PAMBAYESIAN: PAtient Managed decision-support using Bayesian networks

Lead Research Organisation: Queen Mary University of London
Department Name: Sch of Electronic Eng & Computer Science

Abstract

Patients with chronic diseases must take day-to-day decisions about their care and rely on advice from medical staff to do this. However, regular appointments with doctors or nurses are expensive, inconvenient and not necessarily scheduled when really needed. Increasingly, there are low cost and highly portable sensors that can measure a wide range of physiological values. Can such 'wearable' sensors be used to improve the way that chronic conditions are managed? Patients could have more control over their own care if they wished; doctors and nurses could monitor their patients without the expense and inconvenience of visits, except when they are actually needed. Remote monitoring of patients is already in use for some conditions but there are barriers to its wider use: it relies too much on clinical staff to interpret the sensor readings; patients, confused by the information presented, may become more dependent on health professionals, whose work may be increased rather than reduced.

The project seeks to overcome these barriers by addressing two weaknesses of the current systems. First is their lack of intelligence. Intelligent systems that can help medical staff in making decisions already exist and can be used for diagnosis, prognosis and advice on treatments. One especially important form of these systems uses belief or Bayesian networks, which show how the relevant factors are related and allow beliefs, such as the presence of a medical condition, to be updated from the available evidence. However, these intelligent systems do not yet work easily with data coming from sensors. The second weakness is any mismatch between the design of the technical system and the way the people - patients and professional - interact. We will work on these two weaknesses together: patients and medical staff will be involved from the start, enabling us to understand what information is needed by each player and how to use the intelligent reasoning to provide it. The medical work will be centred on three case studies, looking at the management of rheumatoid arthritis, diabetes in pregnancy and atrial fibrillation (irregular heartbeat). These have been chosen both because they are important chronic diseases and because they are investigated by significant research groups in our Medical School, who are partners in the project. This makes them ideal test beds for the technical developments needed to realise our vision and allow patients more autonomy in practice.

To advance the technology, we will design ways to create belief networks for the different intelligent reasoning tasks, derived from an overall model of medical knowledge relevant to the diseases being managed. Then we will investigate how to run the necessary algorithms on the small computers attached to the sensors that gather the data as well as on the systems used by the healthcare team. Finally, we will use the case studies to learn how the technical systems can integrate smoothly into the interactions between patients and health professionals, ensuring that information presented to patients is understandable, useful and reduces demands on the care system while at the same time providing the clinical team with the information they need to ensure that patients are safe.

If successful, our results will be useful not only for the examples of chronic diseases studied on the project but also for managing other chronic medical conditions, when the same techniques can be applied. Although the project will produce prototype systems, several stages of product development and clinical trials will be needed before real systems are available for patients; we will prepare for these and make a first evaluation of the economic benefits of the proposed systems during the project. Also, several technology companies are involved in the project's Advisory Board to help ensure effective commercial exploitation in the long run.

Planned Impact

Technology has the potential both to improve healthcare and reduce its cost, to the benefit of both patients and healthcare professionals. This project aims to develop a new generation of intelligent decision-support systems to work alongside the latest portable sensors so that patients can manage chronic medical conditions with efficient support from healthcare professionals. Achieving these benefits clearly relies on many strands of research (e.g. sensors, communications), but the contribution of this project will allow digital health technology developers to design systems that place less reliance on continuous supervision by health professionals and allow more patient autonomy.

The project's strategy for impact is: (i) early engagement with clinical stakeholders and patients, leading into clinical evaluation through a sequence of pilots and then trials, in parallel with (ii) progressive engineering refinement of the research prototypes developed within the project, in partnership with companies, all supported by (iii) attention to ethical and regulatory requirements and economic viability from an early stage so that these do not become barriers. This strategy will be applied firstly in the context of three medical case studies, in the management of rheumatoid arthritis, diabetes in pregnancy and atrial fibrillation but equally extends to the application of the technical advances to the management of other chronic medical conditions.

Early in the project, we will set-up clinical focus groups to ensure that technology solutions fit the actual problems. Initial engagement with patients and health care professionals will be around the case studies with patient advisory groups formed from existing PPI groups. Later, we will also engage with wider patient groups such as Patient Opinion, UK eHealth Association, Healthwatch and NHS Choices to explore the next stage of the translation of our research into practice. Agile and startup companies have an important role in introducing this disruptive technology, and a group of UK medical technology companies (BeMoreDigital, Mediwise, Rescon, SMART Medical, uMotif) as well as IBM UK and Hasiba Medical GmbH, have committed to advising the project (minimum 2 Advisory Group meetings per year) with a view to exploiting the technology.

