Robust feature learning method for epileptic seizures prediction based on long-term EEG signals

Baghdadi, Asma; Fourati, Rahma; Aribi, Yassine; Siarry, Patrick; Alimi, Adel M.

doi:10.1109/ijcnn48605.2020.9207070

Cited by 11 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Decision support: Reinforcement learning for optimizing mechanical ventilation [135], sedation dosing [136] and smart pump drug dosing [137] given the patient's state. Alarm/event detection: CNNs on raw waveform data to detect arrythmias [138], seizures [139] and respiratory events [140] using domain priors.…”

Section: Intelligent Medical Devicesmentioning

confidence: 99%

AI and the next medical revolution: deep learning’s uncharted healthcare promise

L B,

Kotei

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

Deep learning has shown tremendous potential for transforming healthcare by enabling more accurate diagnoses, improved treatment planning and better patient outcome predictions. In this comprehensive survey, we provide a detailed overview of the state-of-the-art deep learning techniques and their applications across the healthcare ecosystem. We first introduce the fundamentals of deep learning and discuss its key advantages compared to traditional machine learning approaches. We then present an in-depth review of major applications of deep learning in medical imaging, electronic health record analysis, genomics, medical robotics and other domains. For each application, we summarize key advancements, outline the technical details of state-of-the-art methods, discuss challenges and limitations and highlight promising directions for future work. We examine cross-cutting challenges in deploying deep learning in clinical settings, including interpretability, bias and data scarcity. We conclude by proposing a roadmap to accelerate the translation and adoption of high-impact healthcare applications of deep learning. Overall, this survey provides a comprehensive reference for researchers and practitioners working at the intersection of deep learning and healthcare.

show abstract

Section: Intelligent Medical Devicesmentioning

confidence: 99%

AI and the next medical revolution: deep learning’s uncharted healthcare promise

L B,

Kotei

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…The latter does not allow us to validate the model for seizure type classification due to the lack of seizure type labeled data. Only the start and the end of each onset is indicated for whole data in CHB-MIT, making it only usable for seizure detction or for seizure prediction as done in our previous paper [37].…”

Section: B Evaluation On Chb-mit For Ictal Vs Non-ictal Classificationmentioning

confidence: 99%

A channel-wise attention-based representation learning method for epileptic seizure detection and type classification

Baghdadi¹,

Fourati²,

Aribi³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

<div>Epilepsy affect almost 1% of the worldwide population. An early diagnosis of seizure types is a patient-dependent process which is crucial for the treatment selection process. The selection of the proper treatment relies on the correct identification of seizures type. As such, identifying the seizure type has the biggest immediate influence on therapy than the seizure detection, reducing the neurologist’s efforts when reading and detecting seizures in EEG recordings. Most of the existing seizure detection and classification methods are conceptualized following the patient-dependent schema thus fail to perform well with unknown cases. Our work focuses on patient-independent schema for seizure type classification and pays more attention to the explainability of the underlying attention mechanism of our method. Using a channel-wise attention mechanism, a quantification of the EEG channels contribution is enabled. Therefore, results become more interpretable and a visualization of brain lobes contribution by seizure types is allowed. We evaluate our model for seizure detection and type classification on CHB-MIT and the recently released TUH EEG Seizure, respectively. Our model is able to classify 8 seizure types with an accuracy of 98.41%, directly from raw EEG data without any preprocessing. A case study showed a high correlation between the neurological baselines and the interpretable results of our model.</div>

show abstract

A Mutual Information-Based Many-Objective Optimization Method for EEG Channel Selection in the Epileptic Seizure Prediction Task

Kouka,

Fourati,

Baghdadi

et al. 2024

Cogn Comput

View full text Add to dashboard Cite

Robust feature learning method for epileptic seizures prediction based on long-term EEG signals

Cited by 11 publications

References 26 publications

AI and the next medical revolution: deep learning’s uncharted healthcare promise

AI and the next medical revolution: deep learning’s uncharted healthcare promise

A channel-wise attention-based representation learning method for epileptic seizure detection and type classification

A Mutual Information-Based Many-Objective Optimization Method for EEG Channel Selection in the Epileptic Seizure Prediction Task

Contact Info

Product

Resources

About