AI gets real: using routine clinical data and Artificial Intelligence to predict worsening of Multiple Sclerosis despite treatment (AIMS)
Lead Research Organisation:
University of Nottingham
Department Name: School of Medicine
Abstract
Multiple sclerosis (MS) can be a severely disabling disease. Widespread use of MRI and revisions to MS diagnosis have enabled earlier identification and considerable progress in developing therapies for MS. Access to the treatments in MS has been improved recently, but although most people with relapsing MS can benefit from them and outcomes are improving as a result, no single treatment is right for everybody. Some people with MS will relapse, and over the long term will gather psychical and cognitive disability. Despite progress in assessing response to treatments, individual prediction of MS outcomes over the long-term is still inaccurate; the need for information on individualised long-term prognosis for MS patients' forecasting is frequently unmet.
A wealth of clinical and MRI data from patients with MS are acquired every year in clinical practice, but only part of these data are used for clinical decision making. MRI is paramount in MS diagnosis and monitoring, but most often the only feature of clinical use are the MS lesions. However, the structure of MS brains visualised on imaging is likely related to several aspects of MS biology. We propose that a set of structural characteristics extracted from the MRI brain scans of people with MS are related to biological changes which are meaningful to MS, and may therefore act as predictive markers for outcome. Computational imaging approaches using artificial intelligence (AI) have achieved successes in automatically quantifying lesions. AI-based classification of the scan's features referred to as 'radiomics' can provide more detailed characterisation than is possible by the naked eye and can offer the means to extract more information from the whole-image MRI brain scans.
Radiomics-based biomarkers (indicators) have shown success in cancer treatment, but are still in early development in MS. In this study, we aim to use whole-image brain MRI scans processed with AI techniques and detect the clinical and MRI profiles that predict accumulation of MS-related disability or cognitive impairment. We will take advantage of our MS clinic which is one of the largest in England, and the Nottingham MS Society Register. We will draw on a unique environment of research experts in MS, clinical trials, MRI, computational imaging and predictive modelling who work collaboratively with patients and carers within the NIHR Nottingham Biomedical Research Centre. We will use individual data about patients' clinical condition, their demographics and their scans, and analyse it by the means of AI. Using clinical information which patients have consented for us to use, and the MRI images before starting treatment, we'll train a computer to use mathematical models to predict whether a person's MS will determine accumulating disability or cognitive impairment over the long term. Furthermore, we seek to see if the profile can predict development of disability in other patient groups, by validating the models in large sets of MRI scans obtained from other groups of people with MS using different scanners. We will use a large group of patients from the United States, and also align with a clinical trial ongoing in UK and US, which compares treatments for MS with different strengths.
At least a third of people with MS starting on a first-line MS treatment require subsequent escalation to a stronger therapy. By identifying early, at diagnosis, who is likely to fare worse over the long term, we could offer them a more tailored treatment approach. This is a crucial step towards "personalised medicine", which means we'll be able to prescribe the right medication for the right person at the right time.
A wealth of clinical and MRI data from patients with MS are acquired every year in clinical practice, but only part of these data are used for clinical decision making. MRI is paramount in MS diagnosis and monitoring, but most often the only feature of clinical use are the MS lesions. However, the structure of MS brains visualised on imaging is likely related to several aspects of MS biology. We propose that a set of structural characteristics extracted from the MRI brain scans of people with MS are related to biological changes which are meaningful to MS, and may therefore act as predictive markers for outcome. Computational imaging approaches using artificial intelligence (AI) have achieved successes in automatically quantifying lesions. AI-based classification of the scan's features referred to as 'radiomics' can provide more detailed characterisation than is possible by the naked eye and can offer the means to extract more information from the whole-image MRI brain scans.
Radiomics-based biomarkers (indicators) have shown success in cancer treatment, but are still in early development in MS. In this study, we aim to use whole-image brain MRI scans processed with AI techniques and detect the clinical and MRI profiles that predict accumulation of MS-related disability or cognitive impairment. We will take advantage of our MS clinic which is one of the largest in England, and the Nottingham MS Society Register. We will draw on a unique environment of research experts in MS, clinical trials, MRI, computational imaging and predictive modelling who work collaboratively with patients and carers within the NIHR Nottingham Biomedical Research Centre. We will use individual data about patients' clinical condition, their demographics and their scans, and analyse it by the means of AI. Using clinical information which patients have consented for us to use, and the MRI images before starting treatment, we'll train a computer to use mathematical models to predict whether a person's MS will determine accumulating disability or cognitive impairment over the long term. Furthermore, we seek to see if the profile can predict development of disability in other patient groups, by validating the models in large sets of MRI scans obtained from other groups of people with MS using different scanners. We will use a large group of patients from the United States, and also align with a clinical trial ongoing in UK and US, which compares treatments for MS with different strengths.