We will expand this with advice from our innovation team on IP, licensing and spin-outs. The project includes an initial study of the potential health economic impact in the case studies. To address the traditional 'regulatory barrier' we have made safety a core research objective and will progressively engage key regulators (e.g. the Information Governance Alliance) and the Caldicott Guardian and Digital Health lead for Barts Health, with whom initial contracts have already been made.

In addition to the medical beneficiaries, the project promises major impact in the data sciences with advances in methods for building and running Bayesian network (BN) models that combine expert judgment and data. Although many researchers and system developers already use BNs for decision-support and probabilistic analysis, more widespread use is limited by constraints on the size and complexity of models. The project will deliver a framework for integrating models at different levels of granularity, providing a practical way to build more complex models efficiently. Since current state-of-the-art BN technology has extremely limited support for the modelling concepts proposed the research will be of benefit to those applying BNs in other applications. The project will deliver open source code so that academic researchers and users can use the new techniques in their own work without restriction.

Publications

10 25 50

 
Description We have developed the following:

An approach (based on causal modelling) for collecting and analysing clinical data that enables better use of data from observational studies.

A systematic way to elicit clinicians' knowledge using the idea of 'caremaps' (in the areas of rheumatoid arthritis, gestational diabetes, and chronic heart disease) to transform these into the required Bayesian network (BN) models to be used for intelligent decision support.

An idiom-based approach for developing medical BNs

An incremental explanation for explaining the reasoning process in BNs

A large scale scoping review that revealed research gaps and highlighted important research directions for the use of BNs in medical decision-support

A generic web interface for medical BNs enabling users with no knowledge of BNs to access any BN models (it performs inference in real time using a three-layered BN)

An approach to identifying and classifying Learning Health Systems (LHS)

A methodology for analysing barriers, benefits and facilitator factors to adoption of LHS

An AGREED II study evaluating the clinical practice guidelines used with the patient population, who are the subject of our database

Idenified issues with data visualisation in medicine generally, and midwifery specifically

Taxonomy for classification of clinical documentation (CCPS)

Improved decision support (for both clinicians and patients) in a) rheumatoid arthritis and b) gestational diabetes.

New cases studies in multiple scleroris and pelvic floor syndrome

Extensive insights into COVID-19 risks (we have published multiple relevant papers and studies)
Exploitation Route Clinicians and medical researchers will be able to use the improved data collection approach proposed to make better use of observational studies

Medical researchers will be able to use the methods to develop caremaps and Bayesian networks for other chronic conditions, while a number of medical companies are already investigating ways to exploit the technology.

There has already been new pump priming funding to integrate our rheumatoid arthritis model onto a commericial platform (provided by a healthcare company) used by mutliple NHS trusts
Sectors Healthcare

URL https://pambayesian.org/
 
Description A number of clinicians and medical researchers are using the improved data collection approach proposed to make better use of observational studies Several clinicians outside of the original consortium are using methods devleoped in PAMBAYESIAN to develop decision-support/risk assessment BNs for other chronic conditions. This includes: pelvic floor syndrome and multiple sclerosis. They have committed experts and data to work with our research team.
First Year Of Impact 2019
Sector Healthcare
Impact Types Societal

 
Description Our Bayesian analysis helped to enable the prescription of Ivermectin in Nebraska USA
Geographic Reach North America 
Policy Influence Type Contribution to new or Improved professional practice
Impact People previously denied access to this cheap, safe drug can now get it in Nebraska with informed consent
URL https://ago.nebraska.gov/sites/ago.nebraska.gov/files/docs/opinions/21-017_0.pdf
 
Description A best practice guide for managing patellofemoral pain: a synthesis of systematic review, expert clinical and patient values
Amount £30,000 (GBP)
Organisation Private Physiotherapy Educational Foundation 
Sector Charity/Non Profit
Country United Kingdom
Start 03/2020 
End 04/2022
 
Description AI driven biologics optimiser for Rheumatoid Arthritis patients: UEZ PPF collaboration between QMUL and Living With Ltd
Amount £50,000 (GBP)
Organisation Queen Mary University of London 
Sector Academic/University
Country United Kingdom
Start 08/2020 
End 04/2021
 
Description Augmented feedback to enhance motor and artistic learning during social distancing
Amount £235,667 (GBP)
Funding ID ES/V015354/1 
Organisation Economic and Social Research Council 
Sector Public
Country United Kingdom
Start 01/2021 
End 12/2022
 
