Skip to main content
School of Electronic Engineering and Computer Science

Dr William Marsh

William

Senior Lecturer

Email: d.w.r.marsh@qmul.ac.uk
Telephone: +44 20 7882 5254
Room Number: Peter Landin, CS 420a
Website: http://www.eecs.qmul.ac.uk/~william
Office Hours: Wednesday 10:00-12:00

Teaching

Embedded Systems (Postgraduate/Undergraduate)

This module provides a practice-oriented introduction to embedded real-time systems. The main topics are (1) Modelling and simulation in UML and state-of-the-art tools; (2) Basic concepts of micro-controllers; (3) Real-time systems with interrupts and schedulers; (4) Real-time operating systems: processes and communication; (5) Energy aware design and construction; (6) Debugging and testing as part of software development processes.

Statistics for Artificial Intelligence and Data Science (Postgraduate)

This module has two components. The first introduces students to the use of probability and statistics in the context of data analysis. The module starts with basics of descriptive statistics and probability distributions. Then we go on with applied statistics techniques, such as visualisation, fitting probability distributions, time-series analysis, and hypothesis testing, which are all fundamental to the exploration, insight extraction, and modelling activities that are fundamental in handling data, of any size. The second covers some basic matrix algebra, including matrix multiplication and diagonalisation.

Research

Research Interests:

Medical Decision Support Models: Data, Knowledge and Evidence

Can data be used for decision-making? In many applications there are not enough data, key values are not directly observed or the problem requires reasoning about change. In these cases, it is better to combine data and knowledge for building a decision model.

Many medical decision problems fit this pattern. However, given the long history of clinical trials, clinicians are reluctant to assume an understanding of causes even when trials are completely impractical. Recent work on decision making in trauma surgery has shown the potential of causal models implemented using Bayesian networks. However, there are still many challenges before the use of these models can become routine.

Safety, Reliability And Risk: Modelling Accidents & Incident Causes

Analysing what can go wrong is fundamental for assessing risk in safety systems. Existing approaches have a number of deficiencies: (1) human behaviour and technical failures are poorly integrated (2) model created for system approval are often not used when a system is in operation (3) information on incidents and procedural compliance is not used to update risks.

The aim of the research is to extend existing accident-based modelling techniques to resolve these problems. Recent work has proposed a new model structure using a Bayesian network for causal modelling from accident / incident data, with the aim of predicting the likely safety / reliability improvement that would be achieved by changes in the operation of a system at a specific location.

Publications

    • Wohlgemut JM, Kyrimi E, Stoner RS et al. (2022), The outcome of a prediction algorithm should be a true patient state rather than an available surrogate $nameOfConference


    • Marsden M, Perkins Z, Marsh W et al. (2022), 92 Evaluation of an Artificial Intelligence (AI) System to Augment Clinical Risk Prediction of Trauma Induced Coagulopathy: A Prospective Observational Study $nameOfConference


    • Gulle H, Yuceturk H, Sakar C et al. (2022), Can Bayesian statistical approaches reduce the questionnaire burden for respondents when PROMs and PREMs are administered electronically? $nameOfConference


    • Daley BJ, Ni’Man M, Neves MR et al. (2022), mHealth apps for gestational diabetes mellitus that provide clinical decision support or artificial intelligence: A scoping review $nameOfConference


    • Lowe C, Hanuman Sing H, Marsh W et al. (2021), Validation of a Musculoskeletal Digital Assessment Routing Tool: Protocol for a Pilot Randomized Crossover Noninferiority Trial. $nameOfConference


    • Hill A, Keith-Jopp C, Joyner C et al. (2021), Developing BENDi: A BayEsian Network DecIsion support tool for managing low back pain $nameOfConference


    • Perkins ZB, Yet B, Marsden M et al. (2021), Early Identification of Trauma-induced Coagulopathy Development and Validation of a Multivariable Risk Prediction Model $nameOfConference


    • Neves MR, Daley BJ, Hitman GA et al. (2021), Causal Dynamic Bayesian Networks for the Management of Glucose Control in Gestational Diabetes $nameOfConference