At least a third of people with MS starting on a first-line MS treatment require subsequent escalation to a stronger therapy. By identifying early, at diagnosis, who is likely to fare worse over the long term, we could offer them a more tailored treatment approach. This is a crucial step towards "personalised medicine", which means we'll be able to prescribe the right medication for the right person at the right time.
Technical Summary
Multiple Sclerosis (MS) is a common cause of disability in the developed world. Despite progress in MS treatments, significant variability in disability accumulation remains. Prediction of long term outcomes and best use of all data acquired in clinical practice to define the profile of patients at risk for disability and cognitive impairment accrual, are both unmet needs. This project draws on the neurobiological heterogeneity of people with MS and aims to use computational models to identify specific profiles of people with MS who fare worse over the long term despite first-line treatment. We propose a time to event analysis for predicting progression of MS by comparing three different models and incorporating AI state-of-the-art techniques. We will exploit available real world data using AI and build on the experience of research groups at NIHR Nottingham BRC and the Nottingham AI program. We will use deep learning techniques (convolutional neural networks) to extract whole-image features from baseline MRI scans of more than 800 patients with MS, members of the Nottingham MS Society Register. We will use a classical machine learning based regression model, a deep learning model and compare their predictive accuracy with a classical statistical frequentist model incorporating clinical and classical MRI features. After internal validation, we will then externally validate the models in two large independent data sets of which one is a RCT which examines response to moderate versus high potency treatments in MS (DELIVER-MS). The results will help apply for further funding for large deep phenotype collecting (genetics,microbiome) biomarker studies targeted to these biotypes, and explore how they can be integrated into routine clinical practice.
Planned Impact
The key driver behind this study is the patients that we see in our MS clinic who strive for early prognostic markers to inform their future, before irreversible disability occurs. Many of them consistently ask what information their clinical MRI scan provides for their prognosis; they show widespread interest in tools that could deliver individualised prognosis estimates and state that they would be willing to take part in studies to develop such tools. A recent UK nationwide in people with MS members of the MS Society Register study shows that most of people with MS wish to receive early information on long-term prognosis, but this need is unmet. Our PPI feedback confirms the "need to understand the progression" in MS and that the research addressing it is "vitally important" research. It would be of enormous benefit to patients if we could identify early imaging biomarkers to indicate prognosis at an early stage: this would impact how we treat and manage MS, and it could inform patients and carers to plan their future.
The impact on patient care of an easy-to-apply score that can be used at diagnosis to predict relevant disability and cognition outcomes, could be huge. Patients at risk for worsening disability could be offered more potent treatments at the outset and during a window of 'biological opportunity', and people with MS that have good prognosis with moderate efficacy drugs will be spared from exposure to high-risk treatments. It is for now impossible to say how much of the long term disability in MS can really be prevented with current disease modifying treatments, and how much is down to the natural history and individual biology. It's only by identifying these patients who are at risk of faring worse over time, that the impact of a treatment on MS course in a given individual can be clarified, and the risk-benefit trade-off of a treatment can be weighted.
The study could provide a baseline marker to inform clinical longitudinal studies of impact of specific types of MS treatments on cognitive impairment in MS. The whole-image and clinical modelling as predictor for cognitive impairment can be used in cognitive rehabilitation trials in MS, including studies of effects of early high-efficacy treatments on individuals at risk of developing cognitive impairment in MS.
The results of the study could be explored for implementation in the NHS. This would have impact on patient stratification for treatment and rehabilitation. Using routine MRI data for prognosis enables access to a continuously growing wealth of data, without any increase in the costs that the NHS already invests for MS diagnosis and monitoring. Implementing in NHS practice, a deep-learning based tool to extract whole-image features from routine scans to inform disease prognosis, can impact and improve NHS pathways of care in MS and has potential of exploratory application in other neurological conditions. NHSX could offer the direction, the setting and the potential of exploring the implementation of such an AI-based tool in NHS care pathways.
