Developing network methodologies for disease classification
Lead Research Organisation:
University of Edinburgh
Department Name: Centre of Population Health Sciences
Abstract
Theme (1)
The physiological network is an emerging concept in health data science. Its aim is to integrate a wide range of health-related data across the body to establish the quantification of a person's functional interdependencies, to provide important insights and nuanced classification strategies of different bodily states [1]. In this theme, I will pursue the integration of a physiological network approach with deep learning classification for large health datasets, focusing - at least in the first instance - on the UK Biobank. With this, I aim to develop critical novel methodologies for the advancement of understanding and classification of health and disease.
Theme (2)
It is of critical societal importance to develop methods for the detection of Alzheimer's Disease (AD) and other dementias in their early stages in the general population. AD is commonly known as a disconnection syndrome, whereby mass neuronal death leads to the disintegration of the brain's functional architecture [2]. I have developed novel complex network methodologies which have been developed and applied in pilot electroencephalography (EEG) data, finding abnormal topological and temporal functional patterns in patients with AD. I aim to build on this promising work, developing, refining and applying these methodologies to larger datasets of structural and functional imaging data (e.g., UK Biobank), building on my existing collaborations in the Alzheimer Scotland Dementia Research Centre. The information gathered will be used to analyse and classify AD in the general population.
References:
[1] Bashan, A., Bartsch, R.P., Kantelhardt, J.W., Havlin, S., Ivanov, P.C., Network Physiology reveals relations between network topology and physiological function. Nature Comms., 3: 702 (2011).
[2] Delbeuck, X., Van der Linden, M., Collette, F., Alzheimer's disease as a disconnection syndrome?, Neuropsychology Review, 13(2): 79-92 (2003).
[3] Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P., Geometric Deep Learning: going beyond euclidean data, IEEE Signal Processing Magazine, 34(4): 18-42 (2017).
[4] Smith, K., Escudero, J., The complex hierarchical topology of EEG functional connectivity, J. Neurosci. Methods, 276: 1-12 (2017).
[5] Smith, K., Ricaud, B., Shahid, N., Rhodes, S., Starr, J., Ibanez, A., Parra, M.A., Escudero, J., Vandergheynst, P., Locating temporal functional dynamics of visual short-term memory binding using graph modular Dirichlet energy, Scientific Reports, 7: 42013 (2017).
The physiological network is an emerging concept in health data science. Its aim is to integrate a wide range of health-related data across the body to establish the quantification of a person's functional interdependencies, to provide important insights and nuanced classification strategies of different bodily states [1]. In this theme, I will pursue the integration of a physiological network approach with deep learning classification for large health datasets, focusing - at least in the first instance - on the UK Biobank. With this, I aim to develop critical novel methodologies for the advancement of understanding and classification of health and disease.
Theme (2)
It is of critical societal importance to develop methods for the detection of Alzheimer's Disease (AD) and other dementias in their early stages in the general population. AD is commonly known as a disconnection syndrome, whereby mass neuronal death leads to the disintegration of the brain's functional architecture [2]. I have developed novel complex network methodologies which have been developed and applied in pilot electroencephalography (EEG) data, finding abnormal topological and temporal functional patterns in patients with AD. I aim to build on this promising work, developing, refining and applying these methodologies to larger datasets of structural and functional imaging data (e.g., UK Biobank), building on my existing collaborations in the Alzheimer Scotland Dementia Research Centre. The information gathered will be used to analyse and classify AD in the general population.
References:
[1] Bashan, A., Bartsch, R.P., Kantelhardt, J.W., Havlin, S., Ivanov, P.C., Network Physiology reveals relations between network topology and physiological function. Nature Comms., 3: 702 (2011).
[2] Delbeuck, X., Van der Linden, M., Collette, F., Alzheimer's disease as a disconnection syndrome?, Neuropsychology Review, 13(2): 79-92 (2003).
[3] Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P., Geometric Deep Learning: going beyond euclidean data, IEEE Signal Processing Magazine, 34(4): 18-42 (2017).
[4] Smith, K., Escudero, J., The complex hierarchical topology of EEG functional connectivity, J. Neurosci. Methods, 276: 1-12 (2017).
[5] Smith, K., Ricaud, B., Shahid, N., Rhodes, S., Starr, J., Ibanez, A., Parra, M.A., Escudero, J., Vandergheynst, P., Locating temporal functional dynamics of visual short-term memory binding using graph modular Dirichlet energy, Scientific Reports, 7: 42013 (2017).
Technical Summary
For objective (1) I will develop an integrated framework of complex networks and convolutional neural networks for health data which will build upon geometric deep learning [3], building established connections with Prof Pierre Vandergheynst of the École Polytechnique Fédérale de Lausanne (EPFL). Complex physiological networks will be derived from the multidimensional, complex datasets in the UK Biobank, which will then be utilised in this framework to gather important insights into health and disease and develop enhanced large-scale classification strategies.
