techniques for risk models, Bayesian networks, decision support systems, critical systems
Dr William Marsh is Principal Investigator on a new project funded by the Alan Turing Institute: 'Knowledge Discovery from Health Use Data' (KNIFE).
The increasing use and capability of Electronic Health Record (EHR) systems has made available large collections of data about patients’ use of the different health services, treatments and prescriptions. This data has many potential uses (discovering causes, optimising health delivery, choosing treatment and more). However, there are challenges to overcome before these benefits can be achieved.
• Challenge of Understanding the Data and It Potential Use. The data arise from the operation of the health services, so the understanding of the data contents is embedded in the health community and not accessible to the wider AI and ML communities.
• Challenge of Knowledge Elicitation and Modelling. Achieving the full potential from the data
requires knowledge of health care processes so this may need to be modelled for data analysis.
• Statistical Modelling Challenge. Existing data analysis approaches often extract a ‘flat’ dataset from the underlying ‘relational’ structure of the date. New techniques avoiding this (e.g. Statistical Relational Learning) might allow new types of queries but their practical applicability is unknown.
• Challenge of Efficient and Acceptable Data Handling. Existing studies using data from EHR systems, require extensive ‘data wrangling’ to extract and cleanse a usable dataset. This work is largely manual and very time consuming: can this be improved?
The overall objective of the project is to lay the foundations for a transformative approach to patient-linked health data, making it accessible for both medical and data science researchers to fully exploit.
William's other research aims are to develop better ways to build useful risk and decision making techniques, using a combination of data and knowledge (or expertise). He mainly works with Bayesian networks and prefers to work with the 'end users' who are making decisions. He is currently collaborating with several groups of clinicians to build decision support systems for medical decision problems and also collaborates with several industry groups on techniques for risk models and other aspects of Safety Engineering, primarily in the railway industry.
Publications are here
Kyrimi E, Dube K, Fenton N
, Fahmi A, Neves MR, Marsh W
and McLachlan S (2021). Bayesian networks in healthcare: What is preventing their adoption? Artificial Intelligence in Medicine
vol. 116, 10.1016/j.artmed.2021.102079
Lowe C, Hanuman Sing H, Browne M, Alwashmi MF, Marsh W
and Morrissey D (2021). Usability Testing of a Digital Assessment Routing Tool: Protocol for an Iterative Convergent Mixed Methods Study. Jmir Res Protoc
vol. 10, (5) 10.2196/27205
Hill A, Joyner CH, Keith-Jopp C, Yet B, Sakar CT, Marsh W
and Morrissey D (2021). A bayesian network decision support tool for low back pain using a RAND appropriateness procedure: proposal and internal pilot study. Jmir Research Protocols
vol. 10, (1) 10.2196/21804
Fahmi A, Soyel H, Marsh W
, Curzon P, MacBrayne A and Humby F (2020). From personalised predictions to targeted advice: Improving self-management in rheumatoid arthritis. Studies in Health Technology and Informatics
vol. 275, 62-66. 10.3233/SHTI200695
Zhang H and Marsh DWR
(2020). Managing Infrastructure Asset: Bayesian Networks for Inspection and Maintenance Decisions Reasoning and Planning. Elsevier Reliability Engineering and System Safety
vol. 207, 107328-107328. 10.1016/j.ress.2020.107328
Ronaldson A, Freestone MC
, Zhang H, Marsh W
and Bhui K (2020). Using structural equation modelling in routine clinical data: Depression, diabetes, and use of Accident & Emergency (Preprint). Jmir Medical Informatics 10.2196/22912
Perkins ZB, Yet B, Sharrock A, Rickard R, Marsh W
, Rasmussen TE and Tai NRM (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. Annals of Surgery
vol. 272, (4) 564-572. 10.1097/SLA.0000000000004132
Zhang H and Marsh DWR
(2020). Multi-state deterioration prediction for infrastructure asset: Learning from uncertain data, knowledge and similar groups. Information Sciences
vol. 529, 197-213. 10.1016/j.ins.2019.11.017
Wilk M, Marsh DRW, de Freitas S and Prowle J (2020). Predicting length of stay in hospital using electronic records available at the time of admission. Studies in Health Technology and Informatics
vol. 270, 377-381. 10.3233/SHTI200186
Marsden MER, Mossadegh S, Marsh W
and Tai N (2020). Development of a major incident triage tool: The importance of evidence from implementation studies. Bmj Military Health
vol. 166, (3) 10.1136/jramc-2018-001057
Waite J, Curzon P, Marsh W
and Sentance S (2020). Difficulties with design: The challenges of teaching design in K-5 programming. Elsevier Bv Computers & Education
Kyrimi E, Mossadegh S, Tai N and Marsh W
(2020). An incremental explanation of inference in Bayesian networks for increasing model trustworthiness and supporting clinical decision making. Elsevier Artificial Intelligence in Medicine
vol. 103, 10.1016/j.artmed.2020.101812
Perkins ZB, Yet B, Marsden M, Glasgow S, Marsh W
, Davenport R, Brohi K and Tai NRM (2020). Early Identification of Trauma-induced Coagulopathy: Development and Validation of a Multivariable Risk Prediction Model. Ann Surg 10.1097/SLA.0000000000003771
Zhang H and Marsh DWR
(2018). Generic Bayesian network models for making maintenance decisions from available data and expert knowledge. Proceedings of The Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability
vol. 232, (5) 505-523. 10.1177/1748006X17742765
Perkins ZB, Yet B, Glasgow S, Marsh DWR
, Tai NRM and Rasmussen TE (2018). Long-term, patient-centered outcomes of lower-extremity vascular trauma. The Journal of Trauma and Acute Care Surgery
vol. 85, (1S Suppl 2) S104-S111. 10.1097/TA.0000000000001956
MCLACHLAN S, Potts HWW, Dube K, Buchanan D, Lean S, Gallagher T, Johnson O, DALEY B, Marsh W
and FENTON N
(2018). The Heimdall framework for supporting characterisation of learning health systems. Bcs Journal of Innovation in Health Informatics
vol. 25, (2) 10.14236/jhi.v25i2.996
Waite JL, CURZON P, MARSH D
, Sentance S and Hawden-Bennett A (2018). Abstraction in action: K-5 teachers' uses of levels of abstraction,
particularly the design level, in teaching programming.