The model developed through refinement and external validation in two large independent data sets, of which one is a RCT, will proffer a large-scale proposal with a health economic investigation. The radiomic profiles obtained will be fed into the Nottingham BRC imaging network to enhance impact and will be further explored through collaborations with the MS-PATHS and MAGNIMS links for the wider community of researchers, scientists and trialists.
The validated clinical-radiomic models would be used to define populations at risk. These populations could be further subject to extensive patient profiling, including genomics, pharmacogenomics and fully characterised biomarker profiling. The results of this study could be fed into very-large data prospective studies currently ongoing in Europe and USA of biomarker profiling and precision medicine in MS.
The impact on patient care of an easy-to-apply score that can be used at diagnosis to predict relevant disability and cognition outcomes, could be huge. Patients at risk for worsening disability could be offered more potent treatments at the outset and during a window of 'biological opportunity', and people with MS that have good prognosis with moderate efficacy drugs will be spared from exposure to high-risk treatments. It is for now impossible to say how much of the long term disability in MS can really be prevented with current disease modifying treatments, and how much is down to the natural history and individual biology. It's only by identifying these patients who are at risk of faring worse over time, that the impact of a treatment on MS course in a given individual can be clarified, and the risk-benefit trade-off of a treatment can be weighted.
The study could provide a baseline marker to inform clinical longitudinal studies of impact of specific types of MS treatments on cognitive impairment in MS. The whole-image and clinical modelling as predictor for cognitive impairment can be used in cognitive rehabilitation trials in MS, including studies of effects of early high-efficacy treatments on individuals at risk of developing cognitive impairment in MS.
The results of the study could be explored for implementation in the NHS. This would have impact on patient stratification for treatment and rehabilitation. Using routine MRI data for prognosis enables access to a continuously growing wealth of data, without any increase in the costs that the NHS already invests for MS diagnosis and monitoring. Implementing in NHS practice, a deep-learning based tool to extract whole-image features from routine scans to inform disease prognosis, can impact and improve NHS pathways of care in MS and has potential of exploratory application in other neurological conditions. NHSX could offer the direction, the setting and the potential of exploring the implementation of such an AI-based tool in NHS care pathways.
The model developed through refinement and external validation in two large independent data sets, of which one is a RCT, will proffer a large-scale proposal with a health economic investigation. The radiomic profiles obtained will be fed into the Nottingham BRC imaging network to enhance impact and will be further explored through collaborations with the MS-PATHS and MAGNIMS links for the wider community of researchers, scientists and trialists.
The validated clinical-radiomic models would be used to define populations at risk. These populations could be further subject to extensive patient profiling, including genomics, pharmacogenomics and fully characterised biomarker profiling. The results of this study could be fed into very-large data prospective studies currently ongoing in Europe and USA of biomarker profiling and precision medicine in MS.
Publications
De Looze K
(2023)
The gut-microbiota-brain axis: An introduction to a special issue on its role in neurological disorders.
in European journal of neurology
Tanasescu R
(2023)
To predict or not to predict: Multiple sclerosis and B-cell subset-specific genetic risk scores.
in European journal of neurology
Maha Salman. BMedSci Thesis. University Of Nottingham, School Of Medicine. Principal Supervisor: Radu Tanasescu.
(2023)
Predictors of disease severity in Myelin oligodendrocyte glycoprotein antibody associated disease (MOGAD).
Tanasescu R
(2023)
Natalizumab Treatment of Relapsing Remitting Multiple Sclerosis Has No Long-Term Effects on the Proportion of Circulating Regulatory T Cells.