For objective (2) I will build on pilot work (unpublished) which applies novel complex network methods [4,5] to detect AD from task-related EEG signals. This will be extended for the following:
(i) refinement and continued development of theoretical approaches to analyse functional connectivity
(ii) adaptations for application to high spatial resolution fMRI and MRI data
(iii) applied to resting-state fMRI in large datasets such as the Lothian Birth Cohort and UK Biobank
(iv) employment of powerful classification and regression approaches such as support vector machines
Such methods are also of great relevance to an array of different pathologies, including other forms of dementia, epilepsy, Parkinson's disease and schizophrenia, to which the strategy proposed will be generalised.
This project is in alignment with HDR UK priorities, developing novel data analyses and classification strategies for key national health problems, establishing national leadership, developing international collaborations, and strengthening interdisciplinary skills.
References: see Summary
For objective (2) I will build on pilot work (unpublished) which applies novel complex network methods [4,5] to detect AD from task-related EEG signals. This will be extended for the following:
(i) refinement and continued development of theoretical approaches to analyse functional connectivity
(ii) adaptations for application to high spatial resolution fMRI and MRI data
(iii) applied to resting-state fMRI in large datasets such as the Lothian Birth Cohort and UK Biobank
(iv) employment of powerful classification and regression approaches such as support vector machines
Such methods are also of great relevance to an array of different pathologies, including other forms of dementia, epilepsy, Parkinson's disease and schizophrenia, to which the strategy proposed will be generalised.
This project is in alignment with HDR UK priorities, developing novel data analyses and classification strategies for key national health problems, establishing national leadership, developing international collaborations, and strengthening interdisciplinary skills.
References: see Summary
Publications
Blesa M
(2021)
Hierarchical Complexity of the Macro-Scale Neonatal Brain.
in Cerebral cortex (New York, N.Y. : 1991)
Clark RA
(2022)
Robust Assessment of EEG Connectivity Patterns in Mild Cognitive Impairment and Alzheimer's Disease.
in Frontiers in neuroimaging
Quintero-Zea A
(2018)
Phenotyping Ex-Combatants From EEG Scalp Connectivity
in IEEE Access
Smith K
(2019)
Hierarchical complexity of the adult human structural connectome.
in NeuroImage
Smith K
(2019)
Graph-Variate Signal Analysis
in IEEE Transactions on Signal Processing
Smith K
(2022)
Abnormal Functional Hierarchies of EEG Networks in Familial and Sporadic Prodromal Alzheimer's Disease During Visual Short-Term Memory Binding
in Frontiers in Neuroimaging
Smith KM
(2019)
On neighbourhood degree sequences of complex networks.
in Scientific reports
Smith KM
(2021)
Explaining the emergence of complex networks through log-normal fitness in a Euclidean node similarity space.
in Scientific reports
Smith KM
(2020)
Normalised degree variance.
in Applied network science
Tan C
(2019)
Gas-Liquid Flow Pattern Analysis Based on Graph Connectivity and Graph-Variate Dynamic Connectivity of ERT
in IEEE Transactions on Instrumentation and Measurement
Valdés Hernández MDC
(2021)
Brain network reorganisation and spatial lesion distribution in systemic lupus erythematosus.
in Lupus
Zhang H
(2021)
Benchmarking network-based gene prioritization methods for cerebral small vessel disease.
in Briefings in bioinformatics
Description | Analysing brain MRI in health and disease using novel network science methods |
Organisation | University of Edinburgh |
Department | Centre for Clinical Brain Sciences (CCBS) |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | I am leading a research collaboration into the application of novel network methods, developed by myself, to Brain MRI data in health and disease. Future work will look at data from the Lothian Birth Cohort and the UK BioBank to explore links between these analyses and ageing/disease. |
Collaborator Contribution | A pilot study was undergone using brain MRI structural connectome data provided by Dr Mark E Bastin of the Centre for Clinical Brain Sciences. Analyses were conducted by myself and interpreted primarily by Dr. Simon R. Cox of the Centre for Cognitive Ageing and Cognitive Epidemiology and Dr. Maria Valdes-Hernandez of the UK Dementia Research Institute. Future work will look at data from the Lothian Birth Cohort and the UK BioBank to explore links between these analyses and ageing/disease. |
Impact | A pilot study on healthy adult brain MRI has been published in NeuroImage (see publications). This is a multi-disciplinary collaboration between fields of medical imaging, cognitive ageing and epidemiology, computer science and health data science. |
Start Year | 2018 |
Description | Analysing brain MRI in health and disease using novel network science methods |
Organisation | University of Edinburgh |
Department | MRC Centre for Cognitive Ageing and Cognitive Epidemiology |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | I am leading a research collaboration into the application of novel network methods, developed by myself, to Brain MRI data in health and disease. Future work will look at data from the Lothian Birth Cohort and the UK BioBank to explore links between these analyses and ageing/disease. |
Collaborator Contribution | A pilot study was undergone using brain MRI structural connectome data provided by Dr Mark E Bastin of the Centre for Clinical Brain Sciences. Analyses were conducted by myself and interpreted primarily by Dr. Simon R. Cox of the Centre for Cognitive Ageing and Cognitive Epidemiology and Dr. Maria Valdes-Hernandez of the UK Dementia Research Institute. Future work will look at data from the Lothian Birth Cohort and the UK BioBank to explore links between these analyses and ageing/disease. |