, Editors: Kalelioglu F and Allsop Y. International Journal of Computer Science Education in Schools
vol. 2, (1) 14-40. 10.21585/ijcses.v2i1.23
McLachlan S, Dube K, Buchanan D, Lean S, Johnson O, Potts H, Gallagher T, Marsh W
and Fenton N
(2018). Learning health systems: The research community awareness challenge. Journal of Innovation in Health Informatics
vol. 25, (1) 38-40. 10.14236/jhi.v25i1.981
Yet B, Marsh W
and Morrissey D (2018). Towards an Evidence-Based Decision Support Tool for Management of Musculoskeletal Conditions. Studies in Health Technology and Informatics
vol. 255, 175-179. 10.3233/978-1-61499-921-8-175
Waite JL, curzon P, marsh D
and Sentance S (2017). K-5 Teachers' Uses of Levels of Abstraction Focusing on Design.
Coid JW, Ullrich S, Kallis C, Freestone M
, Gonzalez R, Bui L, Igoumenou A, Constantinou A, Fenton N
, Marsh W
, Yang M, DeStavola B, Hu J, Shaw J, Doyle M, Archer-Power L, Davoren M, Osumili B, McCrone P, Barrett K, Hindle D and Bebbington P (2016). Improving risk management for violence in mental health services: a multimethods approach. Programme Grants For Applied Research
vol. 4, (16) 1-408. 10.3310/pgfar04160
Mossadegh S, Yet B, Perkins Z, Marsh W
and Tai N (2016). Predictive Accuracy of a Civilian Bayesian Network Trauma Tool in a Military Cohort and Applicability to Trauma Performance Improvement. British Journal of Surgery
vol. 103, 96-96.
Yet B, Perkins ZB, Tai NRM and Marsh DWR
(2016). Clinical evidence framework for Bayesian networks. Knowledge and Information Systems
vol. 50, (1) 117-143. 10.1007/s10115-016-0932-1
, Nur K, Yet B and Majumdar A (2016). Using operational data for decision making: a feasibility study in rail maintenance. Safety and Reliability
vol. 36, (1) 35-47. 10.1080/09617353.2016.1148923
Perkins ZB, Yet B, Glasgow S, Cole E, Marsh W
, Brohi K, Rasmussen TE and Tai NRM (2015). Meta-analysis of prognostic factors for amputation following surgical repair of lower extremity vascular trauma. British Journal of Surgery
vol. 102, (5) 436-450. 10.1002/bjs.9689
Perkins ZB, Yet B, Glasgow S, Cole E, Marsh W
, Brohi K, Rasmussen TE and Tai NRM (2015). Meta-analysis of prognostic factors for amputation following surgical repair of lower extremity vascular trauma. John Wiley and Sons Ltd British Journal of Surgery 10.1002/bjs.9689
Yet B, Perkins ZB, Rasmussen TE, Tai NRM and Marsh DWR
(2014). Combining data and meta-analysis to build Bayesian networks for clinical decision support. J Biomed Inform
vol. 52, 373-385. 10.1016/j.jbi.2014.07.018
Bearfield G, Holloway A and Marsh W
(2013). Change and safety: decision-making from data. Proceedings of The Institution of Mechanical Engineers Part F-Journal of Rail and Rapid Transit
vol. 227, (6) 704-714. 10.1177/0954409713498381
, Yet B, Bastani K, Raharjo H, Lifvergren S and Bergman B (2013). Decision Support System for Warfarin Therapy Management Using Bayesian Networks. Elsevier Decision Support Systems
vol. 55, (2) 488-498. 10.1016/j.dss.2012.10.007
and Bearfield G (2008). Generalizing event trees using Bayesian networks. Proceedings of The Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability
vol. 222, (2) 105-114. 10.1243/1748006XJRR131
and Bearfield G (2008). Generalizing event trees using Bayesian networks. Proc. Imeche, Parto: J. Risk and Reliability
vol. 222, 105-114-105-114.
WICHMANN B, CANNING A, CLUTTERBUCK D, WINSBORROW L, WARD N and MARSH D
(1995). Industrial Perspective on Static Analysis. Iee-Inst Elec Eng Software Engineering Journal
vol. 10, (2) 69-75.