in Neurology and therapy
Young C
(2023)
Correlates and trajectories of relapses in relapsing-remitting multiple sclerosis
in Neurological Sciences
Description | Contribution to the transformation of the EAN Scientific Panel of Neuroscience/Translational to a EAN Coordinating panel. |
Geographic Reach | Europe |
Policy Influence Type | Participation in a guidance/advisory committee |
Description | Member of the European Academy of Neurology Task Force for the Guideline on the Management of Autoimmune Encephalitis |
Geographic Reach | Europe |
Policy Influence Type | Participation in a guidance/advisory committee |
Description | NUH Clinical Audit 'the Neurological implications of Covid19 and of vaccinations for Covid19' |
Geographic Reach | Local/Municipal/Regional |
Policy Influence Type | Contribution to new or Improved professional practice |
Impact | This initiative has increased the knowledge and awareness on the neurological implications of Covid19 and vaccinations. This was disseminated through publications. This aims to educate and increase awareness for the NHS neurologist to differentiate the true neurological manifestations of Covid19, from spurious or coincidental associations. As the time for these activities and initiative was in part covered by the CARP project allocated time due to the pandemic, this activity and afferent publications are direct outcomes of this award. |
Description | Understanding how Epstein Barr virus promotes the development of Multiple Sclerosis. This is a Research Grant with UoBirmingham (PI: Dr Claire Shanon-Lowe), NUH (Dr Radu Tanasescu, Dr Bruno Gran), UoNottingham (Dr Rachel Tarlinton) |
Amount | £254,972 (GBP) |
Funding ID | 153 |
Organisation | Multiple Sclerosis Society |
Sector | Charity/Non Profit |
Country | United Kingdom |
Start | 03/2023 |
End | 02/2026 |
Title | A non-invasive MRI protocol for characterising subtle neuroinflammation from immune stimulation (in development): AMCOV study |
Description | This is mentioned in the section 'collaborations & partnerships', under the AMCOV heading. This non-invasive MRI protocol for characterising subtle neuroinflammation from immune stimulation developed in AMCOV will be a tool for application in research focused on detection and modelling of neuroinflammation in different contexts of immune-stimulation, clinical and experimental. |
Type Of Material | Model of mechanisms or symptoms - human |
Year Produced | 2022 |
Provided To Others? | No |
Impact | We have developed, and we are further validating, high quality NODDI and DTI images. We have successfully recruited half of the aimed number of subjects. A BMedsci studentship project (I co-supervised with Prof Auer) was successfully finalised. |
Title | A novel method for coordinate based meta-analysis of structural or functional neuroimaging studies |
Description | This contribution is in line with the backbone of the AIMS project - ie. to use available neuroimaging data, and computational algorithms, to extract relevant results which are meaningful to a disease state. The Lead Developer (Dr Chris Tench) is a collaborator in the AIMS CARP award. This computational algorithm is an improved and novel meta-analytic method of coordinates available from neuroimaging studies, ie. it uses a specific algorithm to compute coordinates pooled together from available independent neuroimaging structural (voxel based morphometry) or functional (fMRI, PET) studies. Background - Functional MRI and voxel-based morphometry are important in neuroscience. They are technically challenging with no globally optimal analysis method, and the multiple approaches have been shown to produce different results. It is useful to be able to meta-analyse results from such studies that tested a similar hypothesis potentially using different analysis methods. The aim is to identify replicable results and infer hypothesis specific effects. Coordinate based meta-analysis (CBMA) offers this, but the multiple algorithms can produce different results, making interpretation conditional on the algorithm. Why this method - The new model based CBMA algorithm, Analysis of Brain Coordinates (ABC), avoids empirical elements where possible and uses a simple to interpret statistical threshold, which relates to the primary aim of detecting replicable effects. Value of the method - ABC is compared to both the most used and the most recently developed CBMA algorithms, by reproducing a published meta-analysis of localised grey matter changes in schizophrenia. There are some differences in results and the type of data that can be analysed, which are related to the algorithm specifics. However, compared to other CBMA algorithms, ABC eliminates empirical elements where possible and uses a simple to interpret statistical threshold. Although there may be no optimal way to meta-analyse neuroimaging studies using CBMA, by eliminating some empirical elements and relating the statistical threshold directly to the aim of finding replicable effects, ABC makes the impact of the algorithm on any conclusion easier to understand, and is the most novel algorithm in the field. This has been published ('Easy to interpret Coordinate Based Meta-Analysis of neuroimaging studies: Analysis of Brain Coordinates (ABC)', J Neurosci Methods . 2022 Mar 7;109556. doi: 10.1016/j.jneumeth.2022.109556) and is listed as a deliverable in the publications section (the CARP awardee is the second author). |
