automatically conduct IC classification. Current state-of-the-art models use power spectrum densities (PSDs) and topoplots to classify ICs. The performance of these methods may be limited by disregarding the IC time-series that would contribute to fully simulate the visual inspection performed by experts. Methods: We present a novel ensemble deep neural network that combines time-series, PSDs, and topoplots to classify ICs. Moreover, we study the ability to use our model in transfer learning approaches. Results: Experimental results showed that using time-series improves IC classification. Results also indicated that transfer learning obtained higher performance than simply training a new model from scratch. Conclusion: Researchers should develop IC classifiers using the three sources of information. Moreover, transfer learning approaches should be considered when producing new deep learning models. Significance: This work improves IC classification, enhancing the automatic removal of EEG artifacts. Additionally, since labelled ICs are generally not publicly available, the possibility of using our model in transfer learning studies may motivate other researchers to develop their own classifiers.

17 March 2017 in Journal of Adhesion Science and Technology
Verified
Journal Article
Closed access
ALAdriana Leal
Adriana Leal
Ceci Nunes CarvalhoCeci Nunes Carvalho
Ceci Nunes Carvalho
EMEtevaldo Maia-Filho
Etevaldo Maia-Filho
Valério Monteiro-NetoValério Monteiro-Neto
Valério Monteiro-Neto
MCMonique Carmo
Monique Carmo
Jose BauerJose Bauer
Jose Bauer
This study evaluated the effect of airborne-particle abrasion with niobium phosphate bioglass (NbG) microparticles on the bond strength (μTBS) and longevity of an adhesive system to different dentin substrates. In this study, 18 Caries-free molars were used, of which 12 were microbiologically processed for caries induction. The dentin surfaces were evaluated in three groups: (1) Control – Healthy Dentin; (2) Partial removal of carious tissue; (3) complete removal of carious tissue. Half the teeth in each group were submitted to airborne-particle abrasion with NbG microparticles (15 s/1 cm/5 bar). After this, the adhesive Clearfil S3 was applied and composite buildups were constructed incrementally; and specimens were longitudinally sectioned to obtain bonded sticks (1.0 mm2) to be tested in tension (0.5 mm/min) immediately or after 6 months of storage in water. The fracture patterns were evaluated by stereomicroscope (40×) and then by scanning electron microscopy. The data were analyzed by the Kruskal-Wallis (post hoc Dunn) and Mann-Whitney tests (α = 0.05). Healthy dentin showed the highest bond strength (μTBS). Airborne-particle abrasion with NbG increased the μTBS values in the Group with complete caries removal. The bond strength values in the 24-h period were higher than those at 6 months. In the majority of the specimens the fracture mode was adhesive/mixed. The authors concluded that airborne-particle abrasion on dentin with NbG particles increased the μTBS in the group in which carious dentin was completely removed.