Bio
Zeena Shawa is PhD student in the i4Health Medical Imaging CDT programme. She is part of the Progression of Neurodegenerative Diseases (POND) Group in the Centre for Medical Image Computing (CMIC) and supervised by Dr. Neil Oxtoby and Dr. Rimona Weil. Her PhD project aims at understanding Parkinson’s disease progression using machine learning approaches developed within POND, with a focus on medical imaging data. The insights obtained from this can aid in understanding disease mechanisms, identifying biomarkers associated with disease progression and thus potentially providing targets for therapeutic development.
Zeena graduated in 2020 from King’s College London with a BEng of Biomedical Engineering and in 2021 from University College London with a MRes in Medical Imaging. She is also a UCL Institute of Healthcare Engineering 2021 Impact Fellow, receiving formal training and mentoring in public engagement. Zeena's interests lie in fully utilizing the information in medical images to further understand neurological diseases, predict disease progression and potentially stratify individuals. She is also interested in learning more about transfer learning and microstructure imaging.
Research interests
Although Parkinson’s disease (PD) is the 2nd most common neurodegenerative disease, we have a limited understanding of disease progression. This is because PD is highly heterogeneous, presenting with different symptoms, sequence, and timing of those. A key symptom with no treatment is dementia — within 10 years of diagnosis, 50% of PD patients develop dementia. There are currently no robust clinical nor neuroimaging measures that reliably predict which patients are at greatest risk. Therefore, there is particular interest in identifying typical PD progression patterns to help identify patients at risk of developing dementia.
The project uses a statistical modelling and machine learning method to fuse data from multiple sources, such as tests and brain scans, into quantitative patterns of disease progression. Such patterns may improve our understanding of disease mechanisms and pathophysiology. Additionally, they may impact clinical trial recruitment and treatment development, which would help PD patients as current treatments have limited efficacy and there is no cure for PD.
We utilize data (both clinical and neuroimaging) from large databases to use with our models to learn the progression of PD. By incorporating more advanced neuroimaging analyses, such as combining different types of MRI scans, or building a more robust model of the human brain using scans from other disease areas, a more comprehensive model of PD progression can be built. Such a model can be used to predict symptom onset or future disease progression risk, which could lead to a better understanding at the individual-level for patients, carers, and clinicians.