Description Bayesian Decision Support for the management of low back pain: Development, exploration and feasibility
Amount £289,760 (GBP)
Organisation Barts Charity 
Sector Charity/Non Profit
Country United Kingdom
Start 08/2021 
End 08/2025
 
Description Collaborative R&D
Amount £31,000 (GBP)
Funding ID 24111 
Organisation Innovate UK 
Sector Public
Country United Kingdom
Start 03/2019 
End 08/2019
 
Description Exercise therapy for the treatment of tendinopathies
Amount £243,894 (GBP)
Funding ID Exercise therapy for the treatment of tendinopathies: A mixed methods evidence synthesis 
Organisation National Institute for Health Research 
Sector Public
Country United Kingdom
Start 03/2020 
End 10/2021
 
Description Exercise therapy for the treatment of tendinopathies: A mixed methods evidence synthesis
Amount £243,894 (GBP)
Funding ID NIHR129388 
Organisation National Institute for Health Research 
Sector Public
Country United Kingdom
Start 03/2020 
End 08/2021
 
Description SafeAIR: Safer aviation from ethical Autonomous Intelligence Regulation
Amount £200,000 (GBP)
Funding ID ICRF2122-5-234 
Organisation Royal Academy of Engineering 
Sector Charity/Non Profit
Country United Kingdom
Start 09/2021 
End 09/2023
 
Title Approximate Inference in Discrete Dynamic Bayesian Networks using Partitioned Interface Junction Trees 
Description Dynamic Bayesian Networks (DBNs) generalize Hidden Markov Models and Kalman Filter Models, thereby providing a general framework for modelling of, and Bayesian inference in, discrete-time stochastic processes with Markov properties. Given that exact inference is infeasible in large and dense DBNs due to heavy computational overhead, approaches to robust approximate Bayesian inference in this case are desired to meet practical needs. We present a novel recursive algorithm that is equipped with automated partitioning of interfaces for approximate inference in discrete DBNs with first-order Markov property. The algorithm is generic in that it applies where (1) temporal arcs can either be persistent or non-persistent; (2) nodes in the forward interface can either be hidden or observable. The novelty of the algorithm lies in: (1) the use of Maximum Retrospective Length for a given DBN to determine the minimum size of temporal windows to achieve reliable backward inference recursively; (2) the construction of partitioned interface junction trees, and the use of decomposed messages in line with the partitioned interface junction trees, for efficient message passing in recursive inference. 
Type Of Material Improvements to research infrastructure 
Year Produced 2020 
Provided To Others? No  
Impact Compared to Kevin Murphy's famous interface algorithm, our method can significantly reduce the space complexity of inference in discrete DBNs with large interfaces, for a small loss in computational accuracy. Compared to the well-known Boyen-Koller algorithm,our method can produce smaller inference errors by accommodating more comprehensive associations between a larger scope of interface nodes. 
 
Title A Bayesian network model for personalisation of chronic diseases 
Description We have developed a BN model to support the personalisation of care delivery to the patients with chronic disease, specifically those with RA. 
Type Of Material Computer model/algorithm 
Year Produced 2020 
Provided To Others? No  
Impact We collaborate with a group of experts in the area of human interaction with computer. We investigate the literature and extract a variety of psychological, social, and physical factors as well as some factors of disease manifestation. Our aim is to measure the quality of life of the patients. We trained the BN parameters using expert's knowledge since there is no retrospective data for this model. This model is in the evaluation stage and its initial results will be published soon. 
 
Title A Bayesian network model for rheumatoid arthritis diagnosis 
Description We developed a Bayesian network (BN) model for diagnosis of rheumatoid arthritis (RA) through collaborating with an expert panel of rheumatologists. 
Type Of Material Computer model/algorithm 
Year Produced 2020 
Provided To Others? No  
Impact We began the BN modelling by eliciting medical knowledge from our experts. We analysed and processed an available data provided by our experts. Using the knowledge and data, we created the BN model structure involving RA risk factors, comorbidities, RA manifestation factors, and diagnosis. We trained the BN model using the processed data and evaluated the model. We have written a paper on BN modelling for RA diagnosis and submitted it to the 8th IEEE International Conference on Healthcare Informatics. 
 
Title A Dynamic Bayesian network model for monitoring rheumatoid arthritis 
Description We constructed a dynamic Bayesian networks (DBNs) model to monitor RA patients considering the manifestation of their disease. 
Type Of Material Computer model/algorithm 
Year Produced 2020 
Provided To Others? No  
Impact In this model, we considered a number of time slices in which the disease activity is measured by the RA manifestation factors and temporal abstraction factors. The initial evaluation of this model shows that it is able to predict disease activity. We are further evaluating the outcomes of this model along with our experts and we will publish them soon. Our future work is to transform this DBN model into a model for RA self-care which can be used by the clinicians to remotely monitoring the disease activity of the RA patients. 
 