Type Of Material | Model of mechanisms or symptoms - human |
Year Produced | 2022 |
Provided To Others? | Yes |
Impact | This method has the potential to offer less biased results from coordinate based meta-analyses in neuroscience and neurology. Software to perform analysis is made freely available by Dr Chris Tench. Impacts: Meta-analysis of coordinates can identify the published results that are replicable across multiple studies where potential for study specific effects is high, and where there is potential disparity of results available from the multiple neuroimaging analysis packages or scanning protocols. ABC is the latest methodological development of a CBMA methods series by Dr Chris Tench and the group. It was developed specifically to be easy to think about prospectively, eliminating some empirical components, and by using a principled method of error control that directly relates to replicability of effect. It is hoped this will make CBMA using ABC simpler to plan, and the limitations of the results easier to consider when interpreting. By using already available large amounts of neuroimaging data that are computed and modelled, to provide relevant data about neurological disease (Multiple sclerosis or other), this is directly within the scope of the CARP award. As meta-analysis is high-level evidence, the results of using this method have the potential to realistically reduce the number of neuroimaging studies needed to answer a given research question by offering the most consistent targets for neuroimaging study design relevant to that specific question. |
URL | https://www.nottingham.ac.uk/research/groups/clinicalneurology/neuroi.aspx |
Title | AIMS MRI MS pre-dataset for model training |
Description | In line with the AIMS CARP project plan, a dataset of 160 NHS MRI scans (80 subjects, two scans per subject, baseline and follow-up) from a range of years, was produced (extracted and anonymised).This underwent quality checks in view of selections of scans suitable as training data set. |
Type Of Material | Database/Collection of data |
Year Produced | 2021 |
Provided To Others? | No |
Impact | This dataset is representative of the quality of NHS scans obtained 2005-2010, which are mainly 2D scans, from different scanners and protocols. The pre-processing attempts transcending the technical inhomogeneities. Scans were introduced in the UK Biobank Pre-processing pipeline for homogenisation. MS lesions were manually segmented ('ground truth'). This serves as benchmark for the AI driven registration of lesions which is being developed. |
Title | AIMS MRI sub-dataset for exploration of relevant MRI features - pilot study for prediction of incident MS-related cognitive impairment |
Description | An important activity in the AIMS CATRP project regards cognitive impairment in MS and its association with MRI features. One of the research partners in the AIMS project, Roshan das Nair, leads the NIHR-funded study NeuroMS. People with MS are offered cognitive screening in NeuroMS. This provides benchmarking data for cognitive impairment in a number of people with MS followed up in clinic, of whose MRI scans are to be used in the predictive modelling.. The machine learning arm of the AIMS project involves specific MRI features that are relevant to inform the AI model. A review of the literature up-to-date is performed regarding these features. A number of MRI brain features are cited to be associated with prognosis. These pilot studies are exploring, refining and selecting the relevant MRI features for the modelling. Of these, some have an outstanding pragmatic relevance in this light of their use in clinical decision making. The AIMS project uses NHS clinical scans, hence the features that are used by the clinician have weight on management. Hence, these are to be appraised more in depth, as to whether they have a predictive value on their own, or that value is limited. Separate pilot analyses were and are performed for these relevant MRI features to be used for the AI prediction modelling, as to whether they can have predictive value for disability: -lesion size -lesion number -different measures of brain shrinkage (brain atrophy) This dataset focused on cognitive impairment. It included 77 subjects, of whom the majority had two scans. The features were extracted manually in a specialised software which can compute lesion volume, with care of intra-rater and inter-rater variability. The lesion features are registered with relevant clinical features of the subject, and predictive modelling is then computed. The predictive statistical modelling focused on lesion size and used the average lesion volume as a new parameter. |
Type Of Material | Database/Collection of data |
Year Produced | 2022 |
Provided To Others? | No |
Impact | This work was part of a successful BMedsci student project, for which I was principal supervisor. |
Title | AIMS MRI sub-dataset for exploration of relevant MRI features - pilot study for prediction of physical disability |
