Workshops

1st International Workshop on “Artificial Intelligence Methods for Understanding Complex Brain Disorders”

 

Brain disorders include any disabilities that affect the brain and come with different types, including neurological (Alzheimer’s disease, Parkinson’s disease, multiple sclerosis, stroke, epilepsy and seizures, etc.), sleep disorders, mental health disorders (depression, anxiety, etc.), and more. These diseases interfere with activities of daily living, worsening the quality of life and are often associated with social stigma. However, many disorders are preventable if diagnosed early. Therefore, early diagnosis is crucial for allowing patients to maintain their quality of life.

Nowadays, real-world data, i.e., patient data collected from a variety of sources, and Artificial Intelligence (AI)/Machine Learning (ML) have created new ways for personalized diagnosis and prognosis of complex brain disorders. Specifically, health data come in various formats, including actigraphy data, wearable sensors, speech via conversations between the patient and doctor, electronic health records, imaging, i.e., Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), biosignals, i.e., Polysomnography (PSG), questionnaires, and many more. Through the use of AI and ML methods, especially Natural Language Processing (NLP), Speech Processing, and Image Processing, valuable insights can be obtained. While various methods have been developed, approaches regarding interpretability, fusion of the different modalities, uncertainty estimation, or privacy issues remain as major challenges.

This Workshop aims to bring together researchers with expertise relevant to the use of AI/ML methods in the healthcare domain for discussing the latest advances in this emerging field.

This Workshop is also based on the research activities of the MES-CoBraD project.

 

Topics of interest include (but are not limited to):

  • Supervised, unsupervised, and self-supervised learning models
  • Multimodal and cross-modal approaches
  • Explainability/Interpretability methods
  • Uncertainty estimation methods
  • Neurological disorders, including epilepsy, Alzheimer’s disease and other dementias, Parkinson’s disease, multiple sclerosis, and more,
  • Natural Language Processing, Speech Processing, Image Processing
  • Learning from biosignals, speech, transcripts, MRIs, PET images, actigraphy data, questionnaires, and more
  • Large Language Models (LLMs) for creating chatbots in healthcare
  • Zero/one-shot learning
  • Sleep stage classification, sleep disorders
  • Addressing Privacy issues in AI through the use of Federated learning frameworks
  • Fairness and bias of Artificial Intelligence in healthcare
  • Data Augmentation Techniques in healthcare

Organizers:

  • Dimitris Askounis, National Technical University of Athens, Greece
  • Christos Ntanos, National Technical University of Athens, Greece
  • Spiros Mouzakitis, National Technical University of Athens, Greece
  • Evangelos Karakolis, National Technical University of Athens, Greece
  • Elissaios Karageorgiou, Neurological Institute of Athens, Greece
  • Ioannis Stavropoulos, Kings College London, United Kingdom
  • Loukas Ilias, National Technical University of Athens, Greece
  • Sotiris Pelekis, National Technical University of Athens, Greece

 

Important Dates:

Paper submission: May 17, 2024 (Final Extension)
Author notification: June 10, 2024 (updated)
Camera-ready paper submission: June 24, 2024 (updated)