Title Research database 
Description We have conducting a big scale scoping review on Bayesian networks (BN) in healthcare. From each reviewed paper a number of data have been extracted regarding the targeted decision support, the BN development process and the mode's usefulness in clinical practice. A unique and large database of 123 papers with more than 20 attributes per paper has been developed. 
Type Of Material Database/Collection of data 
Year Produced 2020 
Provided To Others? No  
Impact This is a unique and new scoping review of the domain of BNs in healthcare that provides an analytical framework for comprehensively characterizing the domain and its current status. The review shows that: (1) BNs in healthcare have not been used to their full potential; (2) there is a lack of a generic BN development process; (3) there are limitations in the way researchers report their works on BNs in healthcare, which may impact understanding, trust, consensus towards systematic methodologies, practice and adoption of BNs; and (4) there is a gap between having an accurate BN and a useful BN that has an impact in clinical practice. This review empowers researchers and clinicians with an analytical framework and findings that will enable them to understand the need to address the problems of: (1) restricted aims of BNs; (2) ad hoc BN development methods; and (3) the lack of BN adoption in practice. To map the way forward, the paper also proposes several future research directions regarding BN development methods and adoption in practice and several recommendations for improving reproducibility of modelling approaches described in the literature, and for improving the overall usefulness of medical BNs. 
 
Description Developing Rheumatoid Arthritis application 
Organisation Living With
Country United Kingdom 
Sector Private 
PI Contribution Our reseach team has developed the Bayesian network model for rheumatoid arthritis that is being piloted by Living With
Collaborator Contribution Living With are integrating the Bayesian netowrk model onto their platform as part of their support for RA patients
Impact See https://www.applieddatascience.qmul.ac.uk/news/3863/queen-mary-partner-with-healthtech-startup-living-with-to-help-rheumatoid-arthritis-patients
Start Year 2019
 
Description Research Collaboration - Assoc. Prof. Henry Potts 
Organisation University College London
Country United Kingdom 
Sector Academic/University 
PI Contribution Formative research into Learning Health Systems leading to identification of a formal definition and taxonomy for LHS
Collaborator Contribution Input based on Dr Potts' research in health informatics and LHS and Dr Potts helped to initially direct potential areas of research in order to refine the study of LHS
Impact McLachlan, S., Johnson, O., Dube, K., Buchanan, D., Potts, H.W.W., Gallagher, T., & Fenton, N. (2019). A framework for analysing learning health systems: Are we removing the most impactful barriers? Journal of Learning Health Systems. DOI: 10.1002/lrh2.10189 McLachlan, S., Potts, H.W.W., Dube, K., Buchanan, D., Lean, S., Gallagher, T., Johnson, O., Daley, B., Marsh, W., & Fenton, N. (2018) The Heimdall Framework for supporting characterisation of Learning Health Systems. Journal of Innovation in Health Informatics, 25(2) McLachlan, S., Dube, K., Buchanan, D., Lean, S., Johnson, O., Potts, H.W.W., Gallagher, T., Marsh, W., & Fenton, N. (2018) Learning Health Systems: The research community awareness challenge. Journal of Innovation in Health Informatics, 25(1).
Start Year 2017
 