    • Kyrimi E, Dube K, Fenton N et al. (2021), Bayesian networks in healthcare: What is preventing their adoption? $nameOfConference


    • Lowe C, Sing HH, Browne M et al. (2021), Usability testing of a digital assessment routing tool: Protocol for an iterative convergent mixed methods study $nameOfConference


    • Hill A, Joyner CH, Keith-Jopp C et al. (2021), A bayesian network decision support tool for low back pain using a RAND appropriateness procedure: proposal and internal pilot study $nameOfConference


    • Fahmi A, Soyel H, Marsh DWR et al. (2020), From Personalised Predictions to Targeted Advice: Improving Self-Management in Rheumatoid Arthritis Integrated Citizen Centered Digital Health and Social Care


    • Fahmi A, Soyel H, Marsh W et al. (2020), From personalised predictions to targeted advice: Improving self-management in rheumatoid arthritis $nameOfConference


    • Zhang H, Marsh DWR (2021), Managing Infrastructure Asset: Bayesian Networks for Inspection and Maintenance Decisions Reasoning and Planning $nameOfConference


    • Ronaldson A, Freestone MC, Zhang H et al. (publicationYear), Using structural equation modelling in routine clinical data: Depression, diabetes, and use of Accident & Emergency (Preprint) $nameOfConference


    • Fahmi A, Macbrayne A, Kyrimi E et al. (2020), Causal Bayesian Networks for Medical Diagnosis: A Case Study in Rheumatoid Arthritis $nameOfConference


    • Perkins ZB, Yet B, Sharrock A et al. (2020), Predicting the Outcome of Limb Revascularization in Patients With Lower-extremity Arterial Trauma: Development and External Validation of a Supervised Machine-learning Algorithm to Support Surgical Decisions $nameOfConference


    • Zhang H, Marsh DWR (2020), Multi-state deterioration prediction for infrastructure asset: Learning from uncertain data, knowledge and similar groups $nameOfConference


    • Kyrimi E, Neves MR, McLachlan S et al. (2020), Medical idioms for clinical Bayesian network development $nameOfConference

    • Kyrimi E, Raniere Neves M, Mclachlan S et al. (2020), Medical idioms for clinical Bayesian network development $nameOfConference


    • Wilk M, Marsh DW, de Freitas S et al. (2020), Predicting length of stay in hospital using electronic records available at the time of admission $nameOfConference


    • Marsden MER, Mossadegh S, Marsh W et al. (2020), Development of a major incident triage tool: The importance of evidence from implementation studies $nameOfConference


    • Kyrimi E, Mossadegh S, Tai N et al. (2020), An Incremental Explanation of Inference in Hybrid Bayesian Networks for Increasing Model Trustworthiness and Supporting Clinical Decision Making $nameOfConference

    • Waite J, Curzon P, Marsh W et al. (2020), Difficulties with design: The challenges of teaching design in K-5 programming $nameOfConference


    • Kyrimi E, Mossadegh S, Tai N et al. (2020), An incremental explanation of inference in Bayesian networks for increasing model trustworthiness and supporting clinical decision making $nameOfConference


    • Neves MR, Marsh DWR (2019), Modelling the impact of AI for clinical decision support $nameOfConference


    • Waite JL, CURZON P, MARSH DW et al. (2018), Comparing K-5 teachers’ reported use of design in teaching programming and planning in teaching writing WiPSCE 2018 (13th Workshop in Primary and Secondary Computing Education)


    • Zhang H, Marsh DWR (2018), Generic Bayesian network models for making maintenance decisions from available data and expert knowledge $nameOfConference


    • Perkins ZB, Yet B, Glasgow S et al. (2018), Long-term, patient-centered outcomes of lower-extremity vascular trauma $nameOfConference


    • ZHANG H, MARSH DWR (2018), Towards A Model-Based Asset Deterioration Framework Represented by Probabilistic Relational Models European Safety and Reliability Conference ESREL 2018

