Precision Medicine Doctoral Training Programme

Data-driven insights into Precision Medicine training

Precision Medicine Project - Data-driven insights into Precision Medicine training

Supervisor(s): Dr Kobi Gal, Dr Areti Manataki & Dr Michael Gallagher

Centre/Institute: School of Informatics

Background

Learning and teaching health data science is a strategic priority nationally and internationally [1]. For the precision medicine vision to be realised, we need to effectively train people at the intersection of health and data sciences. There is a growing number of training programmes, including this Doctoral Training Programme, the Data-Driven Innovation Talent programme and a number of MSc programmes being developed in the UK and abroad. However, Health Data Science (HDS) learning and teaching is so new, that little is known about the learning experience and best teaching practices. A recent literature search returned no papers describing research in this area. There are only position papers, such as [2], which mainly argue about the importance of educating medical professionals in data science. The few papers describing interdisciplinary data science education approaches for other audiences are not necessarily applicable or relevant to the health sciences. Simply put, we currently don’t know what works and what doesn’t in HDS education. Nevertheless, there is a growing volume of data from existing HDS training offerings that we can capitalise on. This includes data from the Data Science in Stratified Healthcare andPrecision Medicine1 (DataSciMed) MOOC on Coursera, which has attracted over 10,680 learners worldwide in the last two years, as well as from the postgraduate Medical Informatics course, which is offered to students in the Precision Medicine DTP. This data, which is collected from online learning platforms, is extremely rich, capturing not only student demographics and performance, but also clickstream information (e.g. interaction with lecture videos, accessing course pages, etc.). There is now the opportunity to harness the power of this data, to provide insight into the precision medicine learning experience and to use this knowledge to design personalised learning pathways and effective educational interventions. Artificial intelligence (AI) and educational data mining (EDM) methods have proved useful for providing such insight into the learning experience in several disciplines [3], but not yet in precision medicine or health data science.

Aims

The aim of this project is to employ AI and EDM techniques to provide insight into the precision medicine learning experience, as well as decision support towards the design of personalised learning pathways that are most effective in terms of learning performance. By utilising data from the DataSciMed MOOC and other related educational offerings in the University of Edinburgh, the objectives of this research are to:

  • Discover the learning tactics and strategies employed by students with the use of process mining techniques [4] and analyse their relationship with student performance.
  • Analyse engagement patterns with training materials, so as to identify the most effective types of teaching resources and curriculum designs for precision medicine.
  • Develop AI algorithms for personalised learning pathways, informed by learner characteristics and evidence in effective learning strategies and curriculum design, that can be deployed as an education support tool.

Training Outcomes

We provide a unique opportunity for the student to develop quantitative and interdisciplinary skills at the intersection of data science, health sciences and education. The student will receive training in artificial intelligence, educational data mining, learning analytics and computational modelling as applied to precision medicine education. They will gain experience in working with big data and they will develop a range of soft and transferrable skills that will prepare them for a career in academia or industry.

References

[1] Topol, E. Preparing the healthcare workforce to deliver the digital future. The Topol Review: An independent report on behalf of the Secretary of State for Health and Social Care. February 2019.

[2] Kolachalama VB, Garg PS. Machine learning and medical education. NPJ digital medicine. 2018 Sep 27;1(1):1-3.

[3] Sclater, N, Peasgood, A, Mullan, J. Learning Analytics in Higher Education: A Review of UK and International Practice. JISC. 2016. Available at https://www.jisc.ac.uk/sites/default/files/learning-analytics-in-he-v3.pdf

[4] Rojas E, Munoz-Gama J, Sepúlveda M, Capurro D. Process mining in healthcare: A literature review. Journal of Biomedical Informatics. 2016 Jun; 61:224-36.

Apply Now

Click here to Apply Now

  • The deadline for 21/22 applications is Thursday 7th January 2021.
  • Applicants must apply to a specific project, ensure you include details of the project you are applying to in Section 4 of your application. You should contact the primary supervisor prior to making your application.  
  • As you are applying to a specific project, you are not required to submit a Research Proposal as part of your application. 
  • Please ensure you upload as many of the requested documents as possible, including a CV, at the time of submitting your application.