Description Research Collaboration - Dr Kudakwashe Dube 
Organisation Massey University
Country New Zealand 
Sector Academic/University 
PI Contribution Initial literature review methodology and scoping review data for systematic review of Bayesian networks in healthcare
Collaborator Contribution Dr Dube received sponsorship from his home institution to attend Queen Mary University of London and collaborate as a visiting researcher. He assisted to formalise the novel collaborative literature review approach (now titled: STaR) and was one of the three senior reviewers on the 8-person review of around 120 BNs in Healthcare papers. He also participated in development and testing of the CardiPro application
Impact McLachlan, S., Potts, H.W.W., Dube, K., Buchanan, D., Lean, S., Gallagher, T., Johnson, O., Daley, B., Marsh, W., & Fenton, N. (2018) The Heimdall Framework for supporting characterisation of Learning Health Systems. Journal of Innovation in Health Informatics, 25(2) McLachlan, S., Dube, K., Buchanan, D., Lean, S., Johnson, O., Potts, H.W.W., Gallagher, T., Marsh, W., & Fenton, N. (2018) Learning Health Systems: The research community awareness challenge. Journal of Innovation in Health Informatics, 25(1). McLachlan, S., Dube, K., Kyrimi, E., & Fenton, N. (2019). LAGOS: Making sense of Learning Health Systems and how they can integrate with Patient Care. BMJ Health and Care Informatics (BMJHCI) 26(1). McLachlan, S., Johnson, O., Dube, K., Buchanan, D., Potts, H.W.W., Gallagher, T., & Fenton, N. (2019). A framework for analysing learning health systems: Are we removing the most impactful barriers? Journal of Learning Health Systems. DOI: 10.1002/lrh2.10189 Kyrimi, E., McLachlan, S., Dube, K., Neves, M. R., Fahmi, A., & Fenton, N. (2020). A Comprehensive Scoping Review of Bayesian Networks in Healthcare: Past, Present and Future. Artificial Intelligence in Medicine, 116. https://doi.org/10.1016/j.artmed.2021.102108 McLachlan, S., Kyrimi, E., Dube, K., Hitman, G.A., Simmonds, J., & Fenton, N.E. (2020). Towards Standardisation of clinical care process specifications. SAGE Health Informatics Journal (HIJ) DOI: 10.1177/1460458220906069 McLachlan, S., Dube, K., Hitman, G.A., Fenton, N.E., & Kyrimi, E. (2020). Bayesian Networks in Healthcare: Distribution by Medical Condition. Artificial Intelligence in Medicine (AIIM), 107. https://doi.org/10.1016/j.artmed.2020.101912 Kambarami, F., McLachlan, S., Bozic, B., Dube, K., & Chimhundu, H. (2021). Computational Modelling of Agglutinative Languages: The Challenge for Southern Bantu Languages. Arusha Working Papers in African Linguistics, 3(1), pp 52-81. Kyrimi, E., Dube, K., Fenton, N., Fahmi, A., Neves, M., Marsh, W., & McLachlan, S. (2020). Bayesian Networks in Healthcare: What is preventing their adoption? Artificial Intelligence in Medicine, 116. https://doi.org/10.1016/j.artmed.2021.102079
Start Year 2017
 
Description Research Collaboration - Prof Lisa Webley 
Organisation University of Birmingham
Department Birmingham Law School
Country United Kingdom 
Sector Academic/University 
PI Contribution Formal method for producing Caremaps - an information visualisation approach that describes the clinical path for patients from diagnosis through treatment - including clinical decisions and treatment outcomes - as well as a proposal for how this information visualisation approach could be generalised to other domains and professions
Collaborator Contribution Expertise in law and legal processes and support to take the generalised caremap process and produce Lawmaps - an information visualisation approach for representing legislation and lawyerly processes
Impact McLachlan, S., & Webley, L. (2021). Visualisation of Law and Legal Process: An Opportunity Missed. SAGE Journal of Information Visualisation. https://doi.org/10.1177/14738716211012608 McLachlan, S., Kyrimi, E., Dube, K., Fenton, N., & Webley, L. (2021). Lawmaps: Enabling Legal AI development through Visualisation of the Implicit Structure of Legislation and Lawyerly Process. Journal of Artificial Intelligence and Law. https://doi.org/10.1007/s10506-021-09298-0
Start Year 2018
 
Description Research Collaboration - Prof Owen Johnson 
Organisation University of Leeds
Country United Kingdom 
Sector Academic/University 
PI Contribution Formative research into Learning Health Systems leading to identification of a definition and taxonomy for LHS
Collaborator Contribution Input based on processes Prof Johnson had pioneered at the University of Leeds in analysing clinical behaviours datasets as one form of LHS, and input to the final taxonomy for LHS
Impact McLachlan, S., Johnson, O., Dube, K., Buchanan, D., Potts, H.W.W., Gallagher, T., & Fenton, N. (2019). A framework for analysing learning health systems: Are we removing the most impactful barriers? Journal of Learning Health Systems. DOI: 10.1002/lrh2.10189 McLachlan, S., Potts, H.W.W., Dube, K., Buchanan, D., Lean, S., Gallagher, T., Johnson, O., Daley, B., Marsh, W., & Fenton, N. (2018) The Heimdall Framework for supporting characterisation of Learning Health Systems. Journal of Innovation in Health Informatics, 25(2) McLachlan, S., Dube, K., Buchanan, D., Lean, S., Johnson, O., Potts, H.W.W., Gallagher, T., Marsh, W., & Fenton, N. (2018) Learning Health Systems: The research community awareness challenge. Journal of Innovation in Health Informatics, 25(1).
Start Year 2017
 
