This project is no longer listed on FindAPhD.com and may not be available.
Click here to search FindAPhD.com for PhD studentship opportunitiesAbout the Project
Background
GP practices in England provide over 30 million appointments per month. Some are for urgent medical conditions that require urgent treatment where delays in care can lead to patient harm. Since 2020, almost all GP practices in England have provided online consultations where patients can request help over the internet. Online consultations are received by GP practices unprioritised which can worsen care delays. A potential solution is for the online consultation system to triage patients using artificial intelligence (AI). AI Triage is already used in NHS GP practices despite there being little evidence for its safety or whether this varies based on patient characteristics.
Aim
To evaluate the safety of AI Triage in GP practices and whether it varies according to patient clinical and sociodemographic characteristics including age, sex, socioeconomic deprivation, and ethnicity.
Methods
The candidate will evaluate exemplar online consultation systems with AI Triage (e.g. Patchs, www.patchs.ai). They will join a wider team funded by NIHR (NIHR153121). The project will comprise three workstreams and will use Systems Thinking models (e.g. SEIPS) as an overarching theoretical framework:
WS1 – Literature review: Systematic review of the research literature on AI Triage with a focus on implications for patient safety outcomes and safety inequalities. The outputs will be used to select aspects of patient safety to investigate in workstreams 2 and 3.
WS2 – Qualitative: In-depth ethnographic case studies at purposively selected GP practices supplemented by interviews with patients and GP practice staff. The objective will be to explore how and why AI Triage may affect safety in different patient groups, and how negative impacts could be minimised or eliminated.
WS3 – Quantitative: Controlled interrupted time series analysis of patient safety outcomes, and analysis of counterfactual AI Triage predictions. Subgroup analyses and statistical modelling will assess for the influence of patient clinical and sociodemographic characteristics.
Workstreams 2 and 3 will be conducted concurrently to integrate their findings. A workshop will combine findings from all three workstreams.
Collaborative partners
The candidate will develop links with industry by working with the Patchs team, national NHS policymakers by working with NHS Digital, and Systems Thinking experts aligned with the PSRC.
Impact
Findings will be used to inform NHS Digital policy on how to design and evaluate AI Triage in practice, and to create ‘how-to’ guides for GP practices and patients on how best to use AI Triage.
Training and support
The PhD candidate will be supervised by experts in online consultations, qualitative and quantitative methodologies.
Entry Requirements
Candidates are expected to hold (or be about to obtain) a minimum upper second class undergraduate honours degree (or equivalent) in a related area / subject.
For information on how to apply for this project, please visit the Faculty of Biology, Medicine and Health Doctoral Academy website (https://www.bmh.manchester.ac.uk/study/research/apply/). Interested candidates must first make contact with the Primary Supervisor prior to submitting a formal application, to discuss their interest and suitability for the project. On the online application form select PhD Medicine.
Funding Notes
Funding for this project is through Joint SPCR-GM PSRC PhD Studentship for a duration of 3 years and covers UK tuition fees, running costs and annual stipend. Due to funding restrictions the studentship is only open to UK nationals.

Search suggestions
Based on your current searches we recommend the following search filters.
Check out our other PhDs in Manchester, United Kingdom
Start a New search with our database of over 4,000 PhDs

PhD suggestions
Based on your current search criteria we thought you might be interested in these.
Integration of Internet of Things (IoT) and Artificial Intelligence (AI) for Flame Monitoring and Safety Enhancement in Industrial Settings
Canterbury Christ Church University
Artificial Intelligence enabled Distributed Edge-Centric Cellular Networks
University of York
Artificial Intelligence for Virtual Characters in Computer Graphics and Computer Animation
Durham University