Postgraduate Course: AI for Health & Social Care (HEIN11074)
Course Outline
| School | Deanery of Molecular, Genetic and Population Health Sciences |
College | College of Medicine and Veterinary Medicine |
| Credit level (Normal year taken) | SCQF Level 11 (Postgraduate) |
| Course type | Online Distance Learning |
Availability | Not available to visiting students |
| SCQF Credits | 10 |
ECTS Credits | 5 |
| Summary | This course provides an overview and introduces core concepts concerning data analytics methodology. It set to enable learners to grasp the key design element of robust Decision Support Systems (CDSS) in the context of health and social services. It uses both fundamental and advanced statistical methods to explore data, time-series analysis methods to analyse data, and also an introduction to statistical machine learning. |
| Course description |
Academic description
Leaders of digital transformation in the health, care and housing sectors need to understand and master a diverse set of skills. These are necessary to successfully tackle increasingly complicated problems, when faced with real-world data. This course aims to equip students with the core knowledge, skills and understanding to work on a diverse range of problems amenable to data processing. This includes understanding the requirements for collecting high quality data, understanding practical limitations and trade-offs, in the use of different devices and equipment, and understanding the questions that can be posed to different datasets. The course also covers various approaches to process and visualise data, to gain important insights when applying statistical algorithms for machine learning. The course will also look at indicative practical examples, from Scotland and beyond, to highlight
some cases where processes work well and where they are not. Adopting a data analytics perspective will enable students to critique (insufficient data quality), (inappropriate) statistical test use, development of insufficiently tested statistical learning models, and more.
Week-by-week content breakdown
1. Introduction to data analytics and workflow
2. Data collection, quality, analysis and visualisation
3. Signal processing and time series analysis
4. Statistical learning, model development and model assessment
5. Decision support tools with practical examples
Student Learning Experience
Students will learn from experts who work in leading and managing data analytics, machine learning and clinical decision support tools. The course is delivered online and is divided into five sessions, each lasting a week. Teaching sessions will be composed of written materials and video presentations, accompanied by guided reading in the form of links to journal articles with problem-based learning questions.
Discussion of the content and reading materials will be posted to an online forum, along with students' answers to the problem-based learning questions. Course tutors will moderate discussion boards. Students will be graded on discussion board postings. Students will further evidence their learning by writing a management plan for a case study from the health and social care sector by the end of the course. Formative peer and teacher-led feedback will be given throughout the course through the discussion boards, and summative assessment feedback will be provided at the end of the course.
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
|
Co-requisites | |
| Prohibited Combinations | |
Other requirements | None |
Course Delivery Information
| Not being delivered |
Learning Outcomes
On completion of this course, the student will be able to:
- Critique data quality requirements, in the context of health and care, for further processing
- Appraise the use and limitations of statistical tests as they relate to their own domain of work
- Critically review the full cycle of the data analytics methodology including data exploration up to and including statistical mapping
- Understand how statistical learning models should be developed and tested to ensure they are robust and generalisable
|
Reading List
"An introduction to statistical learning" by G. James, D. Witten, T. Hastie, R. Tibshirani. It is freely available as a pdf from the authors' website. I would encourage students to download it, consult it and use it as a reference. The book has some lab sessions in R, which nicely complements the presented material.
A. Tsanas, M.A. Little, P.E. McSharry: A methodology for the analysis of medical data, in Handbook of Systems and Complexity in Health, Eds. J.P. Sturmberg, and C.M. Martin, Springer, pp. 113-125 (chapter 7), 2013 |
Additional Information
| Graduate Attributes and Skills |
Personal and professional skills
A willingness to engage with the material and learn is by far the most important element. If students are already using programming (particularly in a high level programming language such as MATLAB, R, Python), this would be very useful to complement their learning along with the material in the course. However, programming is not a
requirement and will only be provided as further optional material. |
| Keywords | Clinical decision support,data analysis,machine learning,statistical hypothesis testing |
Contacts
| Course organiser | Dr Thanasis Tsanas
Tel: (0131 6) 51 78 87
Email: Athanasios.Tsanas@ed.ac.uk |
Course secretary | Mr Matthew Newlands
Tel:
Email: Matt.Newlands@ed.ac.uk |
|
|
University Homepage