Description Research Collaboration - Prof Thomas Gallagher (Dean of Missoula College) 
Organisation University of Montana
Country United States 
Sector Academic/University 
PI Contribution Formative research into Learning Health Systems leading to identification of a formal definition and taxonomy for LHS. Synthetic Data Generation approach for Realistic Synthetic Electronic Health Records - essentially synthetic health data to train LHS.
Collaborator Contribution A theoretical framework and expertise in Realistic Synthetic Electronic Health Records. Input to synthetic data generation models and health condition timelines
Impact McLachlan, S., Dube, K., Gallagher, T., Daley, B., & Walonoski, J. (2018) The ATEN Framework for creating the Realistic Synthetic Electronic Health Record, in Proceedings of the 11th International Joint Conference on Biomedical Systems and Technologies (BIOSTEC 2018), volume 5: HEALTHINF, pp 220-230. DOI: 10.5220/0006677602200230 McLachlan, S., Potts, H.W.W., Dube, K., Buchanan, D., Lean, S., Gallagher, T., Johnson, O., Daley, B., Marsh, W., & Fenton, N. (2018) The Heimdall Framework for supporting characterisation of Learning Health Systems. Journal of Innovation in Health Informatics, 25(2) McLachlan, S., Dube, K., Buchanan, D., Lean, S., Johnson, O., Potts, H.W.W., Gallagher, T., Marsh, W., & Fenton, N. (2018) Learning Health Systems: The research community awareness challenge. Journal of Innovation in Health Informatics, 25(1). Gallagher, T., Dube, K., & McLachlan, S. (2018) Ethical Issues in Secondary Use of Personal Health Information. IEEE Future Directions, May 2018.
Start Year 2017
 
Title Bayesian network based COVID-19 Personalised risk assessment online tool 
Description This is an online app based in a causal probabilistic model (a Bayesian network) that provides personalised risk assessment of COVID-19, which has the advantage of minimal infringement of privacy. Users can provide as much or little personal information as they wish about relevant risk factors, symptoms, and recent social interactions. The app then provides them feedback about the likelihood of the presence of asymptotic, mild or severe COVID19 (past, present and projected). Model was developed as part of the PAMBAYESIAN project and Agena Ltd funded its deployment as a web and mobile phone app. 
Type Support Tool - For Fundamental Research
Current Stage Of Development Small-scale adoption
Year Development Stage Completed 2021
Development Status Closed
Impact While we have decided not to 'market' the product (we want it to be used as a reseach tool frst and foremost) users have reported that it is far superior than the many COVID appsthat are are widely available. The development has also provided new insights of web deployment of Bayesian networks models 
URL https://covid19.apps.agenarisk.com/
 
Title Bayesina network based Rheumatoid Arthritis decision support tool 
Description See https://www.qmul.ac.uk/media/news/2020/se/queen-mary-partner-with-healthtech-startup-living-with-to-help-rheumatoid-arthritis-patients.html 
Type Support Tool - For Medical Intervention
Current Stage Of Development Early clinical assessment
Year Development Stage Completed 2021
Development Status Under active development/distribution
Impact Improved understanding of rheumatoid arthritis risks and treatements 
URL https://www.qmul.ac.uk/media/news/2020/se/queen-mary-partner-with-healthtech-startup-living-with-to-...
 
Title CardiPro 
Description CardiPro is one of the first full-suite cross-platform tools that is useable by patients and clinicians and performs computation of diagnostic probabilities using Bayesian networks on mobile devices using the AgenaRisk API. CardiPro was demonstrated capable of predicting diagnosis of Gestational Diabetes Mellitus and COVID. 
Type Of Technology Webtool/Application 
Year Produced 2019 
Impact This software remains the first application that is capable of collecting symptom data and returning diagnostic results of Bayesian computation use on mobile devices like smartphones in near real-time 
URL https://doi.org/10.1109/ICHI48887.2020.9374378
 
Description 10th Annual CAS Conference Talk 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Schools
Results and Impact A Talk for teachers on what machine learning /AI is about and practical ways to include it in the curriculum
Year(s) Of Engagement Activity 2018
URL https://teachinglondoncomputing.org/machine-learning/
 
Description CAS London Annual Conference 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Schools
Results and Impact A workshop to explain AI/Machine Learning and how it can be practically done in the curriculum.
Year(s) Of Engagement Activity 2018
URL https://teachinglondoncomputing.org/machine-learning/
 