    • MCLACHLAN S, Potts HWW, Dube K et al. (2018), The Heimdall framework for supporting characterisation of learning health systems $nameOfConference


    • Waite JL, CURZON P, MARSH D et al. (2018), Abstraction in action: K-5 teachers' uses of levels of abstraction, particularly the design level, in teaching programming $nameOfConference


    • McLachlan S, Dube K, Buchanan D et al. (2018), Learning health systems: The research community awareness challenge $nameOfConference


    • Yet B, Marsh W, Morrissey D (2018), Towards an Evidence-Based Decision Support Tool for Management of Musculoskeletal Conditions $nameOfConference


    • Waite JL, curzon P, marsh D et al. (2017), K-5 Teachers' Uses of Levels of Abstraction Focusing on Design WiPSCE 2017

    • Perkins ZB, Yet B, Glasgow S et al. (2017), Predicting limb viability following lower extremity vascular trauma $nameOfConference

    • Zhang H, Marsh DWR (2017), Bayesian network models for making maintenance decisions from data and expert judgment $nameOfConference

    • Coid JW, Ullrich S, Kallis C et al. (2016), Improving risk management for violence in mental health services: a multimethods approach $nameOfConference


    • Waite JL, Curzon P, marsh D et al. (2016), Abstraction and Common Classroom Activities WiPSCE 2016 11th Workshop in Primary and Secondary Computing Education


    • Fenton N, Neil M, Lagnado D et al. (2016), How to model mutually exclusive events based on independent causal pathways in Bayesian network models $nameOfConference


    • MARSH DWR, Kyrimi E (publicationYear), A Progressive Explanation of Inference in ‘Hybrid’ Bayesian Networks for Supporting Clinical Decision Making Conference on Probabilistic Graphical Models

    • Mossadegh S, Yet B, Perkins Z et al. (2016), Predictive Accuracy of a Civilian Bayesian Network Trauma Tool in a Military Cohort and Applicability to Trauma Performance Improvement $nameOfConference

    • Ahmed N, Shamsujjoha M, Ali MNY et al. (2016), An efficient REDCap based data collection platform for the Primary Immune Thrombocytopenia and its analysis over the conventional approaches $nameOfConference


    • Mossadegh S, Kyrimi E, Marsh W et al. (2016), Implementation science: a Bayesian prediction tool for acute traumatic coagulopathy Society of Academic and Research Surgery Annual Meeting


    • Yet B, Perkins ZB, Tai NRM et al. (2016), Clinical evidence framework for Bayesian networks $nameOfConference


    • Constantinou AC, Fenton N, Marsh W et al. (2016), From complex questionnaire and interviewing data to intelligent Bayesian network models for medical decision support $nameOfConference


    • Marsh W, Nur K, Yet B et al. (2016), Using operational data for decision making: a feasibility study in rail maintenance $nameOfConference


    • CONSTANTINOU AC, Freestone M, Marsh W et al. (2015), Causal inference for violence risk management and decision support in forensic psychiatry $nameOfConference


    • Constantinou AC, Yet B, Fenton N et al. (2015), Value of information analysis for interventional and counterfactual Bayesian networks in forensic medical sciences $nameOfConference


    • Constantinou AC, Freestone M, Marsh W et al. (2015), Risk assessment and risk management of violent re-offending among prisoners $nameOfConference


    • Perkins ZB, Yet B, Glasgow S et al. (2015), Meta-analysis of prognostic factors for amputation following surgical repair of lower extremity vascular trauma $nameOfConference


    • Perkins ZB, Yet B, Glasgow S et al. (2015), Meta-analysis of prognostic factors for amputation following surgical repair of lower extremity vascular trauma $nameOfConference


    • Yet B, Perkins ZB, Rasmussen TE et al. (2014), Combining data and meta-analysis to build Bayesian networks for clinical decision support. $nameOfConference


    • Perkins ZB, Yet B, Glasgow S et al. (2014), Prognostic Factors for Amputation Following Surgical Repair of Lower Extremity Vascular Trauma: A Systematic Review and Meta-Analysis of Observational Studies $nameOfConference


