Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Exploring the value of using large third-party artificial intelligence models in Congenital Heart Disease


   MRC GW4 BioMed Doctoral Training Partnership

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Prof Massimo Caputo  No more applications being accepted  Funded PhD Project (Students Worldwide)

About the Project

Large language models (LLMs) are an artificial intelligence approach that have recently been shown to have extremely promising ability, for example, for conversing with humans or performing tasks such as summarising or extracting information from text. This project will investigate the potential opportunities and challenges of using LLMs in cardiovascular research and explore the use of these models for deriving medical reports from the Medical Information Mart for Intensive Care (MIMIC-III) critical care database as an example. 

Aim:

This project will investigate the opportunities and challenges of large language models to assist cardiovascular research and explore applications of large language models for deriving medical reports from MIMIC-III data as an example. Background: Large language models (LLMs) are an artificial intelligence approach that typically have a very large number of parameters (e.g. millions or billions) and have been trained on extremely large datasets. In recent years these models have gained substantial attention, as they have demonstrated extremely promising performance for being used for a variety of tasks, and they are set to disrupt the way tasks are conducted across many areas of life. They are already being adopted to help scientists do their work more efficiently, for example, to summarise large amounts of information for existing data across the internet. In cardiovascular research there are also opportunities to exploit these pre-trained models, such as for assisting with summarisation, information extraction or prediction using textual data. Objective 1: To review the literature and availability of LLMs, to determine the opportunities and challenges for using LLMs to assist cardiovascular research. This could include considerations of: (1) The LLMs that are available and the differences between them (e.g. in terms of performance/ capability, environmental impact); (2) limitations of using LLMs for cardiovascular research, for example hallucinations, ethical considerations, model interpretability and the potential bias in these models; (3) performance evaluation methods for comparing generated text against gold standard reports; (4) the broad tasks that LLMs have been used for in clinical medicine and what performance have LLMs achieved on these tasks. Objective 2: Determine the extent that LLMs can be used to summarise or extract information from MIMIC-III data. The student will investigate using LLMs to derive diagnostic information from publicly available clinical notes that can be compared to the gold standard diagnosis. The student will be able to derive diagnostic rationales. The student will also explore using LLMs to generate treatment plans based on imaging reports and clinician’s notes, deriving rationale for such plans. This objective will use open source LLMs that can be downloaded and run on the University’s compute services, as they will be applied to sensitive Careflow patient notes data in Objective 3, that cannot be transferred to external services. Objective 3: Explore the use of the LLM on Omacp and Surgical Pearl patient notes to generate treatment plans for patients. The student will set up an analytical pipeline that uses a LLM to derive retrospective treatments plans from clinical notes data available in 1000 Omacp and Surgical Pearl participants. This will use the approaches developed as part of Objective 2 to derive retrospective treatment plans and explore the performance in comparison to gold standard treatment plans in hindsight. The specific congenital abnormalities to be explored can be chosen depending on the student’s interests.  

Lead Supervisor Name: Prof Massimo Caputo Affiliation Bristol College/Faculty of Health Sciences Department/School Bristol Medical School

Co-Supervisors: Serban Stoica, Tim Dong [Email Address Removed]

Research Theme: Translational Health Sciences

How to apply  

This project is part of the GW4 BioMed2 MRC DTP projects.

 Please complete an application to the GW4 BioMed2 MRC DTP for an ‘offer of funding’. If successful, you will also need to make an application for an 'offer to study' to your chosen institution.  

 Please complete the online application form linked from our website by 5.00pm on Wednesday, 1st November 2023. If you are shortlisted for interview, you will be notified from Tuesday 19th December 2023. Interviews will be held virtually on 24th and 25th January 2024. Studentships will start on 1st October 2024.  

Enquiries:  

For enquiries regarding the application procedures please contact [Email Address Removed]  

 For project enquiries contact Tim Dong [Email Address Removed]

Computer Science (8) Medicine (26)

Funding Notes

This studentship is funded through GW4BioMed2 MRC Doctoral Training Partnership. It consists of UK and international tuition fees, as well as a Doctoral Stipend matching UK Research Council National Minimum (£18,622 p.a. for 2023/24, updated each year). 

Additional research training and support funding of up to £5,000 per annum is also available.