Webinar on Artificial Intelligence in Neurosciences
| Speakers: | Betty Tijms and Arman Eshaghi |
| Recorded: | february 16, 2023 |
Share this
Machine learning in Alzheimer’s disease
Betty Tijms, Associate Professor, Alzheimer Center Amsterdam, Amsterdam UMC
Short Abstract
Alzheimer’s disease is the most common cause of dementia, and there are no cures available yet. One reasons for this is that the brain is notoriously hard to access in patients. This makes difficult to determine precise causes for diagnosis and accurate prognoses. Technical advances now make it possible to gain access to the brain through highly detailed neuroimaging and omics techniques, resulting in large complex datasets. Machine learning provides a way to analyse such datasets, and holds great promise to advance our knowledge on brain disease. I will give examples how different types of machine learning techniques are used in Alzheimer’s disease research, and will discuss if this can be considered ‘artificial intelligence’ or that ‘biological intelligence’ may still be warranted.
Personalizing multiple sclerosis care using next-generation machine learning
Arman Eshaghi, MD, PhD, Department of Neuroinflammation, Queen Square institute of Neurology & Centre for Medical Image Computing, Department of Computer Science, University College London
Short Abstract
Artificial intelligence (AI) is a field of computer science that uses algorithms that can learn complex patterns in large data sets. It has the potential to be used as both a prognostic and a monitoring tool to facilitate the move towards personalized decision-making in ways that would not have been possible before. The accumulation of extensive data from real-world registries, imaging, clinical trials and real-time monitoring tools are precursors for future revolutionary decision-aid systems for doctors. Multiple sclerosis (MS) affects nearly 700,000 people in Europe in which medical imaging plays a fundamental role in diagnosis and monitoring. Recent progress in AI can enable (1) optimized image processing, including MRI analysis, (2) prognostication to identify higher-risk patients for effective treatments, and (3) a better understanding of mechanisms underlying disease progression and identifying treatment targets. I will provide an overview of the recent progress in AI applied to medical image processing and its application to neurological disorders, with a focus on MS. I will discuss the future direction of AI research in MS and other neurodegenerative disorders, its limitations and its potential applications in areas that can be revolutionary but have so far been neglected.