    • Yet B, Perkins Z, Fenton N et al. (2014), Not just data: a method for improving prediction with knowledge. $nameOfConference


    • Yet B, Marsh DWR (2014), Compatible and incompatible abstractions in Bayesian networks $nameOfConference


    • Yet B, Perkins Z, Tai N et al. (2014), Explicit evidence for prognostic Bayesian network models. $nameOfConference


    • Winther R, Marsh W (2014), Hazards, accidents and events-A land of confusing terms $nameOfConference

    • Yet B, Perkins Z, Fenton N et al. (2014), Not just data: A method for improving prediction with knowledge $nameOfConference


    • Bearfield G, Holloway A, Marsh W (2013), Change and safety: decision-making from data $nameOfConference


    • Perkins Z, Yet B, Glasgow S et al. (2013), EARLY PREDICTION OF TRAUMATIC COAGULOPATHY USING ADMISSION CLINICAL VARIABLES $nameOfConference

    • MARSH DWR, Yet B, Bastani K et al. (2013), Decision Support System for Warfarin Therapy Management Using Bayesian Networks $nameOfConference


    • Sivell S, Marsh W, Edwards A et al. (2012), Theory-based design and field-testing of an intervention to support women choosing surgery for breast cancer: BresDex $nameOfConference


    • Bearfield G, Marsh W (2010), Causal Modelling of Lower Consequence Rail Safety Incidents European Safety and Reliability Conference 2010 (ESREL 2010)

    • Marsh DWR, Bearfield GJ (2009), Why Risk Models should be Parameterised MASR-2009 Modeling and Analysis of Safety and Risk in Complex Systems

    • Fenton N, Neil M, Marsh W et al. (2008), On the effectiveness of early life cycle defect prediction with Bayesian Nets $nameOfConference


    • Marsh DWR, Bearfield G (2008), Generalizing event trees using Bayesian networks $nameOfConference


    • Marsh DWR, Bearfield G (2008), Generalizing event trees using Bayesian networks $nameOfConference

    • Dray P, Bearfield GJ, Marsh DWR (2007), Constructing Scalable and Parameterised System Wide Risk Models $nameOfConference

    • Marsh DWR, Bearfield GJ (2007), Merging event trees using Bayesian networks $nameOfConference

    • Fenton N, Neil M, Marsh W et al. (2007), Predicting software defects in varying development lifecycles using Bayesian nets $nameOfConference


    • Fenton NE, Neil M, Marsh W et al. (2007), Project Data Incorporating Qualitative Factors for Improved Software Defect Prediction ICSE PROMISE (Predictive Models in Software Engineering) 07


    • Marsh W, Bearfield G (2007), Representing parameterised fault trees using Bayesian networks $nameOfConference


    • Neil M, Fenton N, MARSH DWR (2006), A Software Metrics Challenge: Data for Project Prediction 29th International Conference on Software Engineering (ICSE 2007), Minneapolis, USA

    • Neil M, FENTON NE, Marsh W et al. (2006), Predicting Software Defects in Varying Development Lifecycles using Bayesian Nets ICSE (International Conference on Software Engineering) 2006, May 20-28, 2006, Shanghai, China

    • Bearfield G, Marsh W (2005), Generalising event trees using Bayesian networks with a case study of train derailment $nameOfConference


    • Fenton N, Marsh W, Neil M et al. (2004), Making resource decisions for software projects $nameOfConference


    • Marsh W, Bearfield G (2004), Using Bayesian networks to model accident causation in the UK railway industry $nameOfConference


    • Marsh W (1997), Harmonisation of defence standards for safety-critical software $nameOfConference


    • WICHMANN B, CANNING A, CLUTTERBUCK D et al. (1995), Industrial Perspective on Static Analysis $nameOfConference

    • CARRE B, GARNSWORTHY J, MARSH W (1992), SPARK - A SAFETY - RELATED ADA SUBSET $nameOfConference

Back to top