Description Interview on LBC by Majid Nawaz (9 minutes) about our study of the ONS statistics for vaccine mortality, 4 December, 2021 
Form Of Engagement Activity A press release, press conference or response to a media enquiry/interview
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact This interview - when it was originally uploaded to youtube had over 300,000 views within one week before youtube decided to take it down for 'making statements that were not approved by the WHO'. However, the statements have all subsequently been proved to be accurate. The video has been re-uploaded to rumble where it has (as of 23 Feb 2022) 65,000 views. The research described in the video was subsequently described in Maajid Nawaz's 3 hours podcast on the Joe Rogan show https://open.spotify.com/episode/1ugbn7cuab3mNgKbo81ajM (19 Fb 2022). It is estimated that as of today (just 4 days later) the podcast has been watched by over 20 million people.
Year(s) Of Engagement Activity 2021
URL https://rumble.com/vq9wth-norman-fenton-interviewed-by-majid-nawaz-lbc-radio-4-dec-2021.html
 
Description Invited Keynote Speech 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Keynote speaker at the International Symposium on Advanced Electrical and Communication Technologies (ISAECT 18), 21 to 23 November 2018, Rabat, Morocco.
Year(s) Of Engagement Activity 2018
URL http://www.isaect.org/akram-alomainy/
 
Description Invited Lecture to the Bournemouth Skeptics Society "Fallacies of Probability and Risk" 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact This was attended by about 80 members of the general public (and the talk jas been viewed by many more online). There was a lively debate that followed and multiple follow-up interactions in which people said that their views had changed as a result.
Year(s) Of Engagement Activity 2018
URL http://bournemouth.skepticsinthepub.org/Event.aspx/16558/Fallacies-of-Probability-and-Risk
 
Description Invited Lecture: "Why Big Data and AI machine learning will never work for critical problems of risk assessment - causal reasoning and knowledge to the rescue", UK National Environment Research Council (NERC) initiative on Constructing a Digital Environment Webinar Series, 17 Dec 2020 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact I believe thousands have watched this and I have had multple correspondence about it.
Year(s) Of Engagement Activity 2020
URL https://digitalenvironment.org/cde-webinar-series/#fenton
 
Description Invited Talk to the Portsmouth Skeptics Society 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact 70 people attended this evening talk, but the event was later publicised on twitter and on other websites and the presentations has been viewed widely internationally. This was my second talk at one the UK's skeptics societies (previously did Brighton) and have since been invited to do one at the Bournemouth skeptics in May 2018.
Year(s) Of Engagement Activity 2017
URL https://www.flickr.com/photos/revupreview/sets/72157688176562264/
 
Description Invited panelist: "People and Pandemics - A Better World?", Queen Mary Public Lecture Series, 22 July 2020 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Policymakers/politicians
Results and Impact Over a hundred people attended live and over a thousand have watched since
Year(s) Of Engagement Activity 2020
URL https://www.qmul.ac.uk/events/digital-library/items/people-and-pandemics--a-better-world.html
 
Description Invited seminar at Royal London Hospital: "AI for healthcare relies on smart data rather than big data" 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact This was an invited presentation where the audience were primarily clinicians and clinical researchers. However, the online presentation (see link) has been seen by many others.
Year(s) Of Engagement Activity 2018
URL http://probabilityandlaw.blogspot.com/2018/11/ai-for-healthcare-requires-smart-data.html
 
Description Invited seminar to ERC: "Smart data not big data: Improving critical decision-making with Bayesian networks" 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Policymakers/politicians
Results and Impact 100 policy makers and scientists from the European Research Council attended and the video recording (see url) has been seen by many others. Follow-up discussions suggest the presentation is influencing the way people think about 'big data'.
Year(s) Of Engagement Activity 2018
URL https://webcast.ec.europa.eu/erc-scientific-seminars-prof-norman-fenton-queen-mary-university-of-lon...
 
Description MATURA (MAximising Therapeutic Utility in Rheumatoid Arthritis) Patient Advisory Group (MPAG) meeting 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Patients, carers and/or patient groups
Results and Impact Project members attended a series of patient advisory group meetings and held a focus group specifically on decision support tools at the last one of the year. The focus group involved discussion around the extent to patient managed support for RA, opportunities, and boundaries. This fed into design work and helped shape later formal patient interview and questionnaire studies.
Year(s) Of Engagement Activity 2018,2019
URL http://www.matura.whri.qmul.ac.uk
 
Description Magic of HCI 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Schools
Results and Impact A school talk on Human Computer Interaction on Healthcare using examples from Curzon's research projects and building on the approach developed on the cs4fn project.
Year(s) Of Engagement Activity 2018,2019
 
