PhD level

Research pillar: Digital Health Validitron
Supervisor: Professor Wendy Chapman
Secondary supervisors: Dr Kit Huckvale, Dr Daniel Capurro

Project description

This is a program of research with the option to fit several PhD projects. Research has identified explicit barriers and enablers for implementing and scaling remote monitoring and virtual models of care. We have developed a digital sandbox / ecosystem with capacity for connecting simulated devices, electronic medical records, and apps. This sandbox provides the opportunity to address many of the barriers/enablers such as:

• How to create user-friendly app interfaces for collecting data, such as for older adults
• Methods for bridging the digital divide by making technology available to remote areas, for example
• Workflows that support clinicians proactively monitoring patient-generated data
• New governance and payment models for virtual care
• Feasible ways to capture physical assessments through remote devices and integrating the information in existing models such as telehealth visits
• Governance models for person-centred data control and sharing
• What are the unintended consequences of virtual models of care?

Research Pillar:  Clinical Data Science
Supervisor: Dr Daniel Capurro

Project description

This is a program of research with the option to fit several PhD projects. We aim to adapt and expand the use of process mining techniques to enable the use of data from electronic health records to analyze healthcare performance from the process perspective and improve our understanding of healthcare processes.

Through a series of use cases, we will be using electronic medical record data to develop methods to:

• measure unexplained clinical variability
• measure diffusion of clinical innovations into clinical practice
• assess adherence to clinical guidelines
• understand how collaboration patterns among healthcare professionals can impact patient outcomes
• facilitate the construction of event logs using clinical ontologies, study barriers and facilitators to translating process mining findings into clinical practice.

Research pillar: Health Informatics & Data Science 
Primary Supervisor: Dr Daniel Capurro
Secondary supervisors: Dr Douglas Pires

Project description

This is a program of research with the option to fit several PhD projects. The emergence of digital diagnostic algorithms (ie. ML/AI) have the possibility to significantly improve our diagnostic capabilities. However, when they are deployed to increasingly healthier sections of the population, they carry the risk of generating cases of overdiagnosis.

Overdiagnosis is not a false positive (wrongly labelling a healthy patient as 'diseased') nor it is a misdiagnosis (diagnosing a sick patient with the wrong condition). Overdiagnosis happens when a patient meets the existing diagnostic criteria for a clinical condition but making the diagnosis will not bring any benefit to this patient (improved quality of life, increased survival) but can generate additional unnecessary tests, continuous surveillance, overtreatment, and psychological stress.

Through a series of projects, we will be exploring different dimensions of this problem:

• Perceptions and understanding of the phenomenon by researchers and clinicians designing and implementing digital diagnostic algorithms
• Perceptions and understanding of the phenomenon by patients and caregivers
• Data driven approaches to measuring and reducing the risk of overdiagnosis

Research pillar: Health Informatics & Data Science
Primary Supervisor: Dr Douglas Pires
Secondary supervisor: Dr Daniel Capurro

Project description

While the majority of patients admitted to the intensive care unit (ICU) are expected to have a short ICU length of stay (LoS), a small proportion will instead progress into a syndrome called Persistent Critical Illness (PerCI). Patients who develop PerCI, have an ongoing reliance on intensive care therapies. That is mainly determined by their chronic comorbidities, rather than the reason for which they were first admitted to the ICU.

While only a small proportion of patients remain in the ICU for a prolonged amount of time, the ones who do show worse outcomes. Such outcomes account for a disproportionate number of ICU bed-days and as a consequence, resources. The impact of this group is expected to be of even greater significance in low- and middle-income countries, where fewer ICU beds are available and resources may be limited.

This project will aim to use intensive care databases to assess whether patient information can be used to predict persistent critical illness and how PerCI patient trajectories compare with those that stay for shorter periods of time.