Home » Study and Capacity Building (CRIU)

Study and Capacity Building (CRIU)

At CRIU we work with and support a number of postgraduate students whose main research focus is clinical informatics, artificial intelligence and machine learning.

Current students

Reham AlDakhil

Project title:Exploring the factors that influence the clinical decision making when using electronic prescribing as part of the electronic health record (EHR)”

About my research: Electronic prescribing (eP) systems have been advocated as a strategy and solution to reducing medication errors and improving patient safety.  The evidence for the effectiveness of eP shows mixed outcomes, with some errors being reduced, newer computer related errors being introduced and emergence of various workarounds and unintended consequences on workflow.  The degree to which errors may be reduced is often dependent on the level of sophistication of the system in providing clinical decision support.  Basic clinical decision support systems (CDSS) involve a series of checks such as drug-allergy, drug-drug; drug-disease and drug-food interactions or simple dose checking using an underlying clinical database and are often presented in the form of interruptive alerts.  Advanced clinical decision support may include complex dosing support for renal insufficiency and at extremes of age, guidance for medication-related laboratory testing, drug–pregnancy checking and other guided treatment decisions using order sets or pathways including use of algorithms.

Few studies have conducted robust assessments of factors that influence clinical decision making at point of care when using electronic prescribing systems as part of an integrated electronic health record system (EHRS).

The evidence for the effectiveness of electronic prescribing (eP) shows mixed outcomes; emerges of various workarounds, new types of computer-related errors being introduced and unintended consequences on workflow, with some errors being reduced. The involvement of various forms of decision support within the clinical decision support systems (CDSS) from the basic checks of the drug-drug interactions to the advance form of guided treatment decision using order sets including the use of algorithms.

Few studies have conducted robust assessments of factors that influence clinical decision making at the point of care when using electronic prescribing systems as part of an integrated electronic health record system (EHRS).

The PhD project will conduct a mixed-method approach to map the current evidence of the influence of these factors and will explore the potential of eP within the EHR systems to enhance the appropriate use of the system in the medication management process.

About me: I obtained a BSc in Pharmaceutical Sciences from King Saud University, Riyadh. I worked as a hospital pharmacist at NGHA and was part of some automation projects with the ISD. I was awarded an MSc in Health Informatics, KSAU-HS, in 2018.

My main research interests are electronic prescribing, human factors and clinical decision making related to EHR.

Supervisors:

Professor Folkert Asselbergs

Dr Yogini Jani

Dr Wai Keong Wong 


Katarzyna Dziopa

Project title: “Predicting cardiovascular disease in type 2 diabetes patients utilizing contemporary electronic healthcare records”

About my research: Cardiovascular disease is one of the major complications of T2DM, with 32.2% patients experiencing a CVD event annually. Despite the considerable CVD risk associated with T2DM, individual patients’ risk may differ markedly, between 1% to 28%. This individual variation suggests there is an (unmet) need for risk-stratified management, similar to CVD prevention in the general population. In this research we aim to explore the possibilities for CVD risk-stratification inT2DM patients by:

  • Externally validating 20+ frequently used CVD prediction rules in T2DM patients.
  • Using machine learning to identify relevant CVD features from high-dimensional data such as the UK biobank.
  • Evaluating the utility of ensemble learning methodologies compared to existing prediction algorithms.

About me: I have an MSc in Computer Science.

Supervisors:
Professor Folkert W. Asselbergs

Dr Floriaan Schmidt

Professor Nishi Chaturvedi


Joseph Farrington

Project title: “AI-enabled Blood Transfusion System”.

About my research: Blood products are central to many aspects of modern medical care. Ordering and supply of both red cell and platelet units are complicated by the requirement to use specific blood-group or platelet-group types. This is currently carried out by local experts using crude estimates, which leads to over or under ordering of specific blood groups to constitute stock. Patient care may suffer if blood products are not available and treatment is delayed or cancelled if products are not available.

In this project, we will explore various AI methods to build models of making accurate predictions of the blood product usage by learning from local experts and using actual data from NHS and UCLH. Based on the prediction model, optimal approaches of blood products ordering system can be developed and implemented in the long run. Specifically, integration of hospital and laboratory data can define a practical model that can help to order and reduce wastage, and it would be much more powerful if real-time data and deep learning techniques for prediction of demand are utilized. Furthermore, the AI models of blood products recommendation will be evaluated prospectively on the actual retrospective use at UCLH. The application of this technology at scale, would reduce blood wastage and reduce inappropriate use of universal donor blood. We believe that this project fits with the goals of the CDT as it uses applies AI to manage what is a scarce resource (donations from voluntary donors) to match against the transfusion need for patients. This is a unique collaboration between the national blood service (NHSBT), an NHS trust (UCLH) with a fully integrated comprehensive EHR (Epic) and a maturing research platform (EMAP).

About me: I was awarded an MSc in Machine Learning, UCL, and a BA in Natural Sciences, University of Cambridge.

Supervisors:

Dr Ken Li, Machine Learning supervisor

Dr Wai Keong, Clinical Informatics supervisor


Matt Wilson

Project title:Exploiting natural clinical variation using observational and experimental methods to create an embedded learning healthcare system for Critical Care”

About my research: Many routine clinical decisions in critical care lack a clear evidence base. In these situations of equipoise, clinicians base decisions on experience and acumen. As clinicians vary, so do decisions, contributing to variation in outcomes for patients.

Current practice is to reduce all variation via the application of guidelines, protocols and audit. However, this fails to preserve scenarios where clinicians deviate from guidelines justifiably, resulting in improved outcomes for patients. 

My PhD will explore the feasibility of addressing this question using a combination of observational techniques to map existing variation and a novel 'nudge' tool as part of a randomised, embedded clinical trial of routine critical care interventions. 

About me: I graduated from St Bart's and The Royal London Medical School in 2011 and work as an anaesthetic registrar. I completed an MSc in Health Data Science in 2018 and am currently an MRC Doctoral Training Partnership student. My main research interests include investigating causal relationships using natural experimental methods with observational data and advancing electronic health record systems for clinician learning and feedback. 

Supervisors:

Professor Folkert Asselbergs

Dr Steve Harris

Dr Roma Klapaukh