Description Mittdolcino.com, "Our interview with Prof Fenton: there is no logic to the restrictions", Article and 25 minute interview, 31 August 2021 
Form Of Engagement Activity Engagement focused website, blog or social media channel
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Video interview and article for Italian news site:
https://www.mittdolcino.com/2021/08/31/la-nostra-intervista-al-professor-norman-fenton-non-ce-alcuna-logica-dietro-a-tutte-le-restrizioni/
https://youtu.be/6LFExIjdn7w
Year(s) Of Engagement Activity 2021
URL https://youtu.be/6LFExIjdn7w
 
Description NESTA Public Dialogue on AI 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact Curzon gave a talk / unplugged demonstration on "What is an algorithm for learning" at a day long deliberative workshop Public Dialogue on Artificial Intelligence run by NESTA/Involve in London, 12 June 2018. He also acted as an expert during the day.
Year(s) Of Engagement Activity 2018
URL https://www.involve.org.uk/our-work/our-projects/practice/artificial-intelligence-what-do-public-rea...
 
Description Ocado Technologies Code for Life Launch 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Media (as a channel to the public)
Results and Impact Gave an invited talk and panel session on the need for a "A Fun Inspiring Computing Education for All" and how AI can play a role at the press launch by Ocado Technologies Code for Life AI:MMO, at CodeNode, London, 22 May 2018.
Year(s) Of Engagement Activity 2018
URL https://www.essentialretail.com/news/ocado-unveils-ai-game-for-schools
 
Description PPI Group Work on Personas for Rheumatoid Arthritis 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Patients, carers and/or patient groups
Results and Impact Project members attended a series of PPI group meetings and held a focus group specifically on the project around personas at the last one of the year. All PPI group members were sent copies of personas developed around rheumatoid arthritis to comment on. The focus group involved discussion around the extent to which the personas captured life with the disease, changes to be made to them and new personas that were needed. This led to a series of changes to the personas and two new personas to be researched and written. This fed into design work and helped shape later formal patient interview and questionnaire studies.
Year(s) Of Engagement Activity 2018,2019
 
Description PamBayesian Project: Research Seminars 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Two internal PostDoc members of the PamBayesian team along with one external collaborator gave seminars on the research, findings and collaboration needs of the ongoing PamBayesian project. These seminars were delivered to the Health Data Science and Machine Learning research groups at Technology University Dublin (TUDublin) and for the new Data Science group that started in Jan 2020 at the University of Coventry.
Year(s) Of Engagement Activity 2020
 
Description Presentation of RS-EHR research at Knowledge Management and Data Mining Panel at HEALTHINF 2018 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact Presentation of research to a panel of academic and clinical research fellows at the HEALTHINF 2018 conference presenting a privacy-protecting framework for generating Realistic Synthetic Electronic Health Records (RS-EHR) using clinical expert input and publicly available incidence and treatment statistics
Year(s) Of Engagement Activity 2018
 
Description Royal Society CPD Session for teachers 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Schools
Results and Impact This was a talk about my research related to Machine Learning given as part of a CPD event for teachers run by the Education Outreach team of the Royal Society in February 2018. The day focused on evidence informed education and dissemination of scientific policy into the classroom. After the talk attending teachers split into groups and worked with facilitators to see how they can embed this input into their teaching to support the curriculum.
Year(s) Of Engagement Activity 2018
URL https://teachinglondoncomputing.org/machinelearning/
 
Description Second Annual PAMBAYESIAN Project Workshop 
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 Workshop for researchers, clinicians, and medical companies associated with the PAMBAYESIAN project (see link below)
Year(s) Of Engagement Activity 2019
URL https://pambayesian.org/2019/02/11/687/
 
Description Series of seminars by the PI (Prof Fenton) to medical professsionals and students explaining the PAMBAYESIAN approach 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact A series of invited seminars and workshops were delivered to medical professionals, researchers and students. Many who attended expressed an interest in applying the new methods of risk assessment as they were fully aware of the limitations of current methods. In addition ot leading to further invitations to speak to medical professionals, these events have led to at least three new medical collaborations, with clinicians specialising in three chrnoic conditions that were not part of the orginal proposal: a) pelvic floor syndrome; and b) multiple sclerosis; and 3) chronic heart failure.

The full list of seminars can be found at the URL below
Year(s) Of Engagement Activity 2019,2020
URL http://www.eecs.qmul.ac.uk/~norman/cv.htm#Invited%20seminars%20and%20conference%20presentations%20%2...
 
Description Trends talk for TATA 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact Gave an online talk on Trends in HCI and Healthcare as part of their trends series with both a live audience (with Q&A session) and video archived for others to watch.
Year(s) Of Engagement Activity 2019