Transparent and Adaptive Large Language Model Based  Systems for Personalised Cardiovascular Rehabilitation

About the Project

Large language models (LLMs) are increasingly being explored in healthcare for their ability to interpret complex guidelines and generate personalised recommendations. In cardiovascular prevention and rehabilitation (CVPR), they could support the shift to home-based care by producing exercise prescriptions tailored to an individual’s health profile. These prescriptions could consider both medical data (such as clinical assessments, lab results, and validated device measurements) and everyday data (such as wearable activity trackers, home-monitoring devices, and patient-reported exercise experiences). Incorporating these data sources e.g. into the prompts for an LLM, alongside CVPR exercise guidelines, has the potential to provide more personalised and adaptive prescriptions. However, challenges include reliability, adaptation, data governance, and trust.

This project will investigate how LLMs can generate safe, personalised, and guideline-compliant exercise prescriptions while integrating both medical and everyday data. This will include explainable AI (XAI), ensuring that recommendations are accompanied by a clear rationale that clinicians and patients can understand. The research will also explore how feedback from patients’ exercise sessions can be used to refine and adapt future prescriptions, enabling personalised and evolving support.

By integrating diverse data sources, continuous feedback, and transparent reasoning, this research aims to develop trustworthy LLM-based systems that can support both clinicians and patients in home-based CVPR. It will also examine how explainability and data integration influence adoption, engagement, and safety, helping to define the role of LLMs in the future of personalised cardiovascular care.

Academic qualifications

Have, or expect to achieve by the time of start of the studentship a first-class honours degree, or a distinction at master level, ideally in Artificial Intelligence, Data Science, Computer Science, Software Engineering, Information Systems or Health Informatics, but would also encourage applications from candidates with interdisciplinary experience combining computing skills with biomedical or health-related subjects. Applicants should have a good fundamental knowledge of Machine learning, Natural language processing (including large language models), Data analysis, Programming

English language requirement

IELTS score must be at least 6.5 (with not less than 6.0 in each of the four components). Other, equivalent qualifications will be accepted. Full details of the University’s policy are available online.

Essential attributes:

• Collaborative, communicative, and adaptable - able to work across disciplines with clinicians and researchers
• Good at problem-solving and critical thinking.
• With curiosity, initiative, attention to detail, and ethical awareness.

Desirable attributes:

• Experience of applying Computing or AI to health related scenarios
• Experience with explainable AI

When applying click here

APPLICATION CHECKLIST

• Completed application form
• CV
• 2 academic references, using the Postgraduate Educational Reference Form (download)
• Research project outline of 2 pages (list of references excluded). The outline may provide details about:
  1. Background and motivation of the project. The motivation, explaining the importance of the project, should be supported also by relevant literature. You can also discuss the applications you expect for the project results.
  2. Research questions or objectives.
  3. Methodology: types of data to be used, approach to data collection, and data analysis methods.
  4. List of references.

The outline must be created solely by the applicant. Supervisors can only offer general discussions about the project idea without providing any additional support.

• Statement no longer than 1 page describing your motivations and fit with the project.
• Evidence of proficiency in English (if appropriate)

To be considered, the application must use

• the advertised title as project title

For informal enquiries about this PhD project, please contact Assoc Prof Lawson - a.lawson@napier.ac.uk

References

Boonstra, M. J., Weissenbacher, D., Moore, J. H., Gonzalez-Hernandez, G., & Asselbergs, F. W. (2024). Artificial intelligence: revolutionizing cardiology with large language models. European Heart Journal, 45(5), 332-345.

Dergaa, I., Ben Saad, H., El Omri, A., Glenn, J. M., Clark, C. C., & Washif, J. A. et al. (2024). Using artificial intelligence for exercise prescription in personalised health promotion: A critical evaluation of OpenAI’s GPT-4 model. Biology of Sport, 41(2), 221-241.

Pedroso, A. F., & Khera, R. (2025). Leveraging AI-enhanced digital health with consumer devices for scalable cardiovascular screening, prediction, and monitoring. npj Cardiovascular Health, 2(1), 34.

Martínez-Cid, S., Vallejo, D., Herrera, V., Schez-Sobrino, S., Castro-Schez, J. J., & Albusac, J. A. (2025). Explainable AI-driven decision support system for personalizing rehabilitation routines in stroke recovery. Progress in Artificial Intelligence, 1-23.