AI & Machine Learning

What is AI?

Artificial Intelligence (AI) refers to computer systems that can perform tasks or solve problems that would normally require human intelligence. These systems may for example do things like recognizing patterns in data, or understanding natural language. Many systems aim to function autonomously and improve over time.

What is Machine Learning and Deep Learning?

Machine Learning (ML) is a subset of AI where algorithms learn to identify patterns in data, and use them to make predictions or decisions. Deep Learning (DL), an advanced subset of ML, accomplishes this using biologically inspired neural networks with multiple layers of artificial ‘neurons’ that are programmed to behave like nerve cells in the brain. DL excels in tasks such as image and time series recognition.

Why Are AI and Machine Learning Important in Neurodegenerative Disease Research?

Neurodegenerative diseases, like Parkinson's disease and Progressive Supranuclear Palsy (PSP), are complex and challenging to diagnose and treat. AI and machine learning offer a promising avenue of research:

Early Detection and Diagnosis: AI algorithms analyse medical images, genetic data, and patient records to identify early signs of diseases, leading to earlier and more accurate diagnoses.
Monitoring Disease Progression: Machine learning models track disease progression by continuously analysing data from various sources, allowing for real-time monitoring and timely interventions.
Personalised Treatment: AI helps develop personalised treatment plans tailored to individual patients, increasing treatment success and improving outcomes.
Research and Drug Development: AI accelerates research by identifying potential biomarkers and therapeutic targets, speeding up the drug discovery process.

How We Apply These Methods

Our lab uses machine learning and deep learning to advance the understanding and treatment of neurodegenerative diseases. We analyse our own extensive datasets, including movement data, oculomotor data, imaging data, and more, to develop predictive models and identify key disease indicators. Collaborating with clinicians, neuroscientists, data scientists, and engineers, we ensure our research benefits patients. Staying up to date with the latest AI and deep learning advancements is crucial, as this field evolves rapidly.

Publications

Patel, S., Goh, V., FitzGerald, J. J., & Antoniades, C.A. (2024). 2D and 3D Deep Learning Models for MRI-based Parkinson’s Disease Classification: A Comprehensive Analysis of Convolutional Kolmogorov-Arnold Networks, Convolutional Neural Networks, and Graph Convolutional Networks. https://doi.org/10.48550/arXiv.2407.17380

Patel, S., Bredemeyer, O., FitzGerald, J. J., & Antoniades, C. A. (2024). Hierarchical Machine Learning Classification of Parkinsonian Disorders using Saccadic Eye Movements: A Development and Validation Study. https://arxiv.org/abs/2407.16063

Sotirakis, C., Su, Z., Brzezicki, M. A., Conway, N., Tarassenko, L., FitzGerald, J. J., & Antoniades, C. A. (2023). Identification of motor progression in Parkinson’s disease using wearable sensors and machine learning. Npj Parkinson’s Disease, 9(1), 1–8. https://doi.org/10.1038/s41531-023-00581-2