Description | The machine learning arm of the AIMS project involves specific MRI features that are relevant to inform the AI model. A review of the literature up-to-date is performed regarding these features. A number of MRI brain features are cited to be associated with prognosis. These pilot studies are exploring, refining and selecting the relevant MRI features for the modelling. Of these, some have an outstanding pragmatic relevance in this light of their use in clinical decision making. The AIMS project uses NHS clinical scans, hence the features that are used by the clinician have weight on management. Hence, these are to be appraised more in depth, as to whether they have a predictive value on their own, or that value is limited. Separate pilot analyses were and are performed for these relevant MRI features to be used for the AI prediction modelling, as to whether they can have predictive value for disability: -lesion size -lesion number -different measures of brain shrinkage (brain atrophy) This dataset focused on physical disability, and involved 35 subjects followed-up up to 12years, and with 2 scans : baseline and at 5 years. The features were extracted manually in a specialised software which can compute lesion volume, with care of intra-rater and inter-rater variability. The lesion features are registered with relevant clinical features of the subject, and predictive modelling is then computed. An independent assessment of the same approach was done on an additional sample of 60 subjects (120 scans). |
Type Of Material | Database/Collection of data |
Year Produced | 2021 |
Provided To Others? | No |
Impact | These exploratory analyses have resulted in a successful BMedsci student project - (for which I was principal supervisor), and a PhD student thesis chapter (for which I am internal assessor). |
Title | NMOSD and MOGAD Nottingham database |
Description | we (Thanos Papathanasiou, Radu Tanasescu (CARP PI), Nikos Evangelou (CARP Research Partner)) have obtained the ethical approval for a NMOSD and MOGAD Nottingham database that will be updated prospectively. This will include clinical data of NMOSD/MOGAD patients These are rare forms of demyelinating disease and related to Multiple Sclerosis. |
Type Of Material | Database/Collection of data |
Year Produced | 2021 |
Provided To Others? | No |
Impact | the research dataset which is being built will offer the basis for analysis of clinical outcomes. |
Description | MSPINPOINT- Precision Treatment Strategies in Multiple Sclerosis Using Next-generation Machine Learning. IRAS project ID: 319964 |
Organisation | University College London |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | NIHR funded study , multicentre, to use AI to describe MS phenotypes and predict outcome. It includes 8 NHS Trusts and and other centres (Amsterdam, MNI Institute - Canada). |
Collaborator Contribution | Nottingham University Hospitals will be the eight site. I am PI for this important study. |
Impact | NUH was added as site, and CAG approval was obtained. CAG reference: 23/CAG/0034. |
Start Year | 2023 |
Description | co-PI (with Prof Auer who is a principal CARP research partner) of a NIHR BRC-funded study on Advanced MRI of the brain post-Covid19 Vaccination (AMCOV). |
Organisation | National Institute for Health Research |
Department | NIHR Nottingham Biomedical Research Centre |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Whilst the AIMS CARP award is an effort to seek for features in the routine clinical MRI scans, which could predict outcome in MS and neuroinflammation, in order to further characterise neuroinflammation the development of a specific protocol to detect more subtle changes may be needed. AMCOV is a exploratory study on healthy volunteers, which explores the ability to image non-invasively the physiological state post-immunisation of a novel diffusion and functional MRI protocol. I have contributed (with Prof Auer) to the protocol, documentation, ethics submission, and coordination of this study. This study which I am co-coordinating aims to investigate with advanced MRI in healthy people, the brain changes during physiological 'sickness-behaviour' from immunisation (Covid19 vaccination Public Health England programme); to validate a novel MRI protocol to image the brain's physiological neuroinflammatory response in healthy people by correlating MRI changes with clinical sickness symptoms, and with biological effects (cytokines); to determine test-retest variability and other physiological factors that may affect imaging findings. These data will be used to determine group sizes / power requirements for subsequent clinical trials. I am co-principal investigator of the AMCOV study (with Prof Dorothee Auer, CARP AIMS Research Partner). |
Collaborator Contribution | Prof Auer is an expert in neuroimaging, research partner in the AIMS CARP project, Lead of Beacon Precision imaging at the Nottingham NIHR BRC, my mentor and co-PI for this study. She has designed the radiology protocol and approach, and she coordinates and leads the development of the MRI framework. |
Impact | This collaboration is multi-disciplinary: neuroradiology, neurology, neuroinflammation/neuroimmunology. I am providing the neurology / neuroinflammation expertise. The main expected output will be a novel MRI scanning protocol which is under development (high quality NODDI and DTI images). We have successfully recruited half of the aimed recruitment target. I co-supervised (with Prof Auer as principal supervisor) a successful BMedsci student project. The non-invasive MRI protocol for characterising subtle neuroinflammation from immune stimulation developed in AMCOV will be a tool for application in research focused on detection of neuroinflammation in other contexts of immune-stimulation than vaccination. We plan to target national funding schemes (MRC) and consider international project collaboration. |