Impact | A pilot study on healthy adult brain MRI has been published in NeuroImage (see publications). This is a multi-disciplinary collaboration between fields of medical imaging, cognitive ageing and epidemiology, computer science and health data science. |
Start Year | 2018 |
Description | Analysing brain MRI in health and disease using novel network science methods |
Organisation | University of Edinburgh |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | I am leading a research collaboration into the application of novel network methods, developed by myself, to Brain MRI data in health and disease. Future work will look at data from the Lothian Birth Cohort and the UK BioBank to explore links between these analyses and ageing/disease. |
Collaborator Contribution | A pilot study was undergone using brain MRI structural connectome data provided by Dr Mark E Bastin of the Centre for Clinical Brain Sciences. Analyses were conducted by myself and interpreted primarily by Dr. Simon R. Cox of the Centre for Cognitive Ageing and Cognitive Epidemiology and Dr. Maria Valdes-Hernandez of the UK Dementia Research Institute. Future work will look at data from the Lothian Birth Cohort and the UK BioBank to explore links between these analyses and ageing/disease. |
Impact | A pilot study on healthy adult brain MRI has been published in NeuroImage (see publications). This is a multi-disciplinary collaboration between fields of medical imaging, cognitive ageing and epidemiology, computer science and health data science. |
Start Year | 2018 |
Description | Hierachical complexity of post-synaptic density protein networks |
Organisation | University of Edinburgh |
Department | Informatics Forum |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Applying methods of hierarchical complexity to understand the topology of protein interaction networks in the post-synaptic density of the brain. |
Collaborator Contribution | Provided the protein networkdata, undertaking genetic associations and interpretation of results. |
Impact | None as of yet. |
Start Year | 2018 |
Description | Hierarchical complexity of the neonatal brain |
Organisation | University of Edinburgh |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | I helped generate clinically relevant hypotheses, and tested these implementing novel methodologies. I also helped write a conference abstract and a submitted journal manuscript. |
Collaborator Contribution | My partners collected, processed and provided MRI structural imaging data for this research and helped with the study design and writing manuscripts. |
Impact | Abstract accepted to the ISMRM 2020, the foremost conference in clinical medical imaging, in Sydney. The full study, entitled 'Hierarchical complexity of the macroscale neonatal brain' has been submitted for consideration as a journal manuscript and is available as a preprint here: https://doi.org/10.1101/2020.01.16.909150. |
Start Year | 2019 |
Description | Resilience and evolvability of protein interaction networks |
Organisation | Northeastern University - Boston |
Country | United States |
Sector | Academic/University |
PI Contribution | I helped to design the study, provided supervision of methodology and have contributed to the writing of a journal manuscript. |
Collaborator Contribution | Partners helped design the study, collect and analyse the data and write the manuscript. |
Impact | A summer school abstract has been published here: https://www.santafe.edu/engage/learn/resources/2019-csss-proceedings. A journal manuscript is under preparation. |
Start Year | 2019 |
Description | Resilience and evolvability of protein interaction networks |
Organisation | Santa Fe Institute |
Country | United States |
Sector | Academic/University |
PI Contribution | I helped to design the study, provided supervision of methodology and have contributed to the writing of a journal manuscript. |
Collaborator Contribution | Partners helped design the study, collect and analyse the data and write the manuscript. |
Impact | A summer school abstract has been published here: https://www.santafe.edu/engage/learn/resources/2019-csss-proceedings. A journal manuscript is under preparation. |
Start Year | 2019 |
Description | Resilience and evolvability of protein interaction networks |
Organisation | University of Münster |
Country | Germany |
Sector | Academic/University |
PI Contribution | I helped to design the study, provided supervision of methodology and have contributed to the writing of a journal manuscript. |
Collaborator Contribution | Partners helped design the study, collect and analyse the data and write the manuscript. |
Impact | A summer school abstract has been published here: https://www.santafe.edu/engage/learn/resources/2019-csss-proceedings. A journal manuscript is under preparation. |
Start Year | 2019 |
Description | Popular science article |
Form Of Engagement Activity | A magazine, newsletter or online publication |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | I wrote a two page article on mathematics for a postgraduate community newsletter at the University of Munster called the Eyebrow. |
Year(s) Of Engagement Activity | 2020 |
URL | https://eyebrowevolution.wordpress.com |
Description | School visit (Coatbridge) |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | Regional |
Primary Audience | Schools |
Results and Impact | A presentation with colleagues described career trajectories and a collaborative research project to S4 school pupils in biology to help them deciding what subjects to take and understand different career trajectories in STEM subjects. |
Year(s) Of Engagement Activity | 2020 |
URL | https://culturenl.co.uk/venue-hire/coatbridge-high-school/ |