Postgraduate Course: Biomedical Data Science (MATH11174)
|School||School of Mathematics
||College||College of Science and Engineering
|Credit level (Normal year taken)||SCQF Level 11 (Postgraduate)
||Availability||Available to all students
|Summary||This course will introduce and discuss a large variety of situations that arise in the analysis of biomedical data through examples and assignments carried out in R. Starting from the ground up, we will be building a collection of well-written scripts and functions to perform increasingly sophisticated analyses, with an eye on reproducible research, self-documenting code, correctness of procedure, interpretability of results, and presentation of outcomes of the analysis.
The biomedical setting is rich in opportunities to apply mathematical approaches of different types to the analysis of patient data. These range from routine data collected from national registries, to collections of high-dimensional biomarkers measured via high-throughput techniques, to genetic and sequence data.
Most often the data measured is noisy and fragmented. Moreover, it is more and more likely that the number of observations available is far exceeded by the number of variables and features available. These are important challenges when trying to use data-driven approaches in understanding the data and building predictive models.
The de-facto standard programming language adopted in analysing biomedical data is the free statistical language R. This provides a flexible way to perform all types of analyses, from the simplest to the most complex, thanks to an extensive collection of packages.
Entry Requirements (not applicable to Visiting Students)
||Other requirements|| Prior knowledge of basic concepts of probability and statistics is recommended
Information for Visiting Students
|Pre-requisites||Visiting students are advised to check that they have studied the material covered in the syllabus of each prerequisite course before enrolling.
|High Demand Course?
Course Delivery Information
|Not being delivered|
On completion of this course, the student will be able to:
- Understand setting and complications related to using and analysing biomedical data.
- Discriminate between interpretable and black-box models.
- Manipulate, impute and filter data to setup correctly validated predictive models and construct predictive features.
- Understand and solve difficulties related to using high-dimensional data.
- Write well-written and modular R code.
|An introduction to statistical learning, by G. James, D. Witten, T. Hastie and R. Tibshirani.|
Introductory statistics with R, by P. Dalgaard.
|Graduate Attributes and Skills
||Priority for this course will be given to students studying relevant masters programmes in the School of Mathematics. Students from other Schools will be admitted if space permits. Please contact the Course Organiser.
|Course organiser||Dr Joerg Kalcsics
Tel: (0131 6)50 5953
|Course secretary||Miss Gemma Aitchison
Tel: (0131 6)50 9268