Start Year | 2021 |
Description | prediction of outcome in demyelinating neuroinflammatory disease NMOSD and MOGAD |
Organisation | University Hospitals Birmingham NHS Foundation Trust |
Country | United Kingdom |
Sector | Public |
PI Contribution | As a neuroinflammation neurologist, I deal with Multiple Sclerosis (MS) and other demyelinating neuroinflammatory conditions (neuromyelitis optica spectrum disorder, NMOSD, and MOG associated disease MOGAD. I am doing (with Dr Papathanasiou) the NMOSD clinic at QMC. In the spirit of the AIMS CARP award, I aim to use NHS data (imaging, clinical) pertaining to the disturbed neuroimmune axis in these disorders, to predict outcome and understand subtypes of disease, to treat them efficiently. Whilst data from people with MS comes in larger amounts, making it suitable to AI analysis if the quality allows, NMOSD and MOGAD are rare disease and statistical and computational algorithms bespoke to the data available are to be used, to extract predictive information. Through a collaboration Nottingham - Birmingham, we have joined data and efforts from the two neuroscience centres, to this above aim. I have further initiated a research collaboration with the group at the Walton NMOSD/MOGAD Specialist centre - Liverpool (Dr Saif Huda) |
Collaborator Contribution | Data from NMOSD patients from the neuroinflammation clinics in Birmingham and Nottingham were analysed, to obtain predictors of outcome. This has ended in 2022. Data for MOGAD patients from the Nottingham clinic was analysed for predictors of outcome with a model which was further validated in a dataset from the Walton Centre - Liverpool. Collaboration is still active. |
Impact | The analysis was recently published (listed in the Publication section), doi: 10.1016/j.jns.2021.120039. |
Start Year | 2020 |
Description | the role of herpesviruses in NMOSD and MOGAD |
Organisation | The Walton Centre |
Country | United Kingdom |
Sector | Hospitals |
PI Contribution | I have initiated a collaboration with the NMOSD excellence centre at the Walton Centre (led by Dr Saif Huda). We have expertise in the herpesvirus profiling of MS. I have initiated a similar endeavour for NMOSD and MOGAD. |
Collaborator Contribution | We have established an MTA between QMC in Nottingham and The Walton Centre. The NMOSD excellence centre will provide serum samples from NMOSD and MOGAD patients. These will be transferred to QMC, in 2023 May-June. |
Impact | predicted outputs : herpes virus profiling in NMOSD and MOGAD patients in relapse in remission. This is a multidisciplinary research: neurology, immunology, virology |
Start Year | 2022 |
Title | principal investigator (Nottingham site) for the study: Floodlight MS - TONiC. This is a multi-centre national observational study on the large use of artificial intelligence to monitor real life clinical change in multiple sclerosis. This study is a partnership academia - pharmaceutical companies. It involves centres in Liverpool, Nottingham and Stoke, and it is sponsored by Roche, who has the most advanced to date AI tool (smartphone app) to assess clinical change in MS in outpatient setting. |
Description | This prospective study will assess the feasibility of remote participant monitoring using digital technology in participants with MS and healthy controls. At the enrolment visit, the participants will be provided with a remote patient monitoring solution which includes a specific preconfigured smartphone app. This will contain application software that prompts the user to perform various assessments, referred to as active tests and passive monitoring. Active tests will include Hand Motor Function Test (HMFT), gait test, static balance test, electronic version of the Symbol Digit Modalities Test (eSDMT), Mood Scale Question (MSQ), MS Impact Scale (29-item scale) (MSIS-29) questionnaire, MS Symptom Tracking (MSST). Passive monitoring will be done to collect metrics on gait and mobility throughout the daily life of participants in a continuous and unobtrusive manner. This study is linked synergically to the topic and the aim of the award. It represents an application of AI in MS monitoring, and long-term outcome assesment. |
Type | Management of Diseases and Conditions |
Current Stage Of Development | Early clinical assessment |
Year Development Stage Completed | 2023 |
Development Status | Under active development/distribution |
Clinical Trial? | Yes |
Impact | This study adds an extra layer of follow-up and understanding of disease which pertain to disease trajectories of people with MS (TONIC studies). Prediction of long-term outcome in MS is the main goal of AIMS. This study uses Artificial Intelligence to monitor MS outcome; and uses Patient-Reported-Outcomes to measure MS trajectory. |
Description | I have registered as Expert with the European Medicines Agency, representing EAN. |
Form Of Engagement Activity | A formal working group, expert panel or dialogue |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Policymakers/politicians |
Results and Impact | participation to PCWP and HCPWP EMA meetings in Nov 2023 and Feb 2024. |
