Course Syllabus
Obiettivi formativi
The main objective of the course is to provide the students with basic understanding of neurological
diseases, introducing the main clinical features, as well as their functional neurophysiological
correlates.
Further aim will be to provide an introduction to the basics of Brain Computer Interfaces (BCI)
principally based on oscillatory EEG activity, but also on transient EP and ERP signals. The course
will introduce the main methods for acquiring and processing electrophysiological data allowing the
decoding of brain activity in real time for converting it into BCI control signals.
Programma esteso
The students are expected to:
- Acquire basic knowledge on the major neurological disease and their clinical features
- Know the basic neural substrates of neurophysiological signals, and their alterations
- Identify the main medical applications of AI algorithms in neurological diseases
- Acquire knowledge on the available AI tools to promote early diagnosis of neurodegenerative diseases
- Explore basic principles for applications to drug discovery
- Evaluate potential applications for neuro-rehabilitative interventions
- Acquire basic knowledge of the various oscillatory and transient electrical signals of the brain
- Know which electrical marker might be more appropriate for assessing minimally conscious state, for 'mind reading', or robotic control
- Explore available techniques for EEG-based BCI applications for motor control and augmented communication.
Metodi didattici
Frontal lessons with slides and audio/video presentations.
(a) nature of teaching: dispensing and interactive
(b) type of teaching activity: lecture
(c) hours possibly delivered remotely = 20%
Modalità di verifica dell'apprendimento
Oral colloquim
Testi di riferimento
All relevant materials and slides will be uploaded on Ariel site after each lesson
AI applied to Neurological Sciences and Brain-computer Interfaces (a.a. 2024/25)
https://myariel.unimi.it/course/view.php?id=4150
Sustainable Development Goals
Learning objectives
The aim of this course is to provide an introduction to the basics of Brain Computer Interfaces (BCI) principally based on oscillatory EEG activity, but also on transient EP and ERP signals. The course will introduce the main methods for acquiring and processing electrophysiological data allowing the decoding of brain activity in real time for converting it into BCI control signals.
Contents
• The Electro-ionic origins of brain electrical potentials
• Electrophysiological recording and analysis. EEG rhythms, Evoked Potentials (steady state and pattern onset), Event-related Potentials. Wavelet analysis.
• Biofeedback and Neurofeedback. Eye-movement BCI systems.
• Brain Computer Interface systems.
• Electrical markers for BCI: (P300 and N400, SSVEP, slow cortical potentials, motor and sensorimotor rhythms). Motor imagery. OpenVibe for BCI
• Classification and machine learning algorithms for mind reading
• Examples of EEG/EP based BCI applications
Detailed program
AI applied to Neurological Sciences and Brain-computer Interfaces [M-PSI/02, MED/26]
Aim of this course is to provide the theoretical basis aimed at fostering an interdisciplinary and integrative interaction between clinicians, AI algorithm designers, medical-application-specific “chip scientists”. The interaction between AI and cognitive neuroscience/neuropsychology will be discussed, with a focus on how information derived from neurophysiological data can guide AI to manage different final effectors through brain computer interfaces (BCI). Furthermore, the use of AI to advance the knowledge on brain functioning with the application of machine learning on brain signals will be discussed.
The changing landscape of medical education, with specific focus on Neurology
AI-assisted Detection & Diagnosis- Neuroimaging
AI-assisted Neurorehabilitation
Disease Management - Health Analytics
Neurology and Aging
AI-assisted neurotherapeutics- drug discovery in neurological disorders
Brain computer interfaces (non invasive, semi-invasive, invasive, closed loop, open loop);
Adaptive Interfaces
Using Neural Measures to Predict Real-World Outcomes;
Social/Affective neuroscience for human-machine interaction;
Usability of BCIs in cognitive neuroscience;
BCI in cognitive and neurological rehabilitation
Assessment methods
Oral colloquim
Sustainable Development Goals
Staff
-
Alice Mado Proverbio
