Postgraduate Course: Issues in Clinical Data Modelling (INFR11195)
|School||School of Informatics
||College||College of Science and Engineering
|Credit level (Normal year taken)||SCQF Level 11 (Postgraduate)
||Availability||Not available to visiting students
|Summary||This course provides students on the UKRI CDT in Biomedical Artificial Intelligence with the opportunity to learn the challenges of clinical data modelling directly through guest lectures by leading clinicians who collect and analyse complex biomedical datasets.
The course is a primer in clinical data modelling, informing students upon the challenges involved in a variety of clinical contexts and in depth understanding of the data collection aspects in one particular area.
Upon completion of the course, the students will have acquired:
- The ability to critically assess and discuss the challenges associated with clinical data modelling across a variety of contexts and diseases;
- Familiarity with the data analysis techniques currently being employed in clinical research.
- A broad understanding of the scale and complexity of datasets across a range of subject domains.
Entry Requirements (not applicable to Visiting Students)
||Other requirements|| This course is ONLY available to students in the CDT in Biomedical Artificial Intelligence
Course Delivery Information
|Academic year 2020/21, Not available to visiting students (SS1)
|Learning and Teaching activities (Further Info)
Lecture Hours 16,
Supervised Practical/Workshop/Studio Hours 6,
Programme Level Learning and Teaching Hours 2,
Directed Learning and Independent Learning Hours
|Assessment (Further Info)
|Additional Information (Assessment)
The course assessment will consist of short written report (10 pages max) and a presentation on the data acquisition/ modelling challenges in the laboratory where the student performed the shadowing visit.
Topics to be covered include:
- motivation: why is data being collected?
- protocol: what data is being collected and how?
- analysis: which methods are currently used to analyse the data in the lab?
- possible developments: how could analysis methods be improved? what are the challenges to doing so?
- implications: what are the broader implications of clinical research in this area?
||Feedback on assessed coursework will be provided within two weeks, and will include formative comments on work in relation to concepts studied in the course.
Report drafts will be reviewed by peers, the course instructor, and individual supervisors under a provided rubric.
|No Exam Information
On completion of this course, the student will be able to:
- Critically assess the challenges associated with clinical data modelling across a variety of contexts and diseases, in particular with respect to noise in the data, patient stratification and regulatory and ethical issues;
- Present and discuss the data acquisition protocols in one area of biomedicine to an interdisciplinary audience.
|Graduate Attributes and Skills
||Students on the course will develop skills in using a range of specialised skills, techniques, practices and/or materials that are at the forefront of, or informed by forefront developments; In applying a range of standard and specialised research and/or equivalent instruments and techniques of enquiry; planning and executing a significant project of research, investigation or demonstrating originality and/or creativity, including in practices; exercise substantial autonomy and initiative in professional and equivalent activities.
|Course organiser||Dr Andrea Weisse
Tel: (0131 6)51 1211
|Course secretary||Ms Lindsay Seal
Tel: (0131 6)50 2701