Year(s) Of Engagement Activity | 2023,2024 |
Description | Management Group active member and elected Co-Chair (2022) of the Scientific Panel of Neuroscience / translational neurology of the European Academy of Neurology (EAN) |
Form Of Engagement Activity | A formal working group, expert panel or dialogue |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | The EAN Scientific Panels are the core scientific active groups of the EAN. Elected as a Management Group member in 2020, I have participated to the business meetings, participated in congress preparation and - and was successful in joint activities and congress proposal with other EAN Scientific panels, reviewed fellowships and abstracts for the EAN stipends and EAN congresses respectively. The aim of the panel is to provide for the clinical neurologist, the relevant tools and education from the translational neurology perspective, which can benefit patient care in neurology in Europe. This aim is therefore in the CARP award's scope. I was elected in 2022 as a co-chair of the panel. |
Year(s) Of Engagement Activity | 2020,2021,2022 |
URL | https://www.ean.org/home/organisation/scientific-panels/neurosience/translational-neurology |
Description | National Independent Parliamentary Report- Understanding the Limitations and Innovations of Medical Cannabis Prescribing in the UK |
Form Of Engagement Activity | A formal working group, expert panel or dialogue |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Policymakers/politicians |
Results and Impact | This was a research project focusing on the ethical prescribing of cannabis based medicines for indication-specific purposes, as opposed to untargeted prescribing. Volteface is a research body that has worked with a number of major news outlets and Members of Parliament, releasing ten reports to date. Volteface, alongside a number of Parliamentarians and third sector organisations including the MS Society and Epilepsy Action wrote a report for an All Party Parliamentary Group exploring the need for appropriate and indication-specific prescribing of cannabis medicines in the UK. They spoke to a range of experts on the issue to inform the report's findings through the formation of a working group. I was part of this working group, as specialist clinician, and provided feedback about the perceived barriers to prescribing cannabis and what the feasible solutions are to exploring the evidence base of cannabis medicines where it is medically efficient and appropriate. The report investigated the need for a more medicalised, pharmaceutical approach to prescribing. Whilst the clinic model has been useful for many patients, it is somewhat hindering scientific research for indication specific prescribing. My feedback related to prescribing and use of the cannabis based approved medications within the NHS for the treatment of symptoms of people with Multiple Sclerosis. I consider this activity linked to this award by the fact that the PPI activities during the award (1-to-1 discussions with patients about symptoms of MS that worth to be subject to prediction of outcome), I have collected feedback from patients regarding their symptoms which are incompletely addressed by current medications, and were candidates to cannabinoid-approved medications. This enabled me to provide feedback to the working group on the Parliamentary Report. The group ran on a voluntary basis, and partly during the time covered by this award. There was an official parliamentary launch in the House of Commons, on Thursday 1st December. |
Year(s) Of Engagement Activity | 2021,2022 |
Description | Organiser and Chair of a special session at the Virtual congress of the European academy of neurology in 2021: 'More than a gut feeling: The gut brain axis in neuroinflammation and neurodegeneration' |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | This Special Session was endorsed by the EAN scientific Panel of neuroimmunology, The EAN Scientific Panel of Neuroscience/translational and the European Journal of Neurology (scientific platform of EAN). It oversaw the state of knowledge and perspectives in the gut brain axis research and clinical implications. I have initiated this initiative, designed the content and put forward the proposal for this session on behalf the EAN Scientific Panels of Neuroimmunology and Neuroscience / Translational, together with Kristl Vonckt (on behalf the European Journal of Neurology board). I have Chaired the session. The scientific session involved four different presentations, and a section of questions and answers. The scientific presentations were: 1: Why the gut-brain axis is important for precision neurology - the neuroscientist's view Sarah Vascellari, Cagliari, Italy 2: The gut-brain axis in multiple sclerosis and neuroinflammation: pathophysiology and targets for therapy Hartmut Wekerle, Munich, Germany 3: Does gut microbiota play a role in neurodegenerative disorders? Filip Scheperjans, Helsinki, Finland 4: Is there a role for the gut-brain axis in the pathophysiology and treatment of epilepsy? Katrien De Looze, Ghent, Belgium The session was well attended, and currently the link to the recording is available online. this has enabled reaching broader audiences. |
Year(s) Of Engagement Activity | 2021 |
URL | https://www.ean.org/congress-2021/discover/schedule/scientific-programme/19-june